SEMTEM_membranes_TrainedNet/0002755001645100001440000000000013337127206015561 5ustar mhaberlusersSEMTEM_membranes_TrainedNet/5fm/0002755001645100001440000000000013337124762016254 5ustar mhaberlusersSEMTEM_membranes_TrainedNet/5fm/log/0002755001645100001440000000000013337124765017040 5ustar mhaberlusersSEMTEM_membranes_TrainedNet/5fm/log/accuracy.pdf0000644001645100001440000005557313337124763021340 0ustar mhaberlusers%PDF-1.5
%
3 0 obj
<< /Length 4 0 R
/Filter /FlateDecode
>>
stream
x}K%7>ŷ,-tcil=7B/fmL
I9R7<O/w>߯^G e+_+|^o^?ޒ~+y?y? a5b+Y55y{xo^܀H_6}Cj˨?_~~>OﾏS?~k}kqEõzV9&܈=CnJфfJ2f1!A
٣b01{>+Y|n91Xx`Fc1{V9̎&ܘ=+0^?Y혥
oLuM|݄ګ/c3f&kوyb=7ZgJz<+p_A/oaUo`i/=~ǣV:,ǛWYj)~ÿ&*h_0UF>ۭTaK֩oE~e
v|=NXz{qac}b֏7s#07oŪC[ng?0q;W j~|tWB+ߌ/CgKr0a SKU
c|qW{ʵdyw~ˑYU#[ ܱ[~-TA.D*+l.?eSЃhB7jTo,84 W~@ze^ehvj9GzB'7.϶2N+W
~ ywAM)
\\#FzK:lV_Ы;CbqUcat\'oX_1}B2W]d !/,\42I+V@!}v$m5)}-p`"*fmh] ݒpqeY]%S$;*ɠP쏐߂}KθX mV>8}>fV^XZaAhȄ,6AFCi}4j"&T_ݖvyd;/d,+hPzM&Gh`5lωީ93m',a``ڂc+eݳs
p[dlXK9݅dM2FNw5'!jX{cC{Vv
TXρ1r%á%9d|R/[7UL
Qȹ,-[uc@J9/Z5z߂~qsi|>ZVlp&h_qC&Hޫc2nT
S'Q'BFBJUs./XQ|MlPSVu~3:mٶlvzP.Gi>sBerK`[1)C#ߧ;)`šbjΊǠ7;i~Ш[6]
8t/,5lR_.m$h7hqtm5!NoNGe[-~N@8E
\8ThMs\ oUmKS
(ns"### Rwl
¾0}a`!:|v_`V[ͯ4-k5\Q,;
ڜ
ܹ9O>L݊
7]U>Z` ks2:[x6m{iV.W}s,cxZ7FCw;F_Toup7Qּ8[=YM7}:nA;̍&fpJsq^u_.X̔>0FX~Ãp37
^a8g5
;6]ުi#}#C
α"oG4p[\f8KD][Fh^p(;;|Fe7S
ȘhGzxj!P sj^K01`p>h֠!XtH[=X9A0:2vZu7ǰ~Eۖ
Ʋ^Wwm>3H3>@
WyaWw1T%`v;aЗ=)2dTh@?-sH4%+ҔruZ_ Hx-CƢɓ9X]u8'In{S$Ntqx)g<%-
=P^ ӑLט]E>'v.HW)n`$[<)Y=PP,/UO30ij"J lJ*l
z^uG[wƥHFRwMnTsRgKѫbp3Х|/{{FuVLK@[1-O[:t˗d)hKAA[c;EK'IצLH3̆8uYqDpFb!Vĉ_n,Y?/EEn!_c:f+>${P6,}O5sQq`Sp6ۍ}/yZ!Esv<8d2(6 m7{'&}obs`ޙ7AL Xxm#\;|kI=>a
nwwyzB6;&CLNgX^:,VWfj
vyu/DNb
`p7L:#,oba&E4G6)Vɟ79ު.;;#fSFhFOqbvτTxdUZʡVqה
gf!ԇ)Ob|$-Fv
0zВŌ{suI/T=A!W{ `eR;4=&6zfIzIPKzRӞ䞄%hrjF5#n$d6nԍz\"%pJ9.w+3#!`z
wJ",^GPfGy3Br^bzʮ;is
ೂDN.^0=ereʹS<
xaQvBv
wS*9IF: #wG2ƻ9q57=Kf^Иe-ސIgu=+ecl0OV{g}SaB[uCq1n8SR`lKߤ{Z?$NZ"R{ݬqml
M30h3k0 y`>n
P0fۯ%֧glhv| 5Ⱥg!^k\
H`R}Gw6ƃxutHF4g>Ǹ&*;Z'Ii]azS, |`&ѨmQV4fEEjKx@"w/^]vЁԻ=+FĎ1"o髕V qV._
3nH+HKN(0i#TRj/{\uC.|P]`OD"aO,nSDσȔpAPC-0<2Ny).o"e]wn>HNzTatE]"o9iU5&!4P]gof_q-9n]M\H3 j-6Cѡ[7ͣpKnZ ֠k.hFW2'ET0i{&o#[D^StZhԽU| N͛Oŭ wk(4F뚂lR_;L0w^ zaAk
/Ae; uPouOɱv51T]=j^BS!4*"`ژjcjw3MB8ljTv"&
udH˨1ItuEmǰ15P;dwUF+b;Xvx=^qDLLBoC8eqt{;r"waz_yٵ
XF;#a\Cq!Q1%>щEj3C{j寃2(~:Fƽ\i+ׄѤ%X-CAF5!TשTNwH`]!}UNщdU3ed>We+̷dVD6҇*!{\YSoBpej=,d|3E+b\ǁ^JNSB`\5b #u[L,2WEF;X\. 0.Ÿ)."؇5%2=4@E?m7p/&֊{L di~J#4iHf3G#
PbD'llMdT+-;l¾vn&2d,l*t** ߗحʑأrcP"]' avn(nv3~9k!pnnpM4S{+TƔTxK|iB)
,q+,mIDHh8;ҒY|*ȆU]K"Άذl4g]RQN0Դd_]ҁtͲ (5nPX3)YżkIZwrQSSXn0.|b%kIK
:`k5\9|
ټ4vJߠgtC")xL{E4f(HfBrkD+\
|BT8|B(Dv֣'J}-0ͤξI /{"`Aw_Ty)RtVB{aVkIN\`N{ZoJ"Oh2r2 YX߭!N\1IcJX]AaqD5ܸ{s5UPr Ђ% fArzz[CCNjݑDaXL]?SW0߅CG3zտp+ESe^Ba0ƾ@9Ƅݎ$bHåZ`ݦ
Εbd
PEl Iڣ33XMFG#
pb~B$<ʦIX\C2/ֽDSUB*̶1hIu1y~z%n+3Ol[0YBiM F`ķM|:Ǉ-.:o߰dszaUOʸܯP6_`
CȺcc>6"A|CI\۳@y=[FKRE('"B~?4r/lI8
so w_Pgb8
,@kJ|:Z?7]>SHXS_ܳh@bQgW| V4Nv2Dya(sy-I+#oKC@d'W_):,o:]w9SlQq/'SbY_n
'jz4X`cf|M&0]O1;k
n7\>P!@]d0ư1,6=mTySm.UIkf>*aJsh;D廖d~vw3~p0ZR;ǂ&a8w`|vF~EH+29j!Q`nLYhaD&gϧEH$5C"(~@š2 m*a#VL4YhX\-PD0)9fi(|DٓVYmbq/8 A)a@g;zze|gZ|{
ꌢ*8mC{L@a~4JbD})
A̱>mT`n|P!GmJ`qf-ږ%;;|WTe>HF4>%]QF+#9@-cR`>`T=B**~~)ybfg$L4'pH fR劖0pRUH02i,jB[W2nbLu;9UBYn'
e_u2i#vLJՅbe_pQO4 [@`O :]cɜ>ԉqkYfQ!̰7)#ߗ2>ioJ &A!}ł?2H{"gqb@ gb.L ̇g͂9X0ya)F͊YA1͙@f0,ɧn`k|H9Je-Nk0xE3u`1NV@0seHGavZkP0Zߕdb}yJ`/(&7qyǃ+8qE_=;gb*1iPUAD;{2N}kL.[
Edg" 8XHJW]`!eA ~Ŕ߶oC?-Qr*f"dDaL2p
95 V&9N ,$0|zMIcX9@3}E;2As0i0<n$܂7jl]Ño6qhۉqOaf~4:ja܃**1qێNXu{2"sb\7p#AkC_
g ]tF&hp1
ƶ68GFM_{H5p±ioM{6tRPi~~__ ECF$ܜǼ=YV#zV]ȁaU(/yFVUa<$x>\>vv%6vڴD۹z҄EkcWt`w8{kETF?_lMZ{㴷d@+yof˱?;.@ZxspRja_(CwOC$"].[bzSo
JZ1B;+FjPpuF^h$VF:%|m"2(aB-[lG]69u~_WD鳆h=2Q%Ɲr2})P=p@
"4aiה@8!s{)C ̾p|>l&Myx c%DО|YKk+?
CCp)';8l k>h0A69==ρ6'33;w_ތMC \āvA}Gi3l$ϛ#]I|[QH\. r1^C')w4@V.;7qe#=WA:Qq-fX!Y VocݓoV";ue&#}~Gy{z]GD/vyBDuÑP)xc]y7#xCXռvQ'9Uyjil0K?@!1V
rxCq~+4DaG><&@0o #C`C7 σ( B;)̎@uJJ`Rñ%!̧{5QSĀkhdCdFS/C6BBa){Gw~=թT}E.QiE~9㈹c̍ )A}*"Q[}{&/eo9+AY VZP{QA%I+fO+K)5;h G\9fY쪎9A9o coξu,R±Oe^/MȏE7b8+!*\)g9-T:oGn
Vp]9G+Yt
K)WOH@.3dSr/8Xnۋ<+,sb+8WNn!V,`mQrS(½)9Εӂ<N\"%)Q/=U?`/ys0"Y1[V]t ^`;IV'Kcۻh8[c(NE%IJ'$)P71p9-Lr7ᐒ>M6IZG>y(ﰤMHʤ1s]f9)~u>'!X:me)YUYK)wTQש?Vns)h'cݒBRT9ya?Zst2Qi~:ѠAeФLc-X"itlv(5*QX#e
:mmj"K&jpg` >C9.V:hGX-1x8Q20\O\&x[hD`ޝ)yN;tL#6%vL\*kR2Y|Õ GMT^txJԘl3@Զ9B 1_˴HƊL,8en۸\%*O'}E"Hp͊1w%k+QvDF4e~pzp7탛WD0 DQGbc~ŏLe;<](*).,(RG=~>#Wk('uŵ$,L'D|ۑ `3H(^
mϧ`RBg]YdbԮcJ/>
cf2nq
;lUˢxe`\x^Dc2Vd=MoBDK<(ɭ4NkY:=488C(v^1*3s0Twԝ?Uf{H9Grf$40#%C;~'^/N;Z\q4ajX}>1ks?Cڙb¬M[0Os/fr$pU'lN{.O#ٷU$8Z+&+&:h;6k\t*`+AکKlr#TGwcpb
W`<>`9ޢ46gm"49%}`UJ?TTXP-kJr uG%H稬̋3p$'?T2y9gʹP<tO5+ZNo$̝;1{)
L1>w$D#
p9l
N3ȎZs- ",8HNڥ6FlMD:got;⑬גp8*t Qvϡ
l,Qw`j2]wcN+`RpEgPúrF
[/H>+!m3Fvvy/?d9q|`eΓ5Px.uCsN,;QvM2
Ou~f&Zc/g⑪ZzVA
DhaI@R]Ct%ߕx*Uy֤D hi5L(Ql#]LwúصcLtcIͻٙΆk;0
l"!VLW7sE9>_
_Y>Pcȓ{gƱۈ
Ł|~> *c:п/aΤ+ЈKH
W
KoHL4k4LQ)8en+Py,8,QgEYz+It(/0~h)&%dRV\X`rC{ĨzE1iw^'ruhMt7VDCvhnG_ s@48boOg2,`2Bx$fj>靂g}I|F >$?+^p"m<^5|XwJ5W.UoAede{旅PpDPd}%6c#_A
=vIX0m@"?S-DPVp_i>!ڂlB#G5]~6y
G`aG,S)LYPxvb8TNn gg#'t4<.
0cKˉYTz0prf+ۦ6Pt
w
䖗I 2OY;~e13RKD'%p堚1+>=P)PH-8VYK>"uܵlSuLo\A6*SE.
;4`=c GN}e!ñqJ3N6
X΄s8p@fq^(%O}w8vrbU)ހ^mBeq^>t$~ԛ/m
;[
Q0*&kY>~wyz
endstream
endobj
4 0 obj
14695
endobj
2 0 obj
<<
/ExtGState <<
/a0 << /CA 1 /ca 1 >>
>>
/Font <<
/f-0-0 5 0 R
>>
>>
endobj
6 0 obj
<< /Type /Page
/Parent 1 0 R
/MediaBox [ 0 0 576 432 ]
/Contents 3 0 R
/Group <<
/Type /Group
/S /Transparency
/I true
/CS /DeviceRGB
>>
/Resources 2 0 R
>>
endobj
7 0 obj
<< /Length 8 0 R
/Filter /FlateDecode
/Length1 8792
>>
stream
xY{xU?NwwU;Nwф 11@M O !%< AB
Eǈ'$7{C盙orwέ3TSK?j6 r&4y0+> Gsb}bQչ}?q挩ǟ ̤vóTCO>p
)zOqTɩKg9Tҧf1^=m|&HP"j5@l*3rIwzbkF:b\`ủTZ3 )w6y^ՎkZ-Zի,QTgVSSLTHJ5[_z^z37nyqyE,+$JQ%g"8|D?@X!i; 5c`;qۂ)1qѸ0ey[ȵ^YbfOJ1Ν?.2uN*$89sM2c'T<SȂʓ$by1WcAc8y+b=Y1c-=qHp'dw;{%%*YVv)Xtc kVdǈk{]~r=wGo|Wit9m%]%{Ci?#̕&_?"䶅LOȿ!iJj'W=T]=0%@"J|֖k-WMr`ASwo8A).9!WJX@|0_/9X'num0Ss~i#晍-Ku}jPLz/ћ
mhh18e&f5G1V:1f3f85S5rqhk&V|{VWjQP`C$K^,
g֟&6-ƕF4$-!!1-.]:t|;+z'mb= &ɱR
\!&`ma7xvfTu|a;U)H4u'lLӥnD1>1}Y(}䝙O<^qwdpr/e_C׆
*TB]jZ6`M4ybLUɐZ ]K̛W¦D즖D {XIp)\}**4qg.8|2S)<7Ertǎ㨴>N|_?f兰^s噤&LI'ȑqI!6wa"&v$eMךZp-6$geFpvۤ;D ֬۵kݺݻĮ>=~s7lXb-UU[^2w}?T͇_~a)6˟eS$/UBLȼKAu/\0x< ^HLfCD/=Vv쉸o{|FWN$qg,n[Iz#)\u,YOI`&iQ>fcI?g`ᠴ]<6ؓn3f&͘!tÐ,2LFA1z2W[œa!9@,M@FN+ӱsfJ|i >%/0,4VURi3QIA? 0IjW(\yU/V]<ОŲe8dd{mA굵
FFĪ-=6#]U8Ըuq8N0nD+_{ԩ7^)֏)}vgii{ΜlpRX'ȮpMvTٵf誷LFedzӚǝLTqh[bS",%)[;Pd_ƼgQiwۏnLo=lqѠAb1f*{`V`ϩCCxkMNt(/b{m˺eA+˭#ldՆGWF!|\td:aˈ~HekQJ]WzH%QVhCkD/bnmjA*:F+-Gˈf2 )7 ļ<2:Ȗcqdh@ *AC84<6>a =yr6Zy(3,eV6-v$eT$:knin<0ē&`/ivop[XB8F%O3:<̎"9|:Z8I*\.9Do?IJ6}CGzM,SGXnxjr-އKiϥm/o=JڶYE%Ƙ1;Yc05D:6ŀ92ڪ:aE~N]8\H4|t^z|<,{U/F9:W)ʕf*SEƩ{ICeqtJ73UWqk7Xٱgu'-F+9#<rSXzXNu2wy.\)םҍ馾0͖fgǙCWB8GpnC,n;Zy>.,Sfv`|wӗ
bflt6__*ۈOz;7:5Uf$`T03a^Z}X9pY$%Ct~zehl++}K;6vMgzKE5n|#ܐù[L(r}nr+)r^Ob?b=0y'OI;u߾Mw{rҾ);MPU[&ĭ<3[>M9_tWG9_^gvѕ8\lm!Iד@0ۿiCOzڟuiye?Eޖ>twTjBrJRi9uIbV,hEс*`,ơG7"<"u]j(-5@|Ώ9/DI#grusv]w(95u^s`ﳹzᤤمolsnPH0Eָ%12{p=g
^( uM#|2.hP e=X9^*7,
C|2
Fhy4$D%a>ɋ<lRRI` (ͤ1.yb^U{&MdMAǋx)ov$? W0P+,wI|7<G+FylO**ӿZ]4x:cp?#T_z~=a~=t>ɺ Ol(GJ1mTj졲2*"PÝpQ
ɍpf8]
sh=?{.IL4稜56;&éFDS@6ݎsvӎg7O$ӆ&,3T)8C` :+N̼Pd(' |v~pq"Sh|D ,3Wx8NX+ph6>ZQ6)ZQ+cxX
x]N~w9qr#p@Ԏ|d[-xlyg
ÂatgUg¾'ӊO `{x{0%ˁ&L3bXc
=$Av1T]Q$(4)2]#:iSPߏkP]bY#MF[#"ЬI\Ӊ@2YE
KY=+^,Kp6i
2
endstream
endobj
8 0 obj
6365
endobj
9 0 obj
<< /Length 10 0 R
/Filter /FlateDecode
>>
stream
x]n0Ew}t0P>дHTj ::x/ISٱݸ=343^F'RQEŧmYqꝝE#.kg|R-[?8[e.NeÄ2K}on(<2}\
.~wAy'[k;;nCmEyі8.qbk暸an"~d~$>0"r\ʥ_zSgT?1ĬeO ϒ{/wo^w\@憵MjĬ
i>
endobj
5 0 obj
<< /Type /Font
/Subtype /TrueType
/BaseFont /GGZOGZ+DejaVuSans
/FirstChar 32
/LastChar 121
/FontDescriptor 11 0 R
/Encoding /WinAnsiEncoding
/Widths [ 317 0 0 0 0 0 0 0 0 0 0 0 0 0 317 0 636 636 636 636 636 636 636 636 636 636 0 0 0 0 0 0 0 684 0 0 0 0 0 0 0 0 0 0 0 0 748 0 0 0 0 0 0 0 684 0 0 0 0 0 0 0 0 0 0 612 634 549 634 615 352 0 0 277 0 0 277 974 633 611 0 0 411 520 392 633 0 0 0 591 ]
/ToUnicode 9 0 R
>>
endobj
1 0 obj
<< /Type /Pages
/Kids [ 6 0 R ]
/Count 1
>>
endobj
12 0 obj
<< /Creator (cairo 1.14.6 (http://cairographics.org))
/Producer (cairo 1.14.6 (http://cairographics.org))
>>
endobj
13 0 obj
<< /Type /Catalog
/Pages 1 0 R
>>
endobj
xref
0 14
0000000000 65535 f
0000022806 00000 n
0000014811 00000 n
0000000015 00000 n
0000014787 00000 n
0000022351 00000 n
0000014920 00000 n
0000015134 00000 n
0000021593 00000 n
0000021616 00000 n
0000022057 00000 n
0000022080 00000 n
0000022871 00000 n
0000022999 00000 n
trailer
<< /Size 14
/Root 13 0 R
/Info 12 0 R
>>
startxref
23052
%%EOF
SEMTEM_membranes_TrainedNet/5fm/log/out.log.test0000644001645100001440000051236013337124765021335 0ustar mhaberlusersNumIters,Seconds,LearningRate,accuracy_conv,class_Acc,loss_deconv_all
0.0,1.517228,0.00999856,0.296045,1.0,87.3365
10.0,34.30642,0.00999856,0.320941,0.999484,42.9352
20.0,66.821229,0.00999712,0.327685,0.958302,11.5041
30.0,99.339241,0.00999568,0.353909,0.936765,9.47416
40.0,131.857486,0.00999376,0.498358,0.513953,2.11004
50.0,164.377375,0.00999232,0.612194,0.443657,1.1527
60.0,196.904503,0.00999088,0.703807,0.500021,0.807287
70.0,229.431407,0.00998896,0.720267,0.578775,0.628091
80.0,261.962739,0.00998752,0.714088,0.559617,0.628931
90.0,294.494162,0.00998608,0.724358,0.454427,0.559474
100.0,327.022859,0.00998416,0.725941,0.602062,0.558138
110.0,359.549786,0.00998272,0.7438,0.592007,0.530425
120.0,392.075051,0.00998128,0.744954,0.628582,0.518914
130.0,424.596914,0.00997935,0.751475,0.515245,0.522446
140.0,457.124604,0.00997791,0.751874,0.506932,0.527847
150.0,489.720694,0.00997647,0.749123,0.564821,0.513753
160.0,522.297555,0.00997455,0.743229,0.536439,0.514882
170.0,554.826851,0.00997311,0.75004,0.571319,0.507214
180.0,587.353089,0.00997167,0.765924,0.51231,0.484631
190.0,619.878657,0.00996975,0.745583,0.466005,0.502257
200.0,652.413028,0.00996831,0.758484,0.571312,0.501877
210.0,684.939521,0.00996687,0.76152,0.524117,0.490234
220.0,717.470467,0.00996494,0.755789,0.56491,0.492313
230.0,749.995891,0.0099635,0.771313,0.500078,0.462048
240.0,782.519017,0.00996206,0.760828,0.504456,0.48268
250.0,815.050717,0.00996014,0.761487,0.365759,0.477394
260.0,847.578762,0.0099587,0.75888,0.399027,0.486537
270.0,880.103222,0.00995726,0.725958,0.248989,0.552182
280.0,912.626615,0.00995533,0.757397,0.338605,0.486538
290.0,945.157798,0.00995389,0.733865,0.206461,0.562184
300.0,977.689934,0.00995245,0.75165,0.414423,0.491345
310.0,1010.217335,0.00995053,0.735689,0.337835,0.5129
320.0,1042.739514,0.00994909,0.744989,0.276529,0.516958
330.0,1075.262669,0.00994765,0.762744,0.429844,0.475258
340.0,1107.78851,0.00994572,0.747518,0.306316,0.520854
350.0,1140.317356,0.00994428,0.747787,0.359097,0.499076
360.0,1172.845607,0.00994284,0.758302,0.395457,0.478758
370.0,1205.380677,0.00994092,0.755896,0.427059,0.498689
380.0,1237.902746,0.00993947,0.752435,0.483551,0.491154
390.0,1270.423156,0.00993803,0.745466,0.258035,0.52764
400.0,1302.938502,0.00993611,0.758494,0.498142,0.478185
410.0,1335.467044,0.00993467,0.712171,0.220005,0.654926
420.0,1367.99518,0.00993322,0.769601,0.611899,0.469957
430.0,1400.516267,0.0099313,0.753081,0.311392,0.511101
440.0,1433.034689,0.00992986,0.766772,0.30959,0.482253
450.0,1465.551607,0.00992842,0.744351,0.350286,0.54976
460.0,1498.070257,0.00992649,0.73334,0.381021,0.520097
470.0,1530.600119,0.00992505,0.74155,0.437992,0.513776
480.0,1563.13218,0.00992361,0.765776,0.418619,0.471067
490.0,1595.658461,0.00992168,0.727892,0.393948,0.582534
500.0,1628.188019,0.00992024,0.750634,0.352794,0.496534
510.0,1660.710933,0.0099188,0.721031,0.167547,0.646255
520.0,1693.229636,0.00991687,0.739484,0.388059,0.50962
530.0,1725.754101,0.00991543,0.751754,0.368597,0.506659
540.0,1758.276843,0.00991399,0.757854,0.417669,0.491431
550.0,1790.80116,0.00991206,0.740381,0.309554,0.537817
560.0,1823.328462,0.00991062,0.739168,0.357205,0.534549
570.0,1855.858699,0.00990918,0.765464,0.448464,0.474927
580.0,1888.375013,0.00990725,0.748623,0.269319,0.537195
590.0,1920.897362,0.00990581,0.748366,0.311727,0.520854
600.0,1953.415813,0.00990437,0.753151,0.354482,0.496833
610.0,1985.936517,0.00990244,0.741414,0.309421,0.546626
620.0,2018.466778,0.009901,0.769159,0.515761,0.476081
630.0,2050.99003,0.00989955,0.778155,0.485399,0.454585
640.0,2083.513292,0.00989763,0.76732,0.560379,0.483476
650.0,2116.040501,0.00989618,0.778275,0.453052,0.467973
660.0,2148.571494,0.00989474,0.788716,0.615393,0.44733
670.0,2181.092514,0.00989282,0.77762,0.435199,0.471081
680.0,2213.622276,0.00989137,0.780173,0.44479,0.456916
690.0,2246.154328,0.00988993,0.726094,0.235124,0.614329
700.0,2278.688493,0.009888,0.77383,0.399004,0.468625
710.0,2311.221468,0.00988656,0.77138,0.50819,0.478387
720.0,2343.751683,0.00988511,0.761797,0.364234,0.497128
730.0,2376.27167,0.00988319,0.786272,0.485339,0.447377
740.0,2408.795825,0.00988174,0.70293,0.270407,0.627942
750.0,2441.323255,0.0098803,0.767082,0.336168,0.497245
760.0,2473.850279,0.00987837,0.781836,0.52389,0.465409
770.0,2506.376136,0.00987693,0.784166,0.567283,0.448134
780.0,2538.904434,0.00987549,0.768465,0.353484,0.505208
790.0,2571.435259,0.00987356,0.777901,0.424494,0.457228
800.0,2603.965122,0.00987212,0.749808,0.343193,0.553364
810.0,2636.498034,0.00987067,0.774467,0.353989,0.496054
820.0,2669.027658,0.00986874,0.775263,0.490175,0.477457
830.0,2701.54668,0.0098673,0.787827,0.643727,0.452454
840.0,2734.07505,0.00986585,0.788311,0.534865,0.444796
850.0,2766.609638,0.00986393,0.802463,0.591431,0.425476
860.0,2799.138497,0.00986248,0.793521,0.611592,0.425237
870.0,2831.667459,0.00986104,0.792426,0.665695,0.447729
880.0,2864.20006,0.00985911,0.805534,0.644698,0.421102
890.0,2896.725418,0.00985767,0.766825,0.387163,0.524276
900.0,2929.257632,0.00985622,0.801057,0.670431,0.437589
910.0,2961.787189,0.00985429,0.798962,0.686444,0.431052
920.0,2994.312091,0.00985285,0.812063,0.563008,0.406558
930.0,3026.851299,0.0098514,0.824213,0.613616,0.382101
940.0,3059.381519,0.00984948,0.776408,0.568478,0.485391
950.0,3091.915609,0.00984803,0.807713,0.52052,0.409426
960.0,3124.455418,0.00984658,0.81768,0.58204,0.401427
970.0,3156.979581,0.00984466,0.803926,0.612657,0.428563
980.0,3189.514787,0.00984321,0.787628,0.529922,0.461822
990.0,3222.046238,0.00984177,0.784571,0.528978,0.458305
1000.0,3254.574804,0.00983984,0.808114,0.532594,0.407188
1010.0,3287.097002,0.00983839,0.768645,0.647785,0.495203
1020.0,3319.624181,0.00983695,0.801302,0.51827,0.428615
1030.0,3352.149555,0.00983502,0.813117,0.520601,0.410831
1040.0,3384.676779,0.00983357,0.774988,0.432041,0.492322
1050.0,3417.206563,0.00983213,0.803892,0.4902,0.415701
1060.0,3449.737533,0.0098302,0.779762,0.417157,0.498573
1070.0,3482.269009,0.00982875,0.774047,0.39201,0.50133
1080.0,3514.792272,0.00982731,0.793246,0.480089,0.436357
1090.0,3547.312249,0.00982538,0.788205,0.649497,0.459278
1100.0,3579.838961,0.00982393,0.807552,0.589245,0.421448
1110.0,3612.370057,0.00982248,0.772157,0.481151,0.496155
1120.0,3644.893497,0.00982056,0.7971,0.652794,0.444405
1130.0,3677.415198,0.00981911,0.807984,0.516732,0.41722
1140.0,3709.940874,0.00981766,0.8178,0.567833,0.395423
1150.0,3742.459473,0.00981573,0.767877,0.394894,0.543181
1160.0,3774.982341,0.00981429,0.825836,0.590485,0.382029
1170.0,3807.505284,0.00981284,0.819203,0.596745,0.396157
1180.0,3840.026207,0.00981091,0.824714,0.543201,0.385836
1190.0,3872.555598,0.00980946,0.777423,0.68356,0.477286
1200.0,3905.078686,0.00980802,0.785518,0.556044,0.453677
1210.0,3937.610724,0.00980609,0.811323,0.648852,0.416069
1220.0,3970.140773,0.00980464,0.790938,0.447834,0.462753
1230.0,4002.666649,0.00980319,0.808951,0.626345,0.411477
1240.0,4035.194808,0.00980126,0.816021,0.577134,0.406092
1250.0,4067.719152,0.00979982,0.80183,0.520672,0.426694
1260.0,4100.241202,0.00979837,0.827638,0.574052,0.376101
1270.0,4132.778433,0.00979644,0.811596,0.496341,0.403742
1280.0,4165.308392,0.00979499,0.83702,0.747159,0.361064
1290.0,4197.833805,0.00979354,0.811657,0.674871,0.413075
1300.0,4230.358658,0.00979161,0.823978,0.673868,0.395136
1310.0,4262.88234,0.00979017,0.821542,0.594881,0.390792
1320.0,4295.408453,0.00978872,0.842513,0.681857,0.350321
1330.0,4327.936408,0.00978679,0.834438,0.634254,0.369423
1340.0,4360.463401,0.00978534,0.825377,0.57128,0.385515
1350.0,4392.993736,0.00978389,0.802664,0.581189,0.445194
1360.0,4425.524199,0.00978196,0.830842,0.654457,0.380419
1370.0,4458.051592,0.00978051,0.842242,0.661821,0.351745
1380.0,4490.584685,0.00977907,0.811778,0.492881,0.403601
1390.0,4523.11064,0.00977714,0.817465,0.612285,0.422841
1400.0,4555.631293,0.00977569,0.81943,0.575962,0.396563
1410.0,4588.155208,0.00977424,0.831437,0.614717,0.370954
1420.0,4620.678231,0.00977231,0.843164,0.628446,0.348612
1430.0,4653.205266,0.00977086,0.836335,0.586055,0.357677
1440.0,4685.737519,0.00976941,0.813105,0.529902,0.406153
1450.0,4718.26097,0.00976748,0.821331,0.640579,0.399147
1460.0,4750.78498,0.00976603,0.83386,0.623969,0.364804
1470.0,4783.311108,0.00976458,0.830965,0.69567,0.37704
1480.0,4815.835256,0.00976265,0.734254,0.687521,0.533839
1490.0,4848.368441,0.0097612,0.813947,0.697747,0.412543
1500.0,4880.897794,0.00975975,0.817433,0.562779,0.396058
1510.0,4913.433766,0.00975782,0.825072,0.680431,0.389661
1520.0,4945.969029,0.00975637,0.840385,0.731262,0.356578
1530.0,4978.510464,0.00975492,0.847642,0.68823,0.343924
1540.0,5011.04451,0.00975299,0.841906,0.655153,0.351869
1550.0,5043.574391,0.00975154,0.839107,0.688156,0.359355
1560.0,5076.098086,0.00975009,0.8258,0.530793,0.376009
1570.0,5108.621633,0.00974816,0.817656,0.543371,0.406957
1580.0,5141.151364,0.00974671,0.843672,0.696979,0.352105
1590.0,5173.676939,0.00974526,0.83516,0.610836,0.359787
1600.0,5206.213128,0.00974333,0.843769,0.769634,0.347926
1610.0,5238.744863,0.00974188,0.826243,0.579005,0.375628
1620.0,5271.278986,0.00974043,0.845266,0.635169,0.344566
1630.0,5303.812267,0.0097385,0.824184,0.656112,0.398093
1640.0,5336.344229,0.00973705,0.838626,0.712282,0.360924
1650.0,5368.874141,0.0097356,0.851004,0.686272,0.333834
1660.0,5401.404626,0.00973367,0.848644,0.705724,0.339978
1670.0,5433.943287,0.00973222,0.775989,0.755896,0.469977
1680.0,5466.47685,0.00973077,0.847164,0.695443,0.348361
1690.0,5499.005912,0.00972883,0.831576,0.611575,0.366837
1700.0,5531.534009,0.00972738,0.831627,0.68592,0.375448
1710.0,5564.067938,0.00972593,0.848624,0.673356,0.340255
1720.0,5596.605938,0.009724,0.833765,0.660176,0.363313
1730.0,5629.13789,0.00972255,0.814579,0.563929,0.410072
1740.0,5661.670447,0.0097211,0.782501,0.776144,0.462334
1750.0,5694.193524,0.00971917,0.837582,0.676733,0.361642
1760.0,5726.720982,0.00971772,0.822084,0.766964,0.39516
1770.0,5759.251255,0.00971627,0.848567,0.687148,0.338402
1780.0,5791.780625,0.00971433,0.833474,0.797272,0.37397
1790.0,5824.313034,0.00971288,0.847978,0.700677,0.340566
1800.0,5856.843487,0.00971143,0.851068,0.736333,0.338921
1810.0,5889.378431,0.0097095,0.836266,0.73077,0.360099
1820.0,5921.907251,0.00970805,0.858435,0.764089,0.32184
1830.0,5954.443685,0.0097066,0.848747,0.741473,0.341532
1840.0,5986.974218,0.00970466,0.842074,0.713187,0.357558
1850.0,6019.503884,0.00970321,0.829975,0.628943,0.376948
1860.0,6052.032292,0.00970176,0.686852,0.756811,0.651706
1870.0,6084.559063,0.00969983,0.850049,0.744084,0.337841
1880.0,6117.085981,0.00969837,0.852752,0.688059,0.334727
1890.0,6149.612345,0.00969692,0.833569,0.688266,0.369075
1900.0,6182.142074,0.00969499,0.723309,0.781894,0.578137
1910.0,6214.674601,0.00969354,0.837386,0.545047,0.350723
1920.0,6247.212525,0.00969209,0.860842,0.797345,0.318572
1930.0,6279.742937,0.00969015,0.858526,0.701623,0.318138
1940.0,6312.267594,0.0096887,0.854653,0.773056,0.327834
1950.0,6344.798219,0.00968725,0.842351,0.798529,0.353594
1960.0,6377.333058,0.00968531,0.843793,0.828759,0.351884
1970.0,6409.861683,0.00968386,0.832394,0.504016,0.370496
1980.0,6442.403508,0.00968241,0.848851,0.786148,0.338188
1990.0,6474.934899,0.00968047,0.852022,0.777632,0.334142
2000.0,6508.060274,0.00967902,0.860462,0.736897,0.318663
2010.0,6540.597551,0.00967757,0.854303,0.735467,0.332829
2020.0,6573.138255,0.00967563,0.85155,0.771217,0.336382
2030.0,6605.670874,0.00967418,0.856534,0.760653,0.32609
2040.0,6638.208231,0.00967273,0.818657,0.772823,0.404724
2050.0,6670.746215,0.00967079,0.850703,0.636331,0.336529
2060.0,6703.288098,0.00966934,0.847758,0.770027,0.341505
2070.0,6735.825367,0.00966789,0.832403,0.794159,0.374557
2080.0,6768.361009,0.00966595,0.858307,0.812053,0.321909
2090.0,6800.891901,0.0096645,0.861948,0.694651,0.316368
2100.0,6833.424467,0.00966305,0.846094,0.733891,0.349654
2110.0,6865.955614,0.00966111,0.833173,0.632337,0.389342
2120.0,6898.496493,0.00965966,0.833366,0.78509,0.375968
2130.0,6931.038338,0.00965821,0.847948,0.636315,0.340779
2140.0,6963.571707,0.00965627,0.849799,0.750136,0.335627
2150.0,6996.102625,0.00965482,0.845784,0.753671,0.347934
2160.0,7028.638432,0.00965336,0.808444,0.789702,0.431406
2170.0,7061.179258,0.00965143,0.844053,0.753209,0.349492
2180.0,7093.711409,0.00964997,0.856886,0.770951,0.328835
2190.0,7126.249895,0.00964852,0.848467,0.716516,0.336599
2200.0,7158.791081,0.00964658,0.846334,0.794996,0.348517
2210.0,7191.324474,0.00964513,0.861945,0.723557,0.310937
2220.0,7223.857518,0.00964368,0.848641,0.788261,0.341776
2230.0,7256.394604,0.00964174,0.849505,0.801654,0.337208
2240.0,7288.92284,0.00964029,0.856853,0.784053,0.326834
2250.0,7321.458385,0.00963883,0.859419,0.838372,0.319421
2260.0,7353.985754,0.0096369,0.838285,0.729568,0.360343
2270.0,7386.516752,0.00963544,0.84778,0.794451,0.343996
2280.0,7419.051726,0.00963399,0.86383,0.752915,0.309966
2290.0,7451.594046,0.00963205,0.812478,0.857376,0.408795
2300.0,7484.125863,0.0096306,0.843575,0.642264,0.349641
2310.0,7516.664854,0.00962914,0.848948,0.834233,0.33907
2320.0,7549.202238,0.00962721,0.853942,0.761248,0.327856
2330.0,7581.739551,0.00962575,0.862863,0.815898,0.308196
2340.0,7614.275157,0.0096243,0.852969,0.698524,0.327145
2350.0,7646.815911,0.00962236,0.855279,0.804919,0.321411
2360.0,7679.349111,0.00962091,0.860395,0.8343,0.31465
2370.0,7711.880396,0.00961945,0.857113,0.772616,0.318898
2380.0,7744.417419,0.00961751,0.856281,0.838882,0.322617
2390.0,7776.944482,0.00961606,0.854291,0.782788,0.326266
2400.0,7809.47943,0.0096146,0.864205,0.799279,0.309294
2410.0,7842.009737,0.00961267,0.829677,0.799332,0.380361
2420.0,7874.540086,0.00961121,0.838754,0.78841,0.363193
2430.0,7907.072904,0.00960976,0.854709,0.684283,0.326057
2440.0,7939.607909,0.00960782,0.855758,0.753784,0.32808
2450.0,7972.144555,0.00960636,0.858173,0.755971,0.320687
2460.0,8004.67706,0.00960491,0.853951,0.688736,0.324794
2470.0,8037.216707,0.00960297,0.861779,0.752188,0.314112
2480.0,8069.754157,0.00960151,0.845994,0.839988,0.341122
2490.0,8102.283514,0.00960006,0.865335,0.83257,0.308579
2500.0,8134.815287,0.00959812,0.831183,0.830908,0.382683
2510.0,8167.343938,0.00959667,0.841325,0.846811,0.352708
2520.0,8199.873987,0.00959521,0.840044,0.77776,0.360473
2530.0,8232.402344,0.00959327,0.867858,0.793266,0.300346
2540.0,8264.936247,0.00959182,0.85312,0.807582,0.329674
2550.0,8297.469674,0.00959036,0.863341,0.777975,0.309545
2560.0,8330.007347,0.00958842,0.864467,0.80854,0.307737
2570.0,8362.539658,0.00958696,0.865869,0.809595,0.302113
2580.0,8395.067343,0.00958551,0.853454,0.84693,0.329916
2590.0,8427.598661,0.00958357,0.844967,0.795837,0.345003
2600.0,8460.129717,0.00958211,0.848448,0.841975,0.337187
2610.0,8492.66808,0.00958066,0.845565,0.830534,0.340788
2620.0,8525.196698,0.00957872,0.860355,0.787998,0.317608
2630.0,8557.726733,0.00957726,0.84304,0.801448,0.359941
2640.0,8590.259056,0.00957581,0.839131,0.857546,0.358341
2650.0,8622.782548,0.00957386,0.841311,0.837472,0.35379
2660.0,8655.320903,0.00957241,0.859264,0.824533,0.320331
2670.0,8687.856952,0.00957095,0.861963,0.822508,0.311233
2680.0,8720.393855,0.00956901,0.86799,0.794373,0.302598
2690.0,8752.927927,0.00956756,0.86493,0.765886,0.306069
2700.0,8785.459307,0.0095661,0.86553,0.809532,0.303819
2710.0,8817.998673,0.00956416,0.870325,0.76075,0.293315
2720.0,8850.533682,0.0095627,0.834924,0.906359,0.360421
2730.0,8883.072443,0.00956125,0.841014,0.790473,0.357662
2740.0,8915.600917,0.0095593,0.688336,0.790123,0.591733
2750.0,8948.140043,0.00955785,0.865442,0.747096,0.30133
2760.0,8980.671822,0.00955639,0.863394,0.828511,0.30567
2770.0,9013.202778,0.00955445,0.855863,0.713412,0.317759
2780.0,9045.735243,0.00955299,0.851198,0.751002,0.339298
2790.0,9078.27538,0.00955154,0.85362,0.800925,0.330244
2800.0,9110.806322,0.00954959,0.850375,0.836718,0.332635
2810.0,9143.342382,0.00954814,0.866208,0.7749,0.304972
2820.0,9175.879655,0.00954668,0.866276,0.770811,0.299943
2830.0,9208.416752,0.00954474,0.868746,0.733502,0.295809
2840.0,9240.946458,0.00954328,0.862775,0.713963,0.309544
2850.0,9273.477456,0.00954182,0.857052,0.842729,0.320663
2860.0,9306.007554,0.00953988,0.865212,0.717653,0.306168
2870.0,9338.536132,0.00953843,0.865228,0.792894,0.30606
2880.0,9371.072675,0.00953697,0.866459,0.847803,0.302692
2890.0,9403.597042,0.00953502,0.849396,0.861318,0.340599
2900.0,9436.126389,0.00953357,0.863659,0.855039,0.307112
2910.0,9468.649248,0.00953211,0.850765,0.80421,0.335329
2920.0,9501.175211,0.00953017,0.871648,0.786189,0.292589
2930.0,9533.706242,0.00952871,0.864395,0.79072,0.306544
2940.0,9566.234962,0.00952725,0.8656,0.822156,0.304915
2950.0,9598.761989,0.00952531,0.856448,0.757988,0.32802
2960.0,9631.289004,0.00952385,0.857813,0.799221,0.328147
2970.0,9663.823625,0.00952239,0.856945,0.790111,0.322138
2980.0,9696.351684,0.00952045,0.862596,0.802765,0.312684
2990.0,9728.880999,0.00951899,0.863511,0.775042,0.308017
3000.0,9761.408008,0.00951753,0.86511,0.690595,0.305974
3010.0,9793.942333,0.00951559,0.857889,0.854618,0.32264
3020.0,9826.470402,0.00951413,0.863101,0.760341,0.308652
3030.0,9859.002104,0.00951267,0.860165,0.787101,0.315714
3040.0,9891.528574,0.00951073,0.840994,0.810323,0.363222
3050.0,9924.05464,0.00950927,0.84112,0.722114,0.355235
3060.0,9956.584543,0.00950781,0.842672,0.766999,0.353292
3070.0,9989.117082,0.00950587,0.857052,0.822861,0.3276
3080.0,10021.646698,0.00950441,0.875428,0.79941,0.289438
3090.0,10054.182294,0.00950295,0.855724,0.791159,0.323845
3100.0,10086.710745,0.00950101,0.858767,0.788227,0.320809
3110.0,10119.243462,0.00949955,0.860118,0.806456,0.316926
3120.0,10151.77448,0.00949809,0.864184,0.833349,0.310366
3130.0,10184.306503,0.00949615,0.861205,0.798127,0.313245
3140.0,10216.839282,0.00949469,0.863414,0.820914,0.307192
3150.0,10249.366241,0.00949323,0.840178,0.785392,0.357996
3160.0,10281.892638,0.00949128,0.86739,0.783257,0.300297
3170.0,10314.428308,0.00948982,0.863901,0.758106,0.305409
3180.0,10346.955079,0.00948836,0.861582,0.700861,0.314532
3190.0,10379.485088,0.00948642,0.870619,0.874245,0.29856
3200.0,10412.017911,0.00948496,0.857952,0.837333,0.317174
3210.0,10444.546847,0.0094835,0.838078,0.827839,0.360676
3220.0,10477.07417,0.00948156,0.861631,0.820172,0.315817
3230.0,10509.600683,0.0094801,0.850442,0.820491,0.340359
3240.0,10542.128329,0.00947864,0.86554,0.82926,0.306516
3250.0,10574.659418,0.00947669,0.853346,0.794436,0.327816
3260.0,10607.189477,0.00947523,0.870649,0.847681,0.293028
3270.0,10639.723385,0.00947377,0.857055,0.875616,0.326806
3280.0,10672.243983,0.00947183,0.863864,0.779347,0.31295
3290.0,10704.76865,0.00947037,0.868319,0.833298,0.298387
3300.0,10737.301175,0.00946891,0.852481,0.848714,0.330468
3310.0,10769.827937,0.00946696,0.855186,0.858174,0.324307
3320.0,10802.359863,0.0094655,0.867918,0.736292,0.300464
3330.0,10834.888243,0.00946404,0.877472,0.793418,0.278162
3340.0,10867.415344,0.00946209,0.859317,0.842604,0.315442
3350.0,10899.939995,0.00946063,0.860794,0.849488,0.31693
3360.0,10932.480061,0.00945917,0.879471,0.826147,0.275643
3370.0,10965.01852,0.00945723,0.872436,0.809178,0.293761
3380.0,10997.553951,0.00945577,0.838836,0.828686,0.365659
3390.0,11030.092673,0.00945431,0.86034,0.86216,0.317254
3400.0,11062.627365,0.00945236,0.871478,0.838017,0.292714
3410.0,11095.167498,0.0094509,0.874931,0.860239,0.287231
3420.0,11127.701939,0.00944944,0.863341,0.846552,0.307438
3430.0,11160.23559,0.00944749,0.864967,0.823773,0.305392
3440.0,11192.780296,0.00944603,0.848518,0.836025,0.33862
3450.0,11225.312956,0.00944457,0.86654,0.796708,0.305673
3460.0,11257.849446,0.00944262,0.852535,0.854459,0.336691
3470.0,11290.384056,0.00944116,0.869958,0.807531,0.295757
3480.0,11322.912216,0.0094397,0.85752,0.836123,0.321325
3490.0,11355.451512,0.00943775,0.86813,0.807043,0.299242
3500.0,11387.982582,0.00943629,0.869812,0.742979,0.297009
3510.0,11420.517224,0.00943483,0.86527,0.836694,0.303961
3520.0,11453.055617,0.00943288,0.869706,0.793352,0.294675
3530.0,11485.5909,0.00943142,0.867772,0.885692,0.302328
3540.0,11518.119329,0.00942996,0.852246,0.817914,0.331848
3550.0,11550.645033,0.00942801,0.873264,0.847557,0.286436
3560.0,11583.170074,0.00942655,0.849462,0.858478,0.338543
3570.0,11615.688821,0.00942509,0.845164,0.842967,0.349374
3580.0,11648.220653,0.00942314,0.870333,0.757456,0.292492
3590.0,11680.744275,0.00942168,0.861846,0.804794,0.310631
3600.0,11713.269436,0.00942022,0.858672,0.767276,0.325318
3610.0,11745.800234,0.00941827,0.861643,0.8051,0.316151
3620.0,11778.321363,0.0094168,0.869855,0.819489,0.297957
3630.0,11810.847427,0.00941534,0.864683,0.743417,0.304594
3640.0,11843.372841,0.00941339,0.868865,0.783368,0.295691
3650.0,11875.899555,0.00941193,0.863001,0.771114,0.310279
3660.0,11908.423345,0.00941047,0.83099,0.68389,0.398246
3670.0,11940.955548,0.00940852,0.856885,0.811781,0.319829
3680.0,11973.479125,0.00940706,0.870993,0.843401,0.292003
3690.0,12006.005342,0.0094056,0.872529,0.849786,0.287871
3700.0,12038.532318,0.00940365,0.839016,0.77319,0.362488
3710.0,12071.058203,0.00940218,0.881614,0.809898,0.274531
3720.0,12103.58874,0.00940072,0.876795,0.821631,0.278693
3730.0,12136.1136,0.00939877,0.85546,0.845111,0.324106
3740.0,12168.639774,0.00939731,0.865675,0.777953,0.303186
3750.0,12201.161859,0.00939585,0.825104,0.812831,0.386783
3760.0,12233.690637,0.0093939,0.86715,0.843397,0.304104
3770.0,12266.213061,0.00939243,0.865796,0.81141,0.300693
3780.0,12298.737605,0.00939097,0.866393,0.879061,0.305926
3790.0,12331.265506,0.00938902,0.877189,0.834014,0.27669
3800.0,12363.79796,0.00938756,0.86566,0.812873,0.304307
3810.0,12396.330574,0.00938609,0.849677,0.790626,0.337988
3820.0,12428.855425,0.00938414,0.807901,0.882511,0.408019
3830.0,12461.377376,0.00938268,0.873073,0.829006,0.291521
3840.0,12493.901276,0.00938122,0.86314,0.854096,0.307862
3850.0,12526.424515,0.00937927,0.870094,0.806944,0.296983
3860.0,12558.948789,0.0093778,0.840302,0.811302,0.358238
3870.0,12591.472937,0.00937634,0.881315,0.814498,0.271589
3880.0,12623.996148,0.00937439,0.881802,0.808991,0.272233
3890.0,12656.5235,0.00937293,0.876214,0.813019,0.281745
3900.0,12689.052539,0.00937146,0.86607,0.857899,0.300886
3910.0,12721.578014,0.00936951,0.881752,0.771096,0.27125
3920.0,12754.097583,0.00936805,0.871154,0.888181,0.291668
3930.0,12786.624385,0.00936658,0.856332,0.830435,0.328208
3940.0,12819.152491,0.00936463,0.86024,0.854482,0.315195
3950.0,12851.677889,0.00936317,0.866565,0.845185,0.300212
3960.0,12884.201777,0.0093617,0.872853,0.846264,0.289613
3970.0,12916.726709,0.00935975,0.875131,0.788631,0.285734
3980.0,12949.251173,0.00935829,0.875473,0.838347,0.284488
3990.0,12981.780036,0.00935682,0.859016,0.854284,0.316701
4000.0,13014.798692,0.00935487,0.870075,0.809638,0.295977
4010.0,13047.317323,0.00935341,0.878961,0.802737,0.276098
4020.0,13079.841474,0.00935194,0.865742,0.839089,0.306753
4030.0,13112.366835,0.00934999,0.85649,0.850359,0.326016
4040.0,13144.890257,0.00934853,0.876372,0.840407,0.283562
4050.0,13177.409938,0.00934706,0.867778,0.822397,0.299251
4060.0,13209.933754,0.00934511,0.832051,0.891513,0.369755
4070.0,13242.455704,0.00934364,0.875169,0.816256,0.282696
4080.0,13274.975678,0.00934218,0.870747,0.810615,0.290031
4090.0,13307.497039,0.00934023,0.879237,0.848064,0.277192
4100.0,13340.018474,0.00933876,0.865952,0.843697,0.303436
4110.0,13372.545602,0.0093373,0.873958,0.809375,0.28401
4120.0,13405.068591,0.00933534,0.864826,0.817764,0.30597
4130.0,13437.587564,0.00933388,0.871666,0.851705,0.29326
4140.0,13470.113591,0.00933241,0.880246,0.832974,0.272583
4150.0,13502.636532,0.00933046,0.874107,0.771073,0.286624
4160.0,13535.155965,0.00932899,0.876418,0.794925,0.281765
4170.0,13567.679547,0.00932753,0.88201,0.82736,0.269951
4180.0,13600.202312,0.00932558,0.86897,0.814499,0.303281
4190.0,13632.714931,0.00932411,0.833126,0.865454,0.373877
4200.0,13665.231686,0.00932264,0.812815,0.798864,0.404115
4210.0,13697.749035,0.00932069,0.859206,0.830538,0.315413
4220.0,13730.26218,0.00931923,0.862846,0.860668,0.311667
4230.0,13762.777211,0.00931776,0.871974,0.85402,0.288105
4240.0,13795.299786,0.00931581,0.85817,0.857907,0.317341
4250.0,13827.814557,0.00931434,0.873318,0.74125,0.286714
4260.0,13860.327361,0.00931287,0.880436,0.858775,0.270993
4270.0,13892.844006,0.00931092,0.858154,0.840352,0.325474
4280.0,13925.360012,0.00930945,0.881032,0.84585,0.273757
4290.0,13957.87525,0.00930799,0.878355,0.762251,0.279924
4300.0,13990.394733,0.00930603,0.880298,0.826837,0.273679
4310.0,14022.911087,0.00930457,0.885603,0.767722,0.264147
4320.0,14055.424601,0.0093031,0.876834,0.826057,0.280035
4330.0,14087.937566,0.00930114,0.862438,0.864761,0.311479
4340.0,14120.4518,0.00929968,0.861226,0.828766,0.314276
4350.0,14152.964291,0.00929821,0.875814,0.748528,0.280451
4360.0,14185.48437,0.00929626,0.865257,0.871972,0.305684
4370.0,14217.99998,0.00929479,0.835029,0.821119,0.369289
4380.0,14250.515192,0.00929332,0.835736,0.767028,0.376456
4390.0,14283.028836,0.00929137,0.880573,0.828809,0.271058
4400.0,14315.541726,0.0092899,0.878573,0.85583,0.276247
4410.0,14348.052724,0.00928843,0.874122,0.753994,0.286112
4420.0,14380.572086,0.00928648,0.86659,0.859302,0.300912
4430.0,14413.085267,0.00928501,0.865012,0.840498,0.308783
4440.0,14445.607518,0.00928354,0.860792,0.878561,0.312269
4450.0,14478.123959,0.00928159,0.84169,0.880409,0.348755
4460.0,14510.635955,0.00928012,0.852044,0.854803,0.330076
4470.0,14543.15246,0.00927866,0.883374,0.845064,0.269419
4480.0,14575.669284,0.0092767,0.88224,0.826373,0.2705
4490.0,14608.183286,0.00927523,0.875062,0.855284,0.288277
4500.0,14640.6996,0.00927376,0.872492,0.848692,0.284182
4510.0,14673.216502,0.00927181,0.864131,0.785403,0.305447
4520.0,14705.729391,0.00927034,0.871815,0.86997,0.288667
4530.0,14738.245052,0.00926887,0.815931,0.838103,0.401882
4540.0,14770.762738,0.00926691,0.844771,0.828179,0.355177
4550.0,14803.276991,0.00926545,0.872957,0.836816,0.289717
4560.0,14835.794666,0.00926398,0.881955,0.864107,0.26463
4570.0,14868.310933,0.00926202,0.863943,0.904775,0.305389
4580.0,14900.828586,0.00926055,0.873474,0.866813,0.284916
4590.0,14933.353888,0.00925909,0.862413,0.897624,0.311907
4600.0,14965.866329,0.00925713,0.873622,0.856038,0.284812
4610.0,14998.382637,0.00925566,0.883893,0.819807,0.265975
4620.0,15030.897593,0.00925419,0.878201,0.829132,0.281268
4630.0,15063.408039,0.00925224,0.873857,0.8893,0.282974
4640.0,15095.923133,0.00925077,0.882954,0.851623,0.267094
4650.0,15128.4416,0.0092493,0.874587,0.844034,0.285137
4660.0,15160.955986,0.00924734,0.884313,0.822685,0.264749
4670.0,15193.471372,0.00924587,0.879913,0.8237,0.274623
4680.0,15225.985816,0.0092444,0.868333,0.804415,0.299737
4690.0,15258.511651,0.00924245,0.880108,0.843003,0.274846
4700.0,15291.031378,0.00924098,0.881853,0.822891,0.268273
4710.0,15323.559276,0.00923951,0.875688,0.89333,0.278904
4720.0,15356.086223,0.00923755,0.810128,0.8419,0.403327
4730.0,15388.60594,0.00923608,0.877181,0.848138,0.281925
4740.0,15421.126918,0.00923461,0.873239,0.824442,0.287252
4750.0,15453.651487,0.00923265,0.870512,0.878908,0.291571
4760.0,15486.173527,0.00923118,0.841749,0.846544,0.352505
4770.0,15518.695297,0.00922971,0.884898,0.827119,0.262703
4780.0,15551.214569,0.00922776,0.874734,0.860047,0.28633
4790.0,15583.741248,0.00922629,0.869935,0.845317,0.298103
4800.0,15616.269719,0.00922482,0.870969,0.856622,0.293783
4810.0,15648.792256,0.00922286,0.868282,0.826215,0.297833
4820.0,15681.322587,0.00922139,0.859042,0.877459,0.31128
4830.0,15713.847527,0.00921992,0.870228,0.824461,0.296271
4840.0,15746.367731,0.00921796,0.854355,0.907749,0.32274
4850.0,15778.886491,0.00921649,0.875043,0.791063,0.284308
4860.0,15811.406894,0.00921502,0.887334,0.826772,0.257888
4870.0,15843.931359,0.00921306,0.879775,0.833658,0.273064
4880.0,15876.453105,0.00921159,0.890158,0.833094,0.252595
4890.0,15908.972762,0.00921012,0.873764,0.863001,0.286747
4900.0,15941.493854,0.00920816,0.871825,0.860449,0.289564
4910.0,15974.016113,0.00920669,0.86055,0.823817,0.312034
4920.0,16006.545267,0.00920522,0.880718,0.759714,0.270451
4930.0,16039.069911,0.00920326,0.880064,0.803654,0.278536
4940.0,16071.591131,0.00920179,0.873425,0.780929,0.285658
4950.0,16104.111444,0.00920032,0.8831,0.824402,0.268538
4960.0,16136.634153,0.00919836,0.878301,0.846114,0.275639
4970.0,16169.161824,0.00919689,0.867023,0.846434,0.300515
4980.0,16201.683674,0.00919542,0.879276,0.87993,0.273223
4990.0,16234.209044,0.00919346,0.856638,0.844826,0.323111
5000.0,16266.735778,0.00919199,0.892387,0.835392,0.249438
5010.0,16299.27337,0.00919052,0.86718,0.868822,0.297877
5020.0,16331.800974,0.00918856,0.882971,0.824393,0.269565
5030.0,16364.325094,0.00918709,0.871107,0.842019,0.296909
5040.0,16396.855788,0.00918561,0.885912,0.858759,0.258206
5050.0,16429.38271,0.00918365,0.878101,0.858986,0.272893
5060.0,16461.908977,0.00918218,0.887166,0.848713,0.257759
5070.0,16494.442315,0.00918071,0.88328,0.83776,0.264675
5080.0,16526.967689,0.00917875,0.872667,0.83455,0.284203
5090.0,16559.494625,0.00917728,0.873521,0.828045,0.28523
5100.0,16592.019645,0.00917581,0.850705,0.862062,0.33765
5110.0,16624.540625,0.00917384,0.884297,0.882001,0.26487
5120.0,16657.06362,0.00917237,0.883003,0.813203,0.267412
5130.0,16689.590572,0.0091709,0.850488,0.874831,0.332488
5140.0,16722.110034,0.00916894,0.88807,0.842792,0.256421
5150.0,16754.627813,0.00916747,0.872563,0.865331,0.290446
5160.0,16787.145231,0.009166,0.885093,0.845593,0.264415
5170.0,16819.666521,0.00916403,0.878936,0.770089,0.278714
5180.0,16852.189906,0.00916256,0.883471,0.839299,0.263787
5190.0,16884.718548,0.00916109,0.880953,0.842457,0.27225
5200.0,16917.238485,0.00915913,0.867403,0.841686,0.309983
5210.0,16949.764799,0.00915766,0.875912,0.843743,0.27979
5220.0,16982.289767,0.00915618,0.885378,0.869328,0.261017
5230.0,17014.807624,0.00915422,0.865498,0.869298,0.304534
5240.0,17047.330261,0.00915275,0.863744,0.875728,0.306873
5250.0,17079.853711,0.00915128,0.854781,0.869123,0.322846
5260.0,17112.376784,0.00914931,0.838215,0.797365,0.35934
5270.0,17144.905193,0.00914784,0.884447,0.878498,0.265749
5280.0,17177.432943,0.00914637,0.884106,0.838507,0.263003
5290.0,17209.957762,0.00914441,0.878755,0.859735,0.275225
5300.0,17242.482417,0.00914293,0.874797,0.891666,0.279441
5310.0,17275.007548,0.00914146,0.878816,0.847947,0.273176
5320.0,17307.534723,0.0091395,0.834771,0.869201,0.370447
5330.0,17340.065941,0.00913802,0.874386,0.866556,0.282121
5340.0,17372.58698,0.00913655,0.882571,0.801283,0.268397
5350.0,17405.107335,0.00913459,0.888587,0.881348,0.253358
5360.0,17437.635215,0.00913311,0.887593,0.875612,0.25819
5370.0,17470.16225,0.00913164,0.876037,0.879948,0.279807
5380.0,17502.692037,0.00912968,0.886647,0.832643,0.257422
5390.0,17535.215068,0.0091282,0.875656,0.877418,0.279855
5400.0,17567.743889,0.00912673,0.879062,0.87501,0.272736
5410.0,17600.270301,0.00912477,0.881176,0.847181,0.270231
5420.0,17632.794315,0.00912329,0.857852,0.811525,0.318627
5430.0,17665.321677,0.00912182,0.882671,0.851021,0.267905
5440.0,17697.847769,0.00911985,0.87571,0.882489,0.284366
5450.0,17730.372467,0.00911838,0.881321,0.74749,0.271445
5460.0,17762.899845,0.00911691,0.879136,0.815498,0.27872
5470.0,17795.439505,0.00911494,0.852443,0.85127,0.332575
5480.0,17827.975536,0.00911347,0.887884,0.8794,0.257978
5490.0,17860.50393,0.00911199,0.878894,0.869257,0.275028
5500.0,17893.02729,0.00911003,0.870579,0.847622,0.292539
5510.0,17925.551542,0.00910856,0.877516,0.835892,0.278627
5520.0,17958.085114,0.00910708,0.883391,0.860129,0.265995
5530.0,17990.612244,0.00910512,0.870075,0.814492,0.294293
5540.0,18023.133842,0.00910364,0.873414,0.875432,0.28536
5550.0,18055.662513,0.00910217,0.890903,0.852458,0.24978
5560.0,18088.186085,0.0091002,0.855233,0.8953,0.324355
5570.0,18120.705671,0.00909873,0.875707,0.773316,0.289433
5580.0,18153.226174,0.00909725,0.881948,0.828704,0.269265
5590.0,18185.75031,0.00909529,0.860238,0.815193,0.316394
5600.0,18218.283708,0.00909381,0.881244,0.874341,0.271378
5610.0,18250.810377,0.00909234,0.880432,0.839237,0.270068
5620.0,18283.336862,0.00909037,0.886589,0.866831,0.258519
5630.0,18315.862883,0.0090889,0.879631,0.853176,0.273589
5640.0,18348.383379,0.00908742,0.866601,0.723882,0.307151
5650.0,18380.908966,0.00908546,0.879049,0.873909,0.280405
5660.0,18413.432495,0.00908398,0.876763,0.872084,0.282826
5670.0,18445.957252,0.00908251,0.876406,0.852978,0.280329
5680.0,18478.485003,0.00908054,0.88644,0.843543,0.260794
5690.0,18511.020035,0.00907906,0.88807,0.826991,0.254307
5700.0,18543.551973,0.00907759,0.860187,0.849953,0.319384
5710.0,18576.077381,0.00907562,0.880117,0.779821,0.274325
5720.0,18608.616188,0.00907415,0.883695,0.830493,0.264571
5730.0,18641.150586,0.00907267,0.870826,0.807239,0.296327
5740.0,18673.678761,0.0090707,0.851345,0.857654,0.331357
5750.0,18706.197123,0.00906923,0.875901,0.842289,0.280324
5760.0,18738.72391,0.00906775,0.876541,0.862525,0.277341
5770.0,18771.247164,0.00906578,0.870955,0.857058,0.291652
5780.0,18803.775444,0.00906431,0.884114,0.876098,0.264951
5790.0,18836.296831,0.00906283,0.888488,0.859253,0.251099
5800.0,18868.808524,0.00906087,0.868851,0.796886,0.299892
5810.0,18901.325159,0.00905939,0.889153,0.841991,0.253239
5820.0,18933.837953,0.00905791,0.880284,0.85829,0.275508
5830.0,18966.357381,0.00905595,0.871181,0.82126,0.290634
5840.0,18998.880921,0.00905447,0.874036,0.859684,0.287792
5850.0,19031.401026,0.00905299,0.868972,0.850178,0.294454
5860.0,19063.915044,0.00905102,0.868896,0.910345,0.296528
5870.0,19096.437757,0.00904955,0.857234,0.809755,0.320055
5880.0,19128.955612,0.00904807,0.893842,0.848604,0.243767
5890.0,19161.475475,0.0090461,0.871037,0.874601,0.291419
5900.0,19193.988815,0.00904463,0.877801,0.854521,0.27738
5910.0,19226.504668,0.00904315,0.888342,0.861632,0.256842
5920.0,19259.023667,0.00904118,0.843126,0.843817,0.349107
5930.0,19291.539474,0.0090397,0.887273,0.841652,0.256014
5940.0,19324.055839,0.00903823,0.880476,0.874106,0.271843
5950.0,19356.573805,0.00903626,0.875467,0.8318,0.280203
5960.0,19389.095801,0.00903478,0.889348,0.872054,0.250221
5970.0,19421.620002,0.0090333,0.877079,0.87835,0.277212
5980.0,19454.140758,0.00903133,0.882952,0.786767,0.270506
5990.0,19486.667825,0.00902986,0.857855,0.834256,0.322645
6000.0,19519.685941,0.00902838,0.887126,0.862598,0.25607
6010.0,19552.205274,0.00902641,0.874561,0.872787,0.28822
6020.0,19584.730152,0.00902493,0.848041,0.88251,0.340427
6030.0,19617.250565,0.00902345,0.884556,0.861997,0.264994
6040.0,19649.772501,0.00902149,0.876683,0.86303,0.280139
6050.0,19682.298892,0.00902001,0.872137,0.866633,0.287549
6060.0,19714.8164,0.00901853,0.881078,0.863789,0.27165
6070.0,19747.335966,0.00901656,0.88164,0.872968,0.266506
6080.0,19779.859115,0.00901508,0.877069,0.85644,0.282078
6090.0,19812.37948,0.0090136,0.867946,0.838888,0.296582
6100.0,19844.905896,0.00901163,0.878395,0.866713,0.277173
6110.0,19877.432298,0.00901016,0.879289,0.85893,0.270455
6120.0,19909.956963,0.00900868,0.88633,0.869743,0.261436
6130.0,19942.484422,0.00900671,0.877709,0.831088,0.278629
6140.0,19975.006156,0.00900523,0.884328,0.83172,0.261184
6150.0,20007.533291,0.00900375,0.870886,0.825448,0.293615
6160.0,20040.063937,0.00900178,0.875609,0.881121,0.282449
6170.0,20072.59605,0.0090003,0.886077,0.848462,0.258579
6180.0,20105.132137,0.00899882,0.881,0.873684,0.268271
6190.0,20137.656681,0.00899685,0.831696,0.867857,0.370856
6200.0,20170.177266,0.00899537,0.876764,0.861088,0.280476
6210.0,20202.70566,0.00899389,0.882382,0.872402,0.269605
6220.0,20235.227546,0.00899192,0.888254,0.87199,0.255928
6230.0,20267.756673,0.00899044,0.875433,0.893162,0.280171
6240.0,20300.292278,0.00898896,0.881321,0.860047,0.269105
6250.0,20332.819993,0.00898699,0.881623,0.894875,0.268587
6260.0,20365.352411,0.00898551,0.835944,0.895247,0.363135
6270.0,20397.880383,0.00898403,0.861676,0.854142,0.309661
6280.0,20430.406731,0.00898206,0.859513,0.816085,0.319826
6290.0,20462.93075,0.00898058,0.884199,0.800511,0.262752
6300.0,20495.459372,0.0089791,0.881503,0.784466,0.267705
6310.0,20527.984543,0.00897713,0.885231,0.789714,0.265262
6320.0,20560.515814,0.00897565,0.892559,0.838533,0.245752
6330.0,20593.044248,0.00897417,0.874337,0.886722,0.283396
6340.0,20625.568721,0.0089722,0.889462,0.864659,0.252853
6350.0,20658.093233,0.00897072,0.87835,0.796038,0.276529
6360.0,20690.616516,0.00896924,0.88411,0.834767,0.26479
6370.0,20723.13971,0.00896727,0.870416,0.812742,0.298873
6380.0,20755.667282,0.00896579,0.875903,0.837574,0.282598
6390.0,20788.188102,0.00896431,0.881763,0.756723,0.275855
6400.0,20820.715313,0.00896233,0.870365,0.802645,0.296005
6410.0,20853.239488,0.00896085,0.885545,0.837388,0.262065
6420.0,20885.763209,0.00895937,0.88283,0.855461,0.267014
6430.0,20918.289601,0.0089574,0.832432,0.860166,0.369348
6440.0,20950.812256,0.00895592,0.889068,0.864992,0.252199
6450.0,20983.338061,0.00895444,0.879453,0.88122,0.273118
6460.0,21015.859497,0.00895247,0.844714,0.898352,0.346601
6470.0,21048.386393,0.00895099,0.87099,0.840101,0.291397
6480.0,21080.905394,0.00894951,0.884405,0.862816,0.261669
6490.0,21113.432734,0.00894753,0.890521,0.843142,0.251915
6500.0,21145.952295,0.00894605,0.886645,0.827335,0.260024
6510.0,21178.478341,0.00894457,0.886252,0.870287,0.259852
6520.0,21210.999639,0.0089426,0.875871,0.798886,0.283101
6530.0,21243.520689,0.00894111,0.87211,0.900579,0.287967
6540.0,21276.048365,0.00893963,0.881084,0.885892,0.271003
6550.0,21308.568866,0.00893766,0.894479,0.849612,0.24386
6560.0,21341.08802,0.00893618,0.852184,0.864507,0.328197
6570.0,21373.610579,0.0089347,0.888441,0.797827,0.256938
6580.0,21406.137478,0.00893272,0.883736,0.847145,0.263036
6590.0,21438.655784,0.00893124,0.890021,0.854134,0.25095
6600.0,21471.180929,0.00892976,0.884908,0.86027,0.26548
6610.0,21503.706408,0.00892778,0.878093,0.857131,0.274656
6620.0,21536.235188,0.0089263,0.88201,0.860696,0.268951
6630.0,21568.764321,0.00892482,0.886012,0.855595,0.257485
6640.0,21601.290455,0.00892285,0.883999,0.852929,0.264013
6650.0,21633.813153,0.00892136,0.876826,0.82472,0.282385
6660.0,21666.338491,0.00891988,0.88057,0.831648,0.272257
6670.0,21698.861715,0.00891791,0.864868,0.849904,0.307516
6680.0,21731.385584,0.00891643,0.89031,0.849316,0.249147
6690.0,21763.905913,0.00891494,0.872372,0.864923,0.288907
6700.0,21796.430511,0.00891297,0.876756,0.888207,0.277406
6710.0,21828.952768,0.00891149,0.885326,0.866321,0.258885
6720.0,21861.47795,0.00891,0.889439,0.830086,0.251035
6730.0,21894.000759,0.00890803,0.886578,0.777788,0.262767
6740.0,21926.526627,0.00890655,0.891152,0.859548,0.24839
6750.0,21959.052524,0.00890506,0.879609,0.901976,0.27185
6760.0,21991.57311,0.00890309,0.885918,0.861709,0.261712
6770.0,22024.099415,0.0089016,0.888566,0.868302,0.255877
6780.0,22056.628868,0.00890012,0.881564,0.873335,0.269517
6790.0,22089.150391,0.00889814,0.892312,0.88778,0.245585
6800.0,22121.673988,0.00889666,0.874438,0.881363,0.289253
6810.0,22154.200333,0.00889518,0.887247,0.832415,0.255087
6820.0,22186.724488,0.0088932,0.887061,0.861857,0.262711
6830.0,22219.247291,0.00889172,0.865926,0.858555,0.306202
6840.0,22251.783524,0.00889024,0.883891,0.831577,0.265238
6850.0,22284.319477,0.00888826,0.895329,0.862109,0.240928
6860.0,22316.853645,0.00888678,0.89636,0.858776,0.236462
6870.0,22349.385143,0.00888529,0.868087,0.805124,0.297087
6880.0,22381.920633,0.00888331,0.880558,0.856589,0.272039
6890.0,22414.460559,0.00888183,0.863938,0.831869,0.306672
6900.0,22446.995774,0.00888035,0.890339,0.884632,0.250217
6910.0,22479.530507,0.00887837,0.889796,0.792624,0.251955
6920.0,22512.070444,0.00887689,0.886927,0.904952,0.256015
6930.0,22544.608866,0.0088754,0.885542,0.848936,0.260908
6940.0,22577.14468,0.00887342,0.862511,0.878379,0.308235
6950.0,22609.678414,0.00887194,0.865395,0.868675,0.305514
6960.0,22642.2103,0.00887046,0.89019,0.888977,0.251345
6970.0,22674.734223,0.00886848,0.882616,0.871376,0.26878
6980.0,22707.263412,0.008867,0.876919,0.876732,0.279328
6990.0,22739.787547,0.00886551,0.871963,0.73361,0.293313
7000.0,22772.311888,0.00886353,0.872684,0.901799,0.28502
7010.0,22804.837477,0.00886205,0.890189,0.853636,0.248459
7020.0,22837.366995,0.00886056,0.890676,0.86297,0.248425
7030.0,22869.897042,0.00885858,0.889965,0.864764,0.252129
7040.0,22902.430856,0.0088571,0.875177,0.861751,0.288317
7050.0,22934.959535,0.00885562,0.886619,0.869177,0.260086
7060.0,22967.486324,0.00885364,0.889219,0.8533,0.252357
7070.0,23000.020407,0.00885215,0.887076,0.86441,0.259994
7080.0,23032.550422,0.00885067,0.891214,0.852673,0.251092
7090.0,23065.082471,0.00884869,0.893581,0.842206,0.242562
7100.0,23097.620703,0.0088472,0.875455,0.863446,0.282884
7110.0,23130.153018,0.00884572,0.87543,0.817338,0.283267
7120.0,23162.686077,0.00884374,0.872692,0.847524,0.288119
7130.0,23195.217656,0.00884225,0.883826,0.82845,0.262992
7140.0,23227.743535,0.00884077,0.895002,0.876104,0.24169
7150.0,23260.269216,0.00883879,0.890912,0.83617,0.248127
7160.0,23292.802477,0.0088373,0.891237,0.866038,0.24869
7170.0,23325.335225,0.00883582,0.866939,0.913448,0.299968
7180.0,23357.873033,0.00883384,0.888665,0.854851,0.25512
7190.0,23390.406937,0.00883235,0.881015,0.816463,0.271357
7200.0,23422.939426,0.00883087,0.856773,0.882769,0.322646
7210.0,23455.474108,0.00882889,0.872978,0.859889,0.285154
7220.0,23487.998939,0.0088274,0.886739,0.836309,0.258277
7230.0,23520.527679,0.00882591,0.889318,0.838449,0.251155
7240.0,23553.058079,0.00882393,0.880939,0.880747,0.270161
7250.0,23585.591279,0.00882245,0.831025,0.856325,0.374261
7260.0,23618.123047,0.00882096,0.89023,0.865851,0.249016
7270.0,23650.658153,0.00881898,0.882895,0.853907,0.264818
7280.0,23683.190385,0.00881749,0.880105,0.887094,0.275954
7290.0,23715.733428,0.00881601,0.884573,0.866015,0.263033
7300.0,23748.263868,0.00881403,0.885381,0.826569,0.26206
7310.0,23780.796519,0.00881254,0.879215,0.886265,0.274598
7320.0,23813.334669,0.00881106,0.884881,0.86747,0.261452
7330.0,23845.862569,0.00880907,0.87683,0.778861,0.286189
7340.0,23878.395833,0.00880759,0.884284,0.847375,0.261961
7350.0,23910.92754,0.0088061,0.888612,0.866676,0.253678
7360.0,23943.463076,0.00880412,0.881375,0.88918,0.268261
7370.0,23975.993696,0.00880263,0.880329,0.824433,0.270855
7380.0,24008.523628,0.00880115,0.881298,0.889672,0.266727
7390.0,24041.049263,0.00879916,0.891455,0.863317,0.248115
7400.0,24073.578694,0.00879768,0.876633,0.820522,0.278734
7410.0,24106.108597,0.00879619,0.885502,0.873986,0.261261
7420.0,24138.63597,0.00879421,0.854177,0.886803,0.326777
7430.0,24171.168615,0.00879272,0.866975,0.791429,0.305523
7440.0,24203.699772,0.00879123,0.847456,0.885029,0.339069
7450.0,24236.23233,0.00878925,0.864993,0.865252,0.302399
7460.0,24268.760255,0.00878776,0.878583,0.897284,0.275795
7470.0,24301.2924,0.00878628,0.88625,0.856158,0.259714
7480.0,24333.835036,0.00878429,0.887306,0.82805,0.259008
7490.0,24366.365904,0.0087828,0.878557,0.88869,0.276224
7500.0,24398.90096,0.00878132,0.884697,0.879416,0.261976
7510.0,24431.431296,0.00877933,0.888528,0.859551,0.254077
7520.0,24463.961403,0.00877785,0.888175,0.898825,0.254037
7530.0,24496.508197,0.00877636,0.888449,0.841421,0.256796
7540.0,24529.045967,0.00877437,0.873818,0.845043,0.283337
7550.0,24561.59471,0.00877289,0.886485,0.87189,0.25889
7560.0,24594.127176,0.0087714,0.892714,0.862045,0.244591
7570.0,24626.659155,0.00876941,0.883317,0.901114,0.264257
7580.0,24659.187104,0.00876793,0.88697,0.851929,0.258981
7590.0,24691.722572,0.00876644,0.888731,0.884785,0.251093
7600.0,24724.259913,0.00876445,0.886001,0.863742,0.261221
7610.0,24756.803738,0.00876297,0.882661,0.81476,0.268027
7620.0,24789.335109,0.00876148,0.876334,0.895823,0.279389
7630.0,24821.878715,0.00875949,0.885128,0.884426,0.260564
7640.0,24854.41675,0.008758,0.887357,0.856983,0.25555
7650.0,24886.953051,0.00875652,0.885956,0.882396,0.259029
7660.0,24919.492928,0.00875453,0.876366,0.899831,0.277711
7670.0,24952.034639,0.00875304,0.886375,0.887175,0.259235
7680.0,24984.569572,0.00875155,0.882415,0.877624,0.268416
7690.0,25017.109486,0.00874957,0.887925,0.85126,0.25524
7700.0,25049.645822,0.00874808,0.896696,0.882007,0.236704
7710.0,25082.183401,0.00874659,0.889026,0.822542,0.255437
7720.0,25114.720128,0.0087446,0.8869,0.892031,0.255923
7730.0,25147.257044,0.00874312,0.879753,0.859036,0.274798
7740.0,25179.78533,0.00874163,0.883292,0.877872,0.265702
7750.0,25212.319654,0.00873964,0.894651,0.873902,0.242342
7760.0,25244.860657,0.00873815,0.893177,0.846824,0.246161
7770.0,25277.394717,0.00873666,0.867363,0.83229,0.303854
7780.0,25309.927966,0.00873468,0.852276,0.85694,0.327069
7790.0,25342.472969,0.00873319,0.889336,0.871764,0.249873
7800.0,25375.006809,0.0087317,0.88053,0.895789,0.272963
7810.0,25407.542947,0.00872971,0.88666,0.877232,0.257894
7820.0,25440.074345,0.00872822,0.887886,0.888586,0.252893
7830.0,25472.60543,0.00872673,0.893822,0.863363,0.239803
7840.0,25505.141606,0.00872474,0.88074,0.877511,0.270621
7850.0,25537.675341,0.00872325,0.887256,0.88476,0.255212
7860.0,25570.216244,0.00872176,0.889791,0.871715,0.251328
7870.0,25602.750528,0.00871978,0.891816,0.834063,0.247529
7880.0,25635.28816,0.00871829,0.887244,0.883833,0.256037
7890.0,25667.8229,0.0087168,0.886985,0.869724,0.25762
7900.0,25700.361208,0.00871481,0.891383,0.879943,0.245131
7910.0,25732.895599,0.00871332,0.872424,0.878324,0.290636
7920.0,25765.434631,0.00871183,0.888068,0.879646,0.254427
7930.0,25797.966478,0.00870984,0.890425,0.839954,0.251757
7940.0,25830.496431,0.00870835,0.880333,0.852825,0.276446
7950.0,25863.0313,0.00870686,0.880168,0.807615,0.276508
7960.0,25895.563028,0.00870487,0.886867,0.774539,0.259122
7970.0,25928.093717,0.00870338,0.884067,0.834047,0.262547
7980.0,25960.625185,0.00870189,0.875608,0.809793,0.28555
7990.0,25993.163371,0.0086999,0.896858,0.808308,0.242488
8000.0,26026.198722,0.00869841,0.891042,0.853314,0.249686
8010.0,26058.732926,0.00869692,0.896224,0.86384,0.237277
8020.0,26091.272601,0.00869493,0.88006,0.858532,0.273152
8030.0,26123.816301,0.00869344,0.886268,0.872702,0.259966
8040.0,26156.343496,0.00869195,0.889191,0.826563,0.25231
8050.0,26188.863336,0.00868996,0.882316,0.867776,0.267841
8060.0,26221.393093,0.00868847,0.891012,0.877183,0.251034
8070.0,26253.908829,0.00868698,0.881962,0.861513,0.274056
8080.0,26286.432987,0.00868499,0.891251,0.843688,0.247827
8090.0,26318.957638,0.0086835,0.885546,0.892338,0.260062
8100.0,26351.494635,0.00868201,0.879296,0.871859,0.276574
8110.0,26384.021129,0.00868002,0.886391,0.886657,0.256396
8120.0,26416.547156,0.00867852,0.890491,0.830293,0.249696
8130.0,26449.071402,0.00867703,0.884961,0.913883,0.262581
8140.0,26481.598577,0.00867504,0.896746,0.887929,0.235253
8150.0,26514.12166,0.00867355,0.880848,0.832058,0.273871
8160.0,26546.651616,0.00867206,0.885578,0.896809,0.259595
8170.0,26579.182406,0.00867007,0.888237,0.863928,0.25446
8180.0,26611.711313,0.00866858,0.89279,0.897066,0.242979
8190.0,26644.23612,0.00866709,0.890786,0.889278,0.247181
8200.0,26676.769097,0.0086651,0.893494,0.841192,0.243037
8210.0,26709.302614,0.0086636,0.892764,0.868628,0.24591
8220.0,26741.841632,0.00866211,0.888966,0.831971,0.253387
8230.0,26774.374604,0.00866012,0.867628,0.872297,0.299424
8240.0,26806.912003,0.00865863,0.881883,0.897156,0.270159
8250.0,26839.446599,0.00865713,0.875356,0.865789,0.287053
8260.0,26871.975707,0.00865514,0.892156,0.84566,0.247101
8270.0,26904.499764,0.00865365,0.887944,0.855044,0.254912
8280.0,26937.025594,0.00865216,0.893735,0.861169,0.243749
8290.0,26969.543067,0.00865017,0.873873,0.849828,0.282321
8300.0,27002.072185,0.00864867,0.893998,0.851102,0.240234
8310.0,27034.598212,0.00864718,0.888565,0.896063,0.254213
8320.0,27067.119463,0.00864519,0.885804,0.840882,0.260687
8330.0,27099.645517,0.0086437,0.891502,0.852622,0.250479
8340.0,27132.181041,0.0086422,0.884013,0.872046,0.266135
8350.0,27164.70409,0.00864021,0.887664,0.846927,0.25554
8360.0,27197.226231,0.00863872,0.892589,0.897277,0.243325
8370.0,27229.74737,0.00863722,0.879687,0.787774,0.279769
8380.0,27262.272941,0.00863523,0.876162,0.870363,0.281404
8390.0,27294.800023,0.00863374,0.891613,0.865073,0.248913
8400.0,27327.331388,0.00863224,0.887954,0.865805,0.2531
8410.0,27359.857721,0.00863025,0.877466,0.885081,0.277362
8420.0,27392.389871,0.00862876,0.890002,0.877482,0.250953
8430.0,27424.914847,0.00862726,0.892517,0.877969,0.246192
8440.0,27457.440869,0.00862527,0.889319,0.88183,0.253049
8450.0,27489.965985,0.00862378,0.882637,0.876374,0.267704
8460.0,27522.491625,0.00862228,0.88758,0.853912,0.254023
8470.0,27555.025742,0.00862029,0.877756,0.884191,0.277516
8480.0,27587.550795,0.0086188,0.891926,0.864555,0.247951
8490.0,27620.074643,0.0086173,0.885568,0.900849,0.259171
8500.0,27652.601911,0.00861531,0.884481,0.901862,0.259599
8510.0,27685.125976,0.00861381,0.890471,0.882017,0.250075
8520.0,27717.654066,0.00861232,0.887698,0.900287,0.255018
8530.0,27750.183953,0.00861033,0.88592,0.884206,0.26074
8540.0,27782.703932,0.00860883,0.867575,0.854087,0.300026
8550.0,27815.223246,0.00860734,0.842979,0.87146,0.346678
8560.0,27847.752242,0.00860534,0.885716,0.897648,0.259699
8570.0,27880.274095,0.00860385,0.8917,0.872376,0.247694
8580.0,27912.798994,0.00860235,0.887065,0.888756,0.255048
8590.0,27945.328563,0.00860036,0.899728,0.885701,0.229974
8600.0,27977.85419,0.00859886,0.891908,0.888719,0.245804
8610.0,28010.383229,0.00859737,0.880975,0.875459,0.27199
8620.0,28042.906632,0.00859537,0.890882,0.879487,0.24735
8630.0,28075.443011,0.00859388,0.875312,0.877448,0.279209
8640.0,28107.970396,0.00859238,0.894542,0.886324,0.243097
8650.0,28140.503521,0.00859039,0.895719,0.867037,0.239336
8660.0,28173.039926,0.00858889,0.887043,0.880167,0.256179
8670.0,28205.569222,0.0085874,0.896631,0.876855,0.236062
8680.0,28238.107024,0.0085854,0.864324,0.804887,0.308732
8690.0,28270.639591,0.00858391,0.868905,0.909038,0.295638
8700.0,28303.175318,0.00858241,0.88198,0.835031,0.269984
8710.0,28335.705518,0.00858041,0.892771,0.841524,0.244648
8720.0,28368.238183,0.00857892,0.891394,0.876786,0.248024
8730.0,28400.776048,0.00857742,0.895479,0.873942,0.238027
8740.0,28433.301731,0.00857543,0.887581,0.869762,0.254298
8750.0,28465.82433,0.00857393,0.8988,0.891297,0.233015
8760.0,28498.352273,0.00857243,0.893436,0.861252,0.24165
8770.0,28530.880428,0.00857044,0.884598,0.869287,0.267474
8780.0,28563.422302,0.00856894,0.895515,0.814831,0.242992
8790.0,28595.969342,0.00856745,0.888824,0.866985,0.253727
8800.0,28628.51309,0.00856545,0.89365,0.889515,0.242091
8810.0,28661.047362,0.00856395,0.888887,0.821771,0.256586
8820.0,28693.590029,0.00856246,0.886938,0.84141,0.2587
8830.0,28726.130908,0.00856046,0.891709,0.829002,0.249265
8840.0,28758.665856,0.00855896,0.886252,0.8743,0.257198
8850.0,28791.199688,0.00855747,0.893151,0.85237,0.247362
8860.0,28823.732203,0.00855547,0.858924,0.877875,0.320434
8870.0,28856.262331,0.00855397,0.875684,0.896755,0.283344
8880.0,28888.791937,0.00855247,0.887868,0.829838,0.251182
8890.0,28921.324319,0.00855048,0.885358,0.89762,0.262537
8900.0,28953.84875,0.00854898,0.884731,0.89196,0.259895
8910.0,28986.381547,0.00854748,0.892728,0.838408,0.244589
8920.0,29018.91467,0.00854549,0.885519,0.837704,0.261656
8930.0,29051.447333,0.00854399,0.889227,0.854076,0.253651
8940.0,29083.977191,0.00854249,0.870526,0.871828,0.291472
8950.0,29116.504945,0.00854049,0.893364,0.86513,0.247468
8960.0,29149.032933,0.008539,0.878976,0.86444,0.277733
8970.0,29181.562271,0.0085375,0.871581,0.85571,0.29283
8980.0,29214.088489,0.0085355,0.90112,0.902838,0.2282
8990.0,29246.609434,0.008534,0.88636,0.835025,0.257957
9000.0,29279.139251,0.0085325,0.892378,0.845023,0.246718
9010.0,29311.671251,0.00853051,0.897086,0.856723,0.235362
9020.0,29344.203756,0.00852901,0.893509,0.900566,0.244526
9030.0,29376.732485,0.00852751,0.876322,0.883136,0.281589
9040.0,29409.259238,0.00852551,0.877908,0.867089,0.277162
9050.0,29441.786396,0.00852401,0.887184,0.849334,0.25938
9060.0,29474.310676,0.00852251,0.888574,0.892838,0.252065
9070.0,29506.854664,0.00852052,0.884757,0.900339,0.259644
9080.0,29539.383938,0.00851902,0.878757,0.890806,0.273332
9090.0,29571.910823,0.00851752,0.890193,0.896976,0.249207
9100.0,29604.44066,0.00851552,0.892418,0.853673,0.247609
9110.0,29636.975229,0.00851402,0.880998,0.898347,0.271463
9120.0,29669.505933,0.00851252,0.895159,0.86739,0.23817
9130.0,29702.050213,0.00851052,0.893782,0.835363,0.243468
9140.0,29734.587409,0.00850902,0.883961,0.881094,0.263576
9150.0,29767.125484,0.00850752,0.894365,0.849216,0.241376
9160.0,29799.661063,0.00850552,0.897273,0.872123,0.233518
9170.0,29832.19027,0.00850402,0.891512,0.874175,0.24623
9180.0,29864.729198,0.00850253,0.894844,0.86969,0.239897
9190.0,29897.280762,0.00850053,0.895324,0.882536,0.238162
9200.0,29929.825802,0.00849903,0.894217,0.851981,0.243295
9210.0,29962.364069,0.00849753,0.891555,0.855359,0.249633
9220.0,29994.900876,0.00849553,0.873846,0.844557,0.288717
9230.0,30027.437154,0.00849403,0.883372,0.829808,0.268153
9240.0,30059.978145,0.00849253,0.896726,0.871043,0.236505
9250.0,30092.512941,0.00849053,0.884249,0.848059,0.265796
9260.0,30125.046744,0.00848903,0.889462,0.896482,0.250329
9270.0,30157.593287,0.00848753,0.900577,0.892835,0.230915
9280.0,30190.123448,0.00848552,0.893319,0.894889,0.243456
9290.0,30222.658347,0.00848402,0.891659,0.849373,0.249478
9300.0,30255.193025,0.00848252,0.891596,0.856961,0.249502
9310.0,30287.728944,0.00848052,0.89263,0.904815,0.245211
9320.0,30320.264917,0.00847902,0.896841,0.871284,0.237079
9330.0,30352.794737,0.00847752,0.869214,0.831274,0.302576
9340.0,30385.325522,0.00847552,0.89418,0.891929,0.239753
9350.0,30417.866799,0.00847402,0.891668,0.90338,0.247135
9360.0,30450.403525,0.00847252,0.870118,0.902751,0.29361
9370.0,30482.943896,0.00847052,0.889513,0.894974,0.249303
9380.0,30515.491533,0.00846902,0.890141,0.838455,0.249978
9390.0,30548.026271,0.00846752,0.896741,0.859546,0.237668
9400.0,30580.558941,0.00846551,0.886625,0.864086,0.256625
9410.0,30613.09552,0.00846401,0.897368,0.872817,0.236334
9420.0,30645.625468,0.00846251,0.894258,0.872742,0.240799
9430.0,30678.152516,0.00846051,0.890795,0.861197,0.248556
9440.0,30710.686314,0.00845901,0.897445,0.857079,0.234911
9450.0,30743.215029,0.00845751,0.881339,0.895756,0.268932
9460.0,30775.759809,0.0084555,0.883626,0.877885,0.265198
9470.0,30808.299953,0.008454,0.880203,0.865683,0.272097
9480.0,30840.827728,0.0084525,0.89387,0.888684,0.240313
9490.0,30873.35921,0.0084505,0.888426,0.811575,0.257865
9500.0,30905.896505,0.008449,0.891554,0.863113,0.243591
9510.0,30938.430011,0.0084475,0.876274,0.886046,0.282331
9520.0,30970.963426,0.00844549,0.897302,0.867337,0.238968
9530.0,31003.487916,0.00844399,0.861208,0.892407,0.314695
9540.0,31036.023762,0.00844249,0.894876,0.869949,0.239069
9550.0,31068.563445,0.00844048,0.871213,0.882851,0.290572
9560.0,31101.101057,0.00843898,0.893387,0.884409,0.242877
9570.0,31133.631372,0.00843748,0.888885,0.839271,0.256123
9580.0,31166.162447,0.00843548,0.883575,0.889524,0.260873
9590.0,31198.695017,0.00843397,0.895029,0.882566,0.237484
9600.0,31231.225825,0.00843247,0.894551,0.852452,0.242191
9610.0,31263.762155,0.00843047,0.870741,0.883681,0.292502
9620.0,31296.289163,0.00842896,0.878531,0.913318,0.278704
9630.0,31328.818605,0.00842746,0.885034,0.874192,0.259553
9640.0,31361.351399,0.00842546,0.883987,0.913355,0.263157
9650.0,31393.88595,0.00842396,0.89485,0.892179,0.239378
9660.0,31426.416781,0.00842245,0.887957,0.891349,0.256955
9670.0,31458.945029,0.00842045,0.886178,0.885005,0.255997
9680.0,31491.478135,0.00841894,0.890454,0.888522,0.249421
9690.0,31524.013636,0.00841744,0.899031,0.877721,0.23157
9700.0,31556.543765,0.00841544,0.88982,0.851181,0.253754
9710.0,31589.077408,0.00841393,0.880292,0.890423,0.272256
9720.0,31621.607484,0.00841243,0.88985,0.888366,0.250367
9730.0,31654.128523,0.00841042,0.889768,0.851196,0.25147
9740.0,31686.652846,0.00840892,0.892157,0.864856,0.246688
9750.0,31719.174412,0.00840742,0.891428,0.896178,0.245859
9760.0,31751.696259,0.00840541,0.884396,0.832374,0.267192
9770.0,31784.222784,0.00840391,0.897168,0.864423,0.236912
9780.0,31816.755074,0.0084024,0.893106,0.828161,0.2435
9790.0,31849.281711,0.0084004,0.869327,0.886438,0.293056
9800.0,31881.80888,0.00839889,0.895996,0.894877,0.238418
9810.0,31914.336481,0.00839739,0.892039,0.835519,0.24766
9820.0,31946.861514,0.00839538,0.882645,0.885049,0.266377
9830.0,31979.386593,0.00839388,0.880629,0.755636,0.278606
9840.0,32011.909068,0.00839237,0.89609,0.883358,0.237136
9850.0,32044.431682,0.00839037,0.892726,0.911936,0.246827
9860.0,32076.954983,0.00838886,0.880924,0.855499,0.267995
9870.0,32109.481185,0.00838736,0.894108,0.895933,0.240562
9880.0,32142.00791,0.00838535,0.900367,0.892694,0.227198
9890.0,32174.531704,0.00838385,0.898474,0.867512,0.233336
9900.0,32207.053301,0.00838234,0.885061,0.895121,0.258778
9910.0,32239.573522,0.00838034,0.890256,0.864581,0.250008
9920.0,32272.100119,0.00837883,0.885846,0.847453,0.260074
9930.0,32304.626475,0.00837733,0.894558,0.889427,0.241749
9940.0,32337.151098,0.00837532,0.890613,0.877591,0.248924
9950.0,32369.672881,0.00837381,0.892538,0.850264,0.245426
9960.0,32402.19529,0.00837231,0.877555,0.859755,0.276747
9970.0,32434.719392,0.0083703,0.886495,0.85983,0.258073
9980.0,32467.243518,0.0083688,0.859615,0.896943,0.317512
9990.0,32499.770013,0.00836729,0.886484,0.862852,0.260455
10000.0,32532.792376,0.00836528,0.86508,0.898232,0.305015
10010.0,32565.318035,0.00836378,0.780103,0.864031,0.453398
10020.0,32597.843651,0.00836227,0.892609,0.849809,0.245803
10030.0,32630.374278,0.00836026,0.892589,0.877334,0.246514
10040.0,32662.903229,0.00835876,0.878173,0.861632,0.280821
10050.0,32695.426158,0.00835725,0.887769,0.892965,0.256088
10060.0,32727.947595,0.00835524,0.887154,0.891437,0.25919
10070.0,32760.47053,0.00835374,0.890029,0.90605,0.247506
10080.0,32792.999107,0.00835223,0.894327,0.861085,0.240555
10090.0,32825.521052,0.00835022,0.896185,0.909498,0.236839
10100.0,32858.04782,0.00834872,0.89648,0.859665,0.237228
10110.0,32890.572281,0.00834721,0.889174,0.900232,0.251512
10120.0,32923.096275,0.0083452,0.892989,0.904176,0.242542
10130.0,32955.621172,0.00834369,0.888534,0.888546,0.256899
10140.0,32988.147675,0.00834219,0.889938,0.847424,0.25408
10150.0,33020.680222,0.00834018,0.885699,0.900527,0.259831
10160.0,33053.204548,0.00833867,0.895539,0.866286,0.239539
10170.0,33085.728284,0.00833717,0.891111,0.863015,0.246589
10180.0,33118.254082,0.00833516,0.893753,0.860089,0.245365
10190.0,33150.774209,0.00833365,0.886434,0.889809,0.258345
10200.0,33183.296596,0.00833214,0.88947,0.878225,0.255329
10210.0,33215.807356,0.00833013,0.890792,0.887275,0.247243
10220.0,33248.319297,0.00832862,0.882503,0.827886,0.268377
10230.0,33280.840824,0.00832712,0.888682,0.903714,0.253415
10240.0,33313.356413,0.00832511,0.896427,0.882329,0.238089
10250.0,33345.875631,0.0083236,0.897917,0.885055,0.233803
10260.0,33378.391673,0.00832209,0.895898,0.880382,0.238391
10270.0,33410.90281,0.00832008,0.893297,0.824343,0.244704
10280.0,33443.418491,0.00831857,0.894245,0.860165,0.241586
10290.0,33475.933104,0.00831707,0.89499,0.887076,0.240223
10300.0,33508.452031,0.00831506,0.892975,0.869834,0.243313
10310.0,33540.970509,0.00831355,0.900198,0.894713,0.228469
10320.0,33573.493967,0.00831204,0.895764,0.884288,0.239465
10330.0,33606.005883,0.00831003,0.885446,0.81968,0.263934
10340.0,33638.523056,0.00830852,0.873414,0.85102,0.287807
10350.0,33671.042403,0.00830701,0.876591,0.898097,0.279982
10360.0,33703.559667,0.008305,0.895982,0.869144,0.238219
10370.0,33736.070919,0.00830349,0.893616,0.882925,0.241366
10380.0,33768.585196,0.00830198,0.89716,0.886105,0.235731
10390.0,33801.097582,0.00829997,0.851835,0.853714,0.322765
10400.0,33833.614378,0.00829846,0.893423,0.860166,0.243706
10410.0,33866.128842,0.00829695,0.898529,0.907375,0.231527
10420.0,33898.639998,0.00829494,0.892924,0.915073,0.243085
10430.0,33931.16133,0.00829343,0.895003,0.888158,0.238495
10440.0,33963.678285,0.00829193,0.889292,0.897755,0.251544
10450.0,33996.191106,0.00828991,0.895578,0.885906,0.238916
10460.0,34028.71002,0.0082884,0.892827,0.875422,0.245284
10470.0,34061.22749,0.00828689,0.888066,0.898211,0.256242
10480.0,34093.743227,0.00828488,0.891654,0.906235,0.245817
10490.0,34126.261455,0.00828337,0.899853,0.912401,0.229588
10500.0,34158.778449,0.00828186,0.897864,0.87563,0.233306
10510.0,34191.295304,0.00827985,0.891509,0.898876,0.245905
10520.0,34223.807047,0.00827834,0.869344,0.844388,0.296792
10530.0,34256.319765,0.00827683,0.890166,0.873571,0.252661
10540.0,34288.839039,0.00827482,0.888282,0.86563,0.251793
10550.0,34321.360721,0.00827331,0.892186,0.910516,0.24571
10560.0,34353.87895,0.0082718,0.894006,0.880238,0.241937
10570.0,34386.390324,0.00826978,0.896106,0.863223,0.237322
10580.0,34418.911178,0.00826827,0.894599,0.868969,0.241302
10590.0,34451.424351,0.00826676,0.880894,0.85634,0.269309
10600.0,34483.943658,0.00826475,0.892241,0.873553,0.244567
10610.0,34516.458455,0.00826324,0.884248,0.852902,0.261809
10620.0,34548.976442,0.00826173,0.884216,0.903298,0.261916
10630.0,34581.495048,0.00825972,0.893633,0.879362,0.241552
10640.0,34614.012991,0.00825821,0.897558,0.896589,0.234013
10650.0,34646.530667,0.0082567,0.889833,0.917685,0.249683
10660.0,34679.048131,0.00825468,0.886722,0.839347,0.257655
10670.0,34711.563321,0.00825317,0.892086,0.854275,0.247475
10680.0,34744.077878,0.00825166,0.896351,0.900251,0.237091
10690.0,34776.594012,0.00824965,0.902056,0.88462,0.225546
10700.0,34809.122329,0.00824813,0.88286,0.832721,0.273483
10710.0,34841.637111,0.00824662,0.901621,0.8878,0.225105
10720.0,34874.155813,0.00824461,0.895733,0.863655,0.237944
10730.0,34906.670529,0.0082431,0.895248,0.901827,0.237632
10740.0,34939.179763,0.00824159,0.899116,0.888103,0.229827
10750.0,34971.701497,0.00823957,0.895271,0.832882,0.239963
10760.0,35004.221934,0.00823806,0.894075,0.899984,0.241288
10770.0,35036.742027,0.00823655,0.897546,0.871443,0.235348
10780.0,35069.252833,0.00823453,0.889609,0.874287,0.250771
10790.0,35101.771582,0.00823302,0.897542,0.890122,0.233832
10800.0,35134.287187,0.00823151,0.898143,0.88077,0.231784
10810.0,35166.80399,0.00822949,0.895106,0.895743,0.238981
10820.0,35199.323486,0.00822798,0.895389,0.879801,0.239485
10830.0,35231.843706,0.00822647,0.893084,0.828857,0.248339
10840.0,35264.358834,0.00822445,0.895845,0.862436,0.239281
10850.0,35296.874222,0.00822294,0.90503,0.89711,0.218499
10860.0,35329.389885,0.00822143,0.894929,0.901578,0.238723
10870.0,35361.907305,0.00821941,0.897501,0.904149,0.234616
10880.0,35394.418301,0.0082179,0.895996,0.881782,0.237357
10890.0,35426.935163,0.00821639,0.889029,0.894415,0.248825
10900.0,35459.445743,0.00821437,0.891071,0.870574,0.248219
10910.0,35491.95935,0.00821286,0.902333,0.902088,0.224708
10920.0,35524.473277,0.00821135,0.898481,0.88495,0.232287
10930.0,35556.993123,0.00820933,0.891243,0.904716,0.247815
10940.0,35589.509193,0.00820781,0.884548,0.866223,0.259454
10950.0,35622.029515,0.0082063,0.89329,0.864353,0.244382
10960.0,35654.544268,0.00820429,0.897575,0.870664,0.233963
10970.0,35687.058114,0.00820277,0.89905,0.891829,0.232674
10980.0,35719.573754,0.00820126,0.902373,0.850107,0.228037
10990.0,35752.084705,0.00819924,0.896263,0.859247,0.237148
11000.0,35784.59873,0.00819773,0.892927,0.839795,0.244825
11010.0,35817.114509,0.00819621,0.892153,0.873791,0.24557
11020.0,35849.626418,0.0081942,0.890131,0.838416,0.253069
11030.0,35882.143422,0.00819268,0.903497,0.888652,0.219846
11040.0,35914.66195,0.00819117,0.903937,0.887867,0.219788
11050.0,35947.182541,0.00818915,0.865152,0.908002,0.297954
11060.0,35979.699535,0.00818764,0.89303,0.898057,0.243145
11070.0,36012.219794,0.00818612,0.882782,0.904617,0.269724
11080.0,36044.735294,0.0081841,0.891473,0.907144,0.247389
11090.0,36077.251073,0.00818259,0.8929,0.890602,0.243339
11100.0,36109.765376,0.00818108,0.897947,0.897656,0.235097
11110.0,36142.279535,0.00817906,0.897262,0.897326,0.234225
11120.0,36174.796523,0.00817754,0.897702,0.902726,0.234063
11130.0,36207.318345,0.00817603,0.896011,0.868543,0.238371
11140.0,36239.833511,0.00817401,0.878127,0.910333,0.278614
11150.0,36272.350812,0.0081725,0.895052,0.898749,0.238274
11160.0,36304.873997,0.00817098,0.900068,0.904953,0.230464
11170.0,36337.390855,0.00816896,0.886796,0.888889,0.257044
11180.0,36369.908889,0.00816745,0.890127,0.892935,0.249038
11190.0,36402.427819,0.00816593,0.89726,0.89674,0.234027
11200.0,36434.944508,0.00816391,0.891863,0.907998,0.247448
11210.0,36467.465773,0.0081624,0.886587,0.906806,0.255912
11220.0,36499.988498,0.00816088,0.891998,0.867537,0.244765
11230.0,36532.506642,0.00815886,0.891027,0.911414,0.248572
11240.0,36565.025511,0.00815735,0.888393,0.887315,0.251395
11250.0,36597.545159,0.00815583,0.896673,0.869758,0.236847
11260.0,36630.059157,0.00815381,0.896706,0.874082,0.23694
11270.0,36662.574,0.0081523,0.889816,0.892204,0.24845
11280.0,36695.091228,0.00815078,0.892055,0.892326,0.245834
11290.0,36727.604746,0.00814876,0.900594,0.885882,0.230256
11300.0,36760.119501,0.00814724,0.899172,0.903019,0.228417
11310.0,36792.635644,0.00814573,0.892476,0.883244,0.242683
11320.0,36825.148216,0.00814371,0.883521,0.891511,0.265465
11330.0,36857.664667,0.00814219,0.894621,0.883448,0.239833
11340.0,36890.177385,0.00814067,0.895981,0.886983,0.237344
11350.0,36922.689398,0.00813865,0.885531,0.877797,0.261765
11360.0,36955.208529,0.00813714,0.893174,0.882431,0.245169
11370.0,36987.723791,0.00813562,0.843882,0.923838,0.349441
11380.0,37020.238857,0.0081336,0.89567,0.880548,0.238538
11390.0,37052.763536,0.00813208,0.890531,0.903314,0.249711
11400.0,37085.27845,0.00813057,0.886629,0.900953,0.254501
11410.0,37117.796652,0.00812855,0.880468,0.862771,0.27301
11420.0,37150.312997,0.00812703,0.896415,0.90328,0.235797
11430.0,37182.829364,0.00812551,0.896957,0.90681,0.236433
11440.0,37215.346803,0.00812349,0.879826,0.891532,0.274072
11450.0,37247.857942,0.00812197,0.892897,0.887125,0.244284
11460.0,37280.371613,0.00812046,0.893263,0.895304,0.242596
11470.0,37312.887231,0.00811843,0.898717,0.857209,0.233269
11480.0,37345.403819,0.00811692,0.897337,0.870302,0.234763
11490.0,37377.916639,0.0081154,0.895258,0.904923,0.239678
11500.0,37410.432356,0.00811338,0.899409,0.888987,0.230479
11510.0,37442.95058,0.00811186,0.897682,0.880049,0.234291
11520.0,37475.465636,0.00811034,0.897707,0.886599,0.234143
11530.0,37507.995156,0.00810832,0.896587,0.884196,0.235948
11540.0,37540.513616,0.0081068,0.889476,0.902365,0.251799
11550.0,37573.032146,0.00810528,0.896163,0.876559,0.238131
11560.0,37605.551995,0.00810326,0.899333,0.90784,0.229809
11570.0,37638.071423,0.00810174,0.889745,0.878619,0.249601
11580.0,37670.600105,0.00810022,0.894246,0.894683,0.240123
11590.0,37703.123423,0.0080982,0.891302,0.883083,0.246296
11600.0,37735.643889,0.00809668,0.897479,0.924944,0.234389
11610.0,37768.159677,0.00809516,0.905605,0.880521,0.217531
11620.0,37800.677501,0.00809314,0.887902,0.912499,0.25444
11630.0,37833.190656,0.00809162,0.894103,0.88834,0.240815
11640.0,37865.703118,0.0080901,0.828513,0.83658,0.37385
11650.0,37898.225115,0.00808808,0.893972,0.894484,0.240403
11660.0,37930.745943,0.00808656,0.892248,0.887954,0.245394
11670.0,37963.262236,0.00808504,0.878802,0.846829,0.274889
11680.0,37995.78297,0.00808302,0.898045,0.889675,0.233993
11690.0,38028.302809,0.0080815,0.90118,0.891874,0.226505
11700.0,38060.826247,0.00807998,0.901516,0.904147,0.224556
11710.0,38093.343158,0.00807795,0.89987,0.887327,0.232644
11720.0,38125.862445,0.00807643,0.892511,0.87312,0.24487
11730.0,38158.385564,0.00807492,0.899084,0.913212,0.230181
11740.0,38190.907956,0.00807289,0.892593,0.896293,0.242982
11750.0,38223.430925,0.00807137,0.899042,0.888342,0.229881
11760.0,38255.952958,0.00806985,0.889956,0.88826,0.249618
11770.0,38288.479377,0.00806783,0.873921,0.905257,0.287028
11780.0,38321.009463,0.00806631,0.899063,0.890718,0.230998
11790.0,38353.536528,0.00806479,0.888018,0.880468,0.255088
11800.0,38386.061105,0.00806276,0.891184,0.889685,0.24636
11810.0,38418.58761,0.00806124,0.883162,0.865354,0.263632
11820.0,38451.121333,0.00805972,0.884556,0.88752,0.261623
11830.0,38483.643898,0.00805769,0.891951,0.893574,0.244542
11840.0,38516.170601,0.00805617,0.904211,0.858427,0.222163
11850.0,38548.700298,0.00805466,0.883046,0.834889,0.264654
11860.0,38581.230603,0.00805263,0.89182,0.897188,0.244342
11870.0,38613.759292,0.00805111,0.89529,0.896625,0.239062
11880.0,38646.285164,0.00804959,0.88842,0.902893,0.251075
11890.0,38678.817469,0.00804756,0.897124,0.88033,0.234707
11900.0,38711.351792,0.00804604,0.888764,0.88941,0.253716
11910.0,38743.883215,0.00804452,0.892514,0.869254,0.243615
11920.0,38776.415309,0.00804249,0.894593,0.882566,0.241794
11930.0,38808.948642,0.00804097,0.891806,0.899496,0.245697
11940.0,38841.489725,0.00803945,0.899186,0.876111,0.230483
11950.0,38874.026142,0.00803742,0.895084,0.888319,0.238241
11960.0,38906.560449,0.0080359,0.901625,0.893469,0.226395
11970.0,38939.095029,0.00803438,0.894188,0.850336,0.242522
11980.0,38971.627088,0.00803235,0.893582,0.921442,0.24171
11990.0,39004.154626,0.00803083,0.892989,0.89885,0.2426
12000.0,39037.174588,0.00802931,0.897114,0.864095,0.235512
12010.0,39069.714152,0.00802728,0.897075,0.873057,0.236456
12020.0,39102.240504,0.00802576,0.898185,0.871242,0.231863
12030.0,39134.766271,0.00802424,0.886161,0.896364,0.257374
12040.0,39167.289014,0.00802221,0.894697,0.899835,0.242934
12050.0,39199.812024,0.00802069,0.894548,0.89856,0.239558
12060.0,39232.335123,0.00801917,0.901044,0.896338,0.226196
12070.0,39264.863948,0.00801714,0.893109,0.904422,0.242407
12080.0,39297.389306,0.00801562,0.897848,0.906313,0.232657
12090.0,39329.915038,0.0080141,0.892876,0.904768,0.244442
12100.0,39362.448568,0.00801207,0.897481,0.901383,0.234896
12110.0,39394.976162,0.00801054,0.884936,0.893859,0.262665
12120.0,39427.488709,0.00800902,0.901138,0.887044,0.22663
12130.0,39460.000776,0.00800699,0.898277,0.847755,0.233905
12140.0,39492.532957,0.00800547,0.899704,0.891109,0.22839
12150.0,39525.051242,0.00800395,0.892389,0.895873,0.250295
12160.0,39557.568083,0.00800192,0.894512,0.851376,0.239455
12170.0,39590.07939,0.0080004,0.896968,0.881061,0.234801
12180.0,39622.598776,0.00799887,0.894176,0.855687,0.24154
12190.0,39655.123007,0.00799684,0.891977,0.884444,0.244267
12200.0,39687.644611,0.00799532,0.888841,0.904112,0.251184
12210.0,39720.171438,0.0079938,0.887329,0.834094,0.259929
12220.0,39752.693903,0.00799177,0.889467,0.874228,0.250483
12230.0,39785.222551,0.00799024,0.890314,0.89081,0.247723
12240.0,39817.743452,0.00798872,0.882589,0.919708,0.269559
12250.0,39850.262334,0.00798669,0.898939,0.864968,0.234114
12260.0,39882.782812,0.00798517,0.898003,0.868723,0.234803
12270.0,39915.322421,0.00798364,0.899529,0.87372,0.231429
12280.0,39947.856692,0.00798161,0.854661,0.835186,0.327258
12290.0,39980.378024,0.00798009,0.896732,0.858115,0.238658
12300.0,40012.901704,0.00797856,0.893206,0.830519,0.244254
12310.0,40045.420567,0.00797653,0.889561,0.897989,0.251839
12320.0,40077.939867,0.00797501,0.896869,0.889688,0.235039
12330.0,40110.459357,0.00797348,0.904526,0.85447,0.219081
12340.0,40142.977523,0.00797145,0.901197,0.895859,0.224793
12350.0,40175.522958,0.00796993,0.896284,0.864068,0.236208
12360.0,40208.057892,0.0079684,0.889537,0.896583,0.252853
12370.0,40240.597453,0.00796637,0.900188,0.906534,0.227246
12380.0,40273.123402,0.00796485,0.893466,0.906299,0.24232
12390.0,40305.659814,0.00796332,0.899297,0.881181,0.229814
12400.0,40338.204632,0.00796129,0.891969,0.885873,0.245323
12410.0,40370.740632,0.00795977,0.899503,0.908809,0.229957
12420.0,40403.26473,0.00795824,0.88382,0.897606,0.26299
12430.0,40435.788294,0.00795621,0.886647,0.867807,0.256625
12440.0,40468.308983,0.00795468,0.886225,0.876942,0.262961
12450.0,40500.833959,0.00795316,0.894832,0.887964,0.239038
12460.0,40533.358966,0.00795113,0.895261,0.888798,0.23932
12470.0,40565.88282,0.0079496,0.891692,0.919872,0.245655
12480.0,40598.416553,0.00794808,0.895521,0.895678,0.237816
12490.0,40630.940586,0.00794604,0.886336,0.869559,0.258285
12500.0,40663.481389,0.00794452,0.892683,0.882103,0.242662
12510.0,40696.015051,0.00794299,0.893585,0.87657,0.242395
12520.0,40728.536785,0.00794096,0.889133,0.89577,0.251864
12530.0,40761.064687,0.00793943,0.898733,0.899974,0.230649
12540.0,40793.589872,0.00793791,0.897289,0.867695,0.235595
12550.0,40826.124023,0.00793587,0.895292,0.898814,0.238063
12560.0,40858.658996,0.00793435,0.900118,0.898025,0.230818
12570.0,40891.181414,0.00793282,0.90091,0.898244,0.225422
12580.0,40923.715438,0.00793079,0.898649,0.899591,0.232192
12590.0,40956.247744,0.00792926,0.901006,0.895903,0.223989
12600.0,40988.766312,0.00792774,0.897494,0.88933,0.234503
12610.0,41021.297123,0.0079257,0.892383,0.891004,0.244133
12620.0,41053.826788,0.00792417,0.888482,0.895805,0.255537
12630.0,41086.358767,0.00792265,0.894821,0.911548,0.24038
12640.0,41118.896318,0.00792061,0.899489,0.914379,0.230975
12650.0,41151.424959,0.00791909,0.894355,0.91135,0.239588
12660.0,41183.958817,0.00791756,0.894977,0.895578,0.239028
12670.0,41216.482877,0.00791552,0.886411,0.914677,0.258069
12680.0,41249.015116,0.007914,0.894421,0.901022,0.239998
12690.0,41281.55047,0.00791247,0.886695,0.900702,0.255318
12700.0,41314.082216,0.00791044,0.895924,0.898316,0.237517
12710.0,41346.599792,0.00790891,0.901152,0.896911,0.225265
12720.0,41379.125235,0.00790738,0.893503,0.905362,0.241389
12730.0,41411.65669,0.00790534,0.893335,0.912291,0.242744
12740.0,41444.188146,0.00790382,0.894441,0.905699,0.240052
12750.0,41476.714738,0.00790229,0.888356,0.89177,0.252429
12760.0,41509.242917,0.00790025,0.893051,0.879592,0.2451
12770.0,41541.801649,0.00789873,0.895461,0.918893,0.238783
12780.0,41574.361777,0.0078972,0.897412,0.899009,0.233853
12790.0,41606.928321,0.00789516,0.894852,0.893639,0.239952
12800.0,41639.481542,0.00789363,0.888031,0.901595,0.252233
12810.0,41672.024153,0.00789211,0.901355,0.882261,0.226618
12820.0,41704.560205,0.00789007,0.902442,0.867076,0.224561
12830.0,41737.091219,0.00788854,0.906011,0.881313,0.216448
12840.0,41769.623847,0.00788701,0.88619,0.793559,0.263705
12850.0,41802.150732,0.00788498,0.893679,0.868587,0.240381
12860.0,41834.684659,0.00788345,0.892015,0.890086,0.24604
12870.0,41867.223213,0.00788192,0.890123,0.859749,0.250605
12880.0,41899.758465,0.00787988,0.896205,0.880999,0.238783
12890.0,41932.287691,0.00787835,0.893208,0.898469,0.244555
12900.0,41964.823908,0.00787683,0.897112,0.899702,0.234389
12910.0,41997.352196,0.00787479,0.889623,0.896355,0.253639
12920.0,42029.880708,0.00787326,0.88671,0.881522,0.255575
12930.0,42062.411324,0.00787173,0.883479,0.88429,0.264892
12940.0,42094.938707,0.00786969,0.901781,0.915024,0.224606
12950.0,42127.462773,0.00786816,0.886087,0.91916,0.259694
12960.0,42160.00899,0.00786663,0.893468,0.912497,0.243807
12970.0,42192.533773,0.00786459,0.879317,0.915039,0.269979
12980.0,42225.068289,0.00786307,0.891475,0.900407,0.245372
12990.0,42257.599744,0.00786154,0.896422,0.901814,0.23482
13000.0,42290.129512,0.0078595,0.896703,0.8764,0.236351
13010.0,42322.660953,0.00785797,0.886757,0.887958,0.26083
13020.0,42355.196085,0.00785644,0.891651,0.913591,0.245649
13030.0,42387.732398,0.0078544,0.895018,0.895766,0.240503
13040.0,42420.265572,0.00785287,0.897864,0.91638,0.234997
13050.0,42452.796363,0.00785134,0.898365,0.897065,0.232879
13060.0,42485.32425,0.0078493,0.887609,0.895699,0.256819
13070.0,42517.860332,0.00784777,0.892219,0.891397,0.24481
13080.0,42550.400252,0.00784624,0.887098,0.900628,0.259918
13090.0,42582.935687,0.0078442,0.89537,0.910823,0.238278
13100.0,42615.473391,0.00784267,0.894886,0.892333,0.24199
13110.0,42647.999889,0.00784114,0.893959,0.894521,0.24094
13120.0,42680.527733,0.0078391,0.900425,0.888901,0.228713
13130.0,42713.059914,0.00783757,0.891729,0.917539,0.245947
13140.0,42745.59365,0.00783604,0.895081,0.885458,0.240903
13150.0,42778.116969,0.007834,0.898566,0.918808,0.234452
13160.0,42810.645288,0.00783247,0.888989,0.899269,0.251177
13170.0,42843.170197,0.00783094,0.901254,0.904546,0.227056
13180.0,42875.694938,0.0078289,0.899521,0.897132,0.230058
13190.0,42908.229376,0.00782736,0.90203,0.899389,0.223086
13200.0,42940.767622,0.00782583,0.898246,0.889787,0.232265
13210.0,42973.30725,0.00782379,0.886041,0.913557,0.259702
13220.0,43005.84132,0.00782226,0.897057,0.879961,0.23639
13230.0,43038.378469,0.00782073,0.88148,0.922098,0.267578
13240.0,43070.914977,0.00781869,0.896349,0.894905,0.235829
13250.0,43103.453601,0.00781716,0.887738,0.891797,0.255302
13260.0,43135.979607,0.00781562,0.892346,0.921174,0.243051
13270.0,43168.511845,0.00781358,0.899065,0.897772,0.229317
13280.0,43201.04591,0.00781205,0.896192,0.932155,0.235693
13290.0,43233.58119,0.00781052,0.902642,0.910768,0.221088
13300.0,43266.116077,0.00780848,0.895594,0.909509,0.237945
13310.0,43298.645412,0.00780694,0.893168,0.91564,0.243675
13320.0,43331.178384,0.00780541,0.88583,0.913007,0.259698
13330.0,43363.705167,0.00780337,0.892393,0.918553,0.243518
13340.0,43396.236244,0.00780184,0.888588,0.876941,0.253172
13350.0,43428.760883,0.00780031,0.894315,0.904402,0.240703
13360.0,43461.302624,0.00779826,0.881307,0.873299,0.271729
13370.0,43493.840315,0.00779673,0.869089,0.787312,0.300281
13380.0,43526.37169,0.0077952,0.896186,0.917863,0.239468
13390.0,43558.908586,0.00779315,0.901957,0.886351,0.226784
13400.0,43591.447317,0.00779162,0.894871,0.90655,0.238907
13410.0,43623.985623,0.00779009,0.897193,0.864683,0.233453
13420.0,43656.525154,0.00778804,0.895849,0.895529,0.237498
13430.0,43689.065189,0.00778651,0.896835,0.874668,0.236826
13440.0,43721.603323,0.00778498,0.90508,0.9021,0.218591
13450.0,43754.133745,0.00778293,0.897084,0.877653,0.23514
13460.0,43786.662684,0.0077814,0.868316,0.860353,0.297081
13470.0,43819.200001,0.00777987,0.89735,0.897526,0.236155
13480.0,43851.736179,0.00777782,0.893449,0.876616,0.245444
13490.0,43884.271438,0.00777629,0.897202,0.907688,0.234873
13500.0,43916.802483,0.00777476,0.888676,0.888351,0.25203
13510.0,43949.331418,0.00777271,0.895682,0.861728,0.236409
13520.0,43981.862033,0.00777118,0.903023,0.901068,0.222183
13530.0,44014.386856,0.00776965,0.89624,0.902691,0.23675
13540.0,44046.905479,0.0077676,0.886059,0.81504,0.264813
13550.0,44079.43106,0.00776607,0.893999,0.904181,0.240314
13560.0,44111.965922,0.00776453,0.900786,0.872367,0.228637
13570.0,44144.487311,0.00776249,0.900652,0.890085,0.227649
13580.0,44177.015406,0.00776095,0.894729,0.879998,0.241197
13590.0,44209.538175,0.00775942,0.89212,0.859301,0.24899
13600.0,44242.069128,0.00775737,0.897153,0.854705,0.23876
13610.0,44274.596166,0.00775584,0.893785,0.910004,0.243479
13620.0,44307.126984,0.0077543,0.896599,0.872349,0.238131
13630.0,44339.655165,0.00775226,0.894176,0.891747,0.240158
13640.0,44372.189095,0.00775072,0.897832,0.871785,0.234277
13650.0,44404.723038,0.00774919,0.900415,0.888805,0.228651
13660.0,44437.252312,0.00774714,0.901377,0.883767,0.225793
13670.0,44469.782886,0.00774561,0.896836,0.877985,0.234943
13680.0,44502.318664,0.00774407,0.893233,0.831548,0.25136
13690.0,44534.851241,0.00774202,0.893844,0.814151,0.247131
13700.0,44567.37575,0.00774049,0.879677,0.785614,0.277798
13710.0,44599.91237,0.00773895,0.89649,0.81662,0.239646
13720.0,44632.43898,0.00773691,0.899559,0.869403,0.232306
13730.0,44664.973109,0.00773537,0.877138,0.7626,0.285257
13740.0,44697.501457,0.00773384,0.89628,0.867299,0.238915
13750.0,44730.032445,0.00773179,0.889895,0.77499,0.257484
13760.0,44762.562679,0.00773025,0.876372,0.836284,0.286517
13770.0,44795.091411,0.00772872,0.897412,0.874364,0.237824
13780.0,44827.621427,0.00772667,0.894963,0.85799,0.240848
13790.0,44860.154473,0.00772513,0.898465,0.869143,0.232037
13800.0,44892.680761,0.0077236,0.903234,0.882169,0.221635
13810.0,44925.208039,0.00772155,0.903429,0.911777,0.223354
13820.0,44957.742573,0.00772001,0.903645,0.901789,0.221145
13830.0,44990.272233,0.00771848,0.903911,0.908649,0.221717
13840.0,45022.805081,0.00771643,0.895676,0.898772,0.238329
13850.0,45055.331864,0.00771489,0.894901,0.905631,0.24092
13860.0,45087.851807,0.00771336,0.898643,0.898123,0.233841
13870.0,45120.380588,0.00771131,0.882796,0.899678,0.267118
13880.0,45152.907436,0.00770977,0.895497,0.919372,0.241048
13890.0,45185.436388,0.00770823,0.894262,0.907266,0.242632
13900.0,45217.959481,0.00770618,0.893772,0.934522,0.24305
13910.0,45250.486642,0.00770465,0.896796,0.915222,0.234412
13920.0,45283.014923,0.00770311,0.896844,0.910498,0.235546
13930.0,45315.540378,0.00770106,0.85429,0.873464,0.32624
13940.0,45348.066528,0.00769952,0.902744,0.911044,0.223286
13950.0,45380.599235,0.00769799,0.890746,0.90439,0.248269
13960.0,45413.130404,0.00769594,0.895471,0.895974,0.240295
13970.0,45445.659495,0.0076944,0.896158,0.893789,0.237854
13980.0,45478.19154,0.00769286,0.897653,0.887906,0.234129
13990.0,45510.728253,0.00769081,0.889224,0.904867,0.253944
14000.0,45543.758789,0.00768927,0.894599,0.920764,0.24194
14010.0,45576.294927,0.00768773,0.897146,0.918084,0.235858
14020.0,45608.841586,0.00768568,0.89166,0.886019,0.248446
14030.0,45641.37193,0.00768415,0.896041,0.90728,0.23706
14040.0,45673.911543,0.00768261,0.891502,0.913945,0.251766
14050.0,45706.444163,0.00768056,0.888496,0.895258,0.25398
14060.0,45738.972186,0.00767902,0.887761,0.911708,0.25534
14070.0,45771.503876,0.00767748,0.894485,0.921675,0.240124
14080.0,45804.033986,0.00767543,0.896149,0.907816,0.237883
14090.0,45836.563833,0.00767389,0.896984,0.893151,0.238175
14100.0,45869.090716,0.00767235,0.890507,0.906167,0.248718
14110.0,45901.620723,0.0076703,0.885958,0.90456,0.258813
14120.0,45934.144812,0.00766876,0.900465,0.91186,0.226805
14130.0,45966.671209,0.00766722,0.901016,0.917429,0.227466
14140.0,45999.201224,0.00766517,0.8991,0.930077,0.232108
14150.0,46031.729419,0.00766363,0.900481,0.914658,0.229861
14160.0,46064.257846,0.00766209,0.897528,0.900951,0.235371
14170.0,46096.788798,0.00766004,0.880507,0.925629,0.276152
14180.0,46129.31557,0.0076585,0.901957,0.928496,0.225586
14190.0,46161.844965,0.00765696,0.894143,0.930453,0.243551
14200.0,46194.378755,0.00765491,0.894805,0.913169,0.239743
14210.0,46226.907261,0.00765337,0.90029,0.878114,0.229953
14220.0,46259.428009,0.00765183,0.897348,0.92567,0.235272
14230.0,46291.954268,0.00764978,0.885997,0.884837,0.257898
14240.0,46324.485441,0.00764824,0.894412,0.914485,0.242802
14250.0,46357.006757,0.0076467,0.901379,0.904952,0.226188
14260.0,46389.530985,0.00764465,0.880632,0.917827,0.271661
14270.0,46422.058002,0.00764311,0.901473,0.887848,0.225303
14280.0,46454.588045,0.00764157,0.888412,0.922708,0.257379
14290.0,46487.110409,0.00763951,0.896504,0.90246,0.236284
14300.0,46519.63575,0.00763797,0.898987,0.921804,0.231823
14310.0,46552.160135,0.00763643,0.900436,0.879796,0.228613
14320.0,46584.695595,0.00763438,0.897911,0.903811,0.232951
14330.0,46617.22558,0.00763284,0.903221,0.884401,0.220463
14340.0,46649.764427,0.0076313,0.895178,0.906002,0.240088
14350.0,46682.3054,0.00762924,0.902832,0.900666,0.221952
14360.0,46714.840917,0.0076277,0.899061,0.919044,0.232283
14370.0,46747.375342,0.00762616,0.901653,0.892637,0.226005
14380.0,46779.910558,0.00762411,0.891685,0.902242,0.247352
14390.0,46812.436485,0.00762256,0.899771,0.924993,0.229739
14400.0,46844.983035,0.00762102,0.900641,0.889141,0.227753
14410.0,46877.530723,0.00761897,0.905461,0.919316,0.218698
14420.0,46910.079725,0.00761743,0.88543,0.886221,0.265421
14430.0,46942.623765,0.00761588,0.893545,0.91574,0.242572
14440.0,46975.170439,0.00761383,0.894594,0.903759,0.239904
14450.0,47007.715078,0.00761229,0.907293,0.919167,0.211517
14460.0,47040.257033,0.00761075,0.896749,0.89516,0.238275
14470.0,47072.783808,0.00760869,0.890405,0.898,0.248693
14480.0,47105.326044,0.00760715,0.895338,0.905762,0.23793
14490.0,47137.867221,0.00760561,0.898217,0.898905,0.233913
14500.0,47170.413392,0.00760355,0.898494,0.915712,0.231619
14510.0,47202.942892,0.00760201,0.902595,0.876074,0.226323
14520.0,47235.487093,0.00760047,0.902685,0.905432,0.223061
14530.0,47268.031853,0.00759841,0.900423,0.885773,0.22865
14540.0,47300.577227,0.00759687,0.901474,0.923249,0.226946
14550.0,47333.123752,0.00759533,0.901784,0.907935,0.225407
14560.0,47365.666093,0.00759327,0.897697,0.906091,0.235125
14570.0,47398.207099,0.00759173,0.905319,0.899576,0.217827
14580.0,47430.753667,0.00759018,0.844646,0.890082,0.341113
14590.0,47463.298628,0.00758813,0.8904,0.927601,0.250183
14600.0,47495.835626,0.00758658,0.893661,0.90512,0.243413
14610.0,47528.376023,0.00758504,0.896223,0.910139,0.23839
14620.0,47560.912812,0.00758298,0.897108,0.896556,0.236071
14630.0,47593.456361,0.00758144,0.905853,0.899707,0.215322
14640.0,47625.993602,0.0075799,0.905161,0.899574,0.221149
14650.0,47658.534182,0.00757784,0.892492,0.926091,0.245232
14660.0,47691.069394,0.0075763,0.89545,0.895378,0.24194
14670.0,47723.607087,0.00757475,0.894465,0.910889,0.242658
14680.0,47756.142611,0.00757269,0.884253,0.906571,0.265235
14690.0,47788.681805,0.00757115,0.893973,0.901233,0.23948
14700.0,47821.215125,0.00756961,0.895242,0.915723,0.239113
14710.0,47853.748781,0.00756755,0.902652,0.897549,0.223606
14720.0,47886.292084,0.007566,0.890016,0.924529,0.250747
14730.0,47918.836297,0.00756446,0.88961,0.858916,0.253772
14740.0,47951.368271,0.0075624,0.877292,0.872004,0.279675
14750.0,47983.909439,0.00756086,0.893863,0.893509,0.240723
14760.0,48016.446121,0.00755931,0.89982,0.917321,0.227871
14770.0,48048.986208,0.00755725,0.884682,0.872832,0.261897
14780.0,48081.520988,0.00755571,0.89671,0.903033,0.236896
14790.0,48114.065326,0.00755416,0.893407,0.903071,0.243842
14800.0,48146.609324,0.0075521,0.896285,0.885086,0.237244
14810.0,48179.146838,0.00755056,0.896477,0.900332,0.236302
14820.0,48211.692533,0.00754901,0.89964,0.894868,0.230518
14830.0,48244.234556,0.00754696,0.901,0.92849,0.2275
14840.0,48276.769853,0.00754541,0.897564,0.906311,0.233508
14850.0,48309.305218,0.00754387,0.90482,0.908419,0.220847
14860.0,48341.839592,0.0075418,0.893223,0.927719,0.245132
14870.0,48374.373315,0.00754026,0.895391,0.91692,0.238772
14880.0,48406.907532,0.00753871,0.889466,0.922946,0.255698
14890.0,48439.451507,0.00753665,0.898201,0.891194,0.234173
14900.0,48471.991135,0.00753511,0.889889,0.924646,0.25286
14910.0,48504.522653,0.00753356,0.904194,0.896882,0.220307
14920.0,48537.049179,0.0075315,0.897071,0.912387,0.236076
14930.0,48569.578648,0.00752996,0.870406,0.849456,0.287959
14940.0,48602.103878,0.00752841,0.894899,0.87455,0.241161
14950.0,48634.632411,0.00752635,0.8988,0.889052,0.23221
14960.0,48667.153746,0.0075248,0.876071,0.919,0.279978
14970.0,48699.677616,0.00752326,0.896566,0.93004,0.234935
14980.0,48732.203334,0.00752119,0.893684,0.910509,0.241015
14990.0,48764.727857,0.00751965,0.906526,0.920349,0.215488
15000.0,48797.252221,0.0075181,0.892333,0.924802,0.246853
15010.0,48829.774593,0.00751604,0.891597,0.897099,0.247554
15020.0,48862.297802,0.00751449,0.896796,0.915606,0.235653
15030.0,48894.822834,0.00751295,0.883061,0.877649,0.267769
15040.0,48927.345014,0.00751088,0.88184,0.916803,0.270192
15050.0,48959.870376,0.00750934,0.893433,0.916097,0.243713
15060.0,48992.391317,0.00750779,0.901306,0.898373,0.226158
15070.0,49024.911353,0.00750573,0.90034,0.894602,0.228954
15080.0,49057.428318,0.00750418,0.898324,0.930698,0.232626
15090.0,49089.94715,0.00750263,0.900428,0.917753,0.227994
15100.0,49122.471687,0.00750057,0.898323,0.925709,0.23317
15110.0,49154.988326,0.00749902,0.899253,0.92259,0.232752
15120.0,49187.50578,0.00749748,0.903729,0.905376,0.221173
15130.0,49220.032509,0.00749541,0.897987,0.918181,0.234451
15140.0,49252.551815,0.00749386,0.89908,0.910558,0.231441
15150.0,49285.067078,0.00749232,0.893819,0.89312,0.24032
15160.0,49317.588884,0.00749025,0.898786,0.919629,0.2284
15170.0,49350.105433,0.0074887,0.900198,0.901782,0.227268
15180.0,49382.631,0.00748716,0.905058,0.907812,0.217064
15190.0,49415.154298,0.00748509,0.900573,0.897119,0.228318
15200.0,49447.681718,0.00748354,0.895583,0.916185,0.237781
15210.0,49480.202927,0.007482,0.904261,0.89208,0.220791
15220.0,49512.725083,0.00747993,0.902844,0.913481,0.222785
15230.0,49545.24726,0.00747838,0.888145,0.906557,0.253675
15240.0,49577.768379,0.00747683,0.882275,0.900668,0.268538
15250.0,49610.287389,0.00747477,0.896415,0.934442,0.238751
15260.0,49642.808336,0.00747322,0.900823,0.905767,0.228798
15270.0,49675.329832,0.00747167,0.898983,0.917676,0.233298
15280.0,49707.847674,0.00746961,0.899975,0.912338,0.229938
15290.0,49740.367181,0.00746806,0.91067,0.903439,0.207412
15300.0,49772.890276,0.00746651,0.901598,0.929477,0.225504
15310.0,49805.416001,0.00746444,0.897096,0.92105,0.237394
15320.0,49837.943879,0.00746289,0.902318,0.889684,0.224171
15330.0,49870.472525,0.00746134,0.902938,0.888417,0.224044
15340.0,49902.997425,0.00745928,0.894663,0.906807,0.243995
15350.0,49935.519462,0.00745773,0.896873,0.8887,0.237013
15360.0,49968.042827,0.00745618,0.886041,0.912665,0.260106
15370.0,50000.586489,0.00745411,0.89721,0.909627,0.235081
15380.0,50033.134517,0.00745256,0.899609,0.924404,0.232613
15390.0,50065.652033,0.00745101,0.902449,0.932543,0.225742
15400.0,50098.168414,0.00744895,0.901886,0.920528,0.223248
15410.0,50130.717883,0.0074474,0.892875,0.923795,0.245817
15420.0,50163.271681,0.00744585,0.89033,0.917912,0.249519
15430.0,50195.815525,0.00744378,0.901164,0.905254,0.226551
15440.0,50228.361478,0.00744223,0.893483,0.88048,0.245456
15450.0,50260.906191,0.00744068,0.902951,0.910321,0.223264
15460.0,50293.45058,0.00743861,0.901735,0.877873,0.226155
15470.0,50325.996557,0.00743706,0.89717,0.902316,0.235212
15480.0,50358.553586,0.00743551,0.906856,0.920162,0.21292
15490.0,50391.104603,0.00743344,0.906058,0.918589,0.214931
15500.0,50423.661099,0.00743189,0.892602,0.909938,0.243279
15510.0,50456.221605,0.00743034,0.905652,0.928136,0.21685
15520.0,50488.779943,0.00742827,0.896893,0.906166,0.236524
15530.0,50521.337283,0.00742672,0.902112,0.904554,0.224352
15540.0,50553.890006,0.00742517,0.899583,0.913808,0.231385
15550.0,50586.446128,0.0074231,0.895128,0.864912,0.240392
15560.0,50618.976507,0.00742155,0.899625,0.899086,0.229548
15570.0,50651.506918,0.00742,0.895657,0.900402,0.236835
15580.0,50684.035802,0.00741793,0.903466,0.910097,0.22116
15590.0,50716.570779,0.00741638,0.902737,0.910384,0.223309
15600.0,50749.097494,0.00741483,0.897042,0.925639,0.234744
15610.0,50781.624745,0.00741276,0.909109,0.900118,0.209911
15620.0,50814.149217,0.00741121,0.890606,0.914373,0.248232
15630.0,50846.679783,0.00740965,0.905013,0.885412,0.218919
15640.0,50879.212965,0.00740758,0.903868,0.905658,0.219871
15650.0,50911.7419,0.00740603,0.901465,0.893878,0.226313
15660.0,50944.275732,0.00740448,0.902769,0.907073,0.223216
15670.0,50976.800101,0.00740241,0.905896,0.893597,0.215641
15680.0,51009.323424,0.00740086,0.89801,0.887922,0.2352
15690.0,51041.849342,0.0073993,0.90497,0.871915,0.220402
15700.0,51074.379419,0.00739723,0.903644,0.90068,0.221765
15710.0,51106.901252,0.00739568,0.901368,0.928878,0.224504
15720.0,51139.425231,0.00739413,0.909425,0.906351,0.209615
15730.0,51171.948151,0.00739206,0.906752,0.925279,0.215348
15740.0,51204.477297,0.00739051,0.882438,0.883526,0.26764
15750.0,51237.002792,0.00738895,0.903021,0.922807,0.22444
15760.0,51269.527923,0.00738688,0.897702,0.904729,0.234425
15770.0,51302.051824,0.00738533,0.899708,0.915782,0.229671
15780.0,51334.57676,0.00738378,0.898841,0.861686,0.233435
15790.0,51367.101617,0.0073817,0.899403,0.887607,0.231571
15800.0,51399.632919,0.00738015,0.901264,0.915564,0.227075
15810.0,51432.16483,0.0073786,0.901614,0.9062,0.225154
15820.0,51464.685544,0.00737652,0.895571,0.900477,0.240338
15830.0,51497.216849,0.00737497,0.896681,0.907707,0.236618
15840.0,51529.740826,0.00737342,0.909383,0.921387,0.211439
15850.0,51562.269128,0.00737134,0.897941,0.902786,0.235811
15860.0,51594.798211,0.00736979,0.895006,0.909993,0.241559
15870.0,51627.326072,0.00736824,0.909659,0.900741,0.207796
15880.0,51659.847517,0.00736616,0.90281,0.910234,0.222589
15890.0,51692.372141,0.00736461,0.900976,0.912422,0.227022
15900.0,51724.892668,0.00736306,0.890446,0.913601,0.250525
15910.0,51757.421091,0.00736098,0.895175,0.935395,0.240693
15920.0,51789.942021,0.00735943,0.887716,0.92878,0.255093
15930.0,51822.479814,0.00735787,0.907023,0.918532,0.215592
15940.0,51855.009598,0.0073558,0.883806,0.924415,0.261786
15950.0,51887.532478,0.00735424,0.898376,0.836207,0.232809
15960.0,51920.057078,0.00735269,0.651246,0.923967,0.739067
15970.0,51952.581164,0.00735062,0.658805,0.884371,0.631271
15980.0,51985.104872,0.00734906,0.902084,0.871844,0.225086
15990.0,52017.631869,0.00734751,0.886044,0.855628,0.259371
16000.0,52050.658621,0.00734543,0.895894,0.861793,0.23928
16010.0,52083.186635,0.00734388,0.904679,0.868579,0.221616
16020.0,52115.714677,0.00734232,0.90322,0.882374,0.223268
16030.0,52148.241642,0.00734025,0.90068,0.914469,0.227523
16040.0,52180.769891,0.00733869,0.906314,0.909256,0.215358
16050.0,52213.301211,0.00733713,0.902531,0.912445,0.22515
16060.0,52245.826968,0.00733506,0.898406,0.910234,0.233267
16070.0,52278.363027,0.0073335,0.891772,0.921766,0.246826
16080.0,52310.891055,0.00733195,0.904796,0.901059,0.221778
16090.0,52343.417385,0.00732987,0.898838,0.911256,0.230331
16100.0,52375.950561,0.00732832,0.902155,0.92741,0.224646
16110.0,52408.475273,0.00732676,0.906186,0.920572,0.215395
16120.0,52441.004475,0.00732468,0.898081,0.919573,0.234469
16130.0,52473.52762,0.00732313,0.904123,0.933459,0.220014
16140.0,52506.054822,0.00732157,0.888091,0.914138,0.259268
16150.0,52538.587222,0.0073195,0.90712,0.908451,0.214087
16160.0,52571.115408,0.00731794,0.895531,0.930096,0.239819
16170.0,52603.645468,0.00731638,0.902266,0.887955,0.225431
16180.0,52636.16846,0.00731431,0.900198,0.911846,0.228537
16190.0,52668.701195,0.00731275,0.893272,0.926099,0.244542
16200.0,52701.229816,0.00731119,0.899563,0.888939,0.231713
16210.0,52733.752653,0.00730912,0.885974,0.902347,0.261046
16220.0,52766.279477,0.00730756,0.895833,0.899622,0.236784
16230.0,52798.805392,0.007306,0.907298,0.894234,0.212962
16240.0,52831.33077,0.00730392,0.899613,0.908392,0.228615
16250.0,52863.860858,0.00730237,0.895145,0.891529,0.239091
16260.0,52896.38788,0.00730081,0.902866,0.915043,0.223872
16270.0,52928.91397,0.00729873,0.90281,0.904024,0.226302
16280.0,52961.439135,0.00729717,0.894952,0.917422,0.241256
16290.0,52993.964605,0.00729562,0.899654,0.921078,0.229703
16300.0,53026.494076,0.00729354,0.899955,0.912263,0.229155
16310.0,53059.02115,0.00729198,0.909942,0.902493,0.205565
16320.0,53091.553967,0.00729042,0.894817,0.901788,0.240936
16330.0,53124.083645,0.00728834,0.899828,0.915886,0.22878
16340.0,53156.617068,0.00728678,0.898192,0.909668,0.232666
16350.0,53189.147471,0.00728523,0.899603,0.884898,0.229067
16360.0,53221.678509,0.00728315,0.900415,0.916957,0.230544
16370.0,53254.209332,0.00728159,0.901871,0.916997,0.224164
16380.0,53286.739504,0.00728003,0.895894,0.926955,0.237832
16390.0,53319.2687,0.00727795,0.905046,0.923085,0.217313
16400.0,53351.796162,0.00727639,0.899226,0.940431,0.232049
16410.0,53384.32293,0.00727483,0.900666,0.900065,0.227274
16420.0,53416.851632,0.00727275,0.887288,0.919235,0.257883
16430.0,53449.375518,0.00727119,0.902114,0.912712,0.223422
16440.0,53481.900592,0.00726963,0.899877,0.930971,0.227985
16450.0,53514.420831,0.00726756,0.894014,0.946316,0.2413
16460.0,53546.94484,0.007266,0.903282,0.904843,0.222379
16470.0,53579.470907,0.00726444,0.881016,0.929284,0.270653
16480.0,53611.996915,0.00726236,0.897481,0.919439,0.232543
16490.0,53644.530182,0.0072608,0.903095,0.930717,0.222098
16500.0,53677.060873,0.00725924,0.885475,0.885002,0.263154
16510.0,53709.589137,0.00725716,0.884699,0.898675,0.265227
16520.0,53742.11853,0.0072556,0.896949,0.920445,0.235194
16530.0,53774.644652,0.00725404,0.899437,0.929975,0.231952
16540.0,53807.170568,0.00725196,0.90239,0.922019,0.224101
16550.0,53839.695359,0.00725039,0.901092,0.914829,0.225898
16560.0,53872.224901,0.00724883,0.89921,0.904457,0.229472
16570.0,53904.761505,0.00724675,0.903196,0.901071,0.222464
16580.0,53937.292014,0.00724519,0.904983,0.895996,0.21782
16590.0,53969.817536,0.00724363,0.897197,0.921809,0.237677
16600.0,54002.340524,0.00724155,0.908436,0.906323,0.209938
16610.0,54034.867878,0.00723999,0.896446,0.924422,0.237178
16620.0,54067.39388,0.00723843,0.894232,0.91116,0.240741
16630.0,54099.919974,0.00723635,0.895001,0.907248,0.239723
16640.0,54132.44479,0.00723479,0.903509,0.923064,0.221904
16650.0,54164.97188,0.00723322,0.897626,0.934735,0.234152
16660.0,54197.498795,0.00723114,0.902559,0.91421,0.224632
16670.0,54230.025142,0.00722958,0.903271,0.914199,0.220117
16680.0,54262.552155,0.00722802,0.905384,0.901611,0.219692
16690.0,54295.076265,0.00722594,0.90095,0.884072,0.225893
16700.0,54327.598997,0.00722437,0.895869,0.90625,0.236898
16710.0,54360.130271,0.00722281,0.895139,0.921485,0.237612
16720.0,54392.65512,0.00722073,0.901116,0.895572,0.225744
16730.0,54425.183986,0.00721917,0.904851,0.914178,0.21737
16740.0,54457.711556,0.0072176,0.902996,0.901005,0.223948
16750.0,54490.238732,0.00721552,0.90803,0.925306,0.210493
16760.0,54522.773009,0.00721396,0.89931,0.882858,0.231679
16770.0,54555.311705,0.0072124,0.896098,0.912562,0.238528
16780.0,54587.852631,0.00721031,0.906623,0.919142,0.21535
16790.0,54620.39333,0.00720875,0.908961,0.898545,0.208845
16800.0,54652.932891,0.00720719,0.910743,0.893093,0.206642
16810.0,54685.472322,0.0072051,0.90232,0.901939,0.224217
16820.0,54718.010303,0.00720354,0.907797,0.888755,0.21061
16830.0,54750.551574,0.00720198,0.899769,0.902061,0.230873
16840.0,54783.093359,0.00719989,0.902121,0.917624,0.224626
16850.0,54815.62921,0.00719833,0.907513,0.909894,0.214533
16860.0,54848.169774,0.00719677,0.896913,0.929848,0.23615
16870.0,54880.714846,0.00719468,0.907544,0.877239,0.214818
16880.0,54913.252036,0.00719312,0.906571,0.932144,0.214098
16890.0,54945.791708,0.00719156,0.903368,0.91414,0.222382
16900.0,54978.326306,0.00718947,0.903831,0.892302,0.220393
16910.0,55010.858401,0.00718791,0.896305,0.884852,0.238651
16920.0,55043.398157,0.00718634,0.907834,0.896669,0.211526
16930.0,55075.931144,0.00718426,0.903119,0.923245,0.221164
16940.0,55108.492445,0.00718269,0.903772,0.890212,0.21994
16950.0,55141.033399,0.00718113,0.90224,0.910595,0.225065
16960.0,55173.57382,0.00717904,0.893932,0.8897,0.241516
16970.0,55206.117316,0.00717748,0.904524,0.912452,0.218754
16980.0,55238.653671,0.00717591,0.900978,0.907054,0.225834
16990.0,55271.198341,0.00717383,0.894535,0.881949,0.24375
17000.0,55303.734182,0.00717226,0.897913,0.903672,0.233911
17010.0,55336.275461,0.0071707,0.900183,0.907624,0.228965
17020.0,55368.825921,0.00716861,0.897354,0.931069,0.234411
17030.0,55401.366379,0.00716705,0.870731,0.896728,0.292799
17040.0,55433.914837,0.00716548,0.897895,0.922106,0.232246
17050.0,55466.464266,0.00716339,0.895167,0.930222,0.23968
17060.0,55499.012722,0.00716183,0.899008,0.919128,0.230432
17070.0,55531.553654,0.00716026,0.897488,0.908962,0.23344
17080.0,55564.094271,0.00715818,0.900382,0.908075,0.228408
17090.0,55596.634494,0.00715661,0.898819,0.924842,0.232041
17100.0,55629.161705,0.00715505,0.893208,0.938327,0.245227
17110.0,55661.688854,0.00715296,0.892484,0.918806,0.246455
17120.0,55694.223374,0.00715139,0.900451,0.938896,0.231028
17130.0,55726.758471,0.00714983,0.896846,0.907569,0.238012
17140.0,55759.289318,0.00714774,0.903002,0.934718,0.222216
17150.0,55791.822683,0.00714617,0.899389,0.920513,0.230036
17160.0,55824.363044,0.00714461,0.904378,0.892199,0.219186
17170.0,55856.906784,0.00714252,0.900599,0.920007,0.22781
17180.0,55889.444864,0.00714095,0.910964,0.904989,0.206191
17190.0,55921.98789,0.00713938,0.894141,0.897561,0.243147
17200.0,55954.520728,0.00713729,0.904398,0.913032,0.219577
17210.0,55987.04992,0.00713573,0.904901,0.923111,0.218724
17220.0,56019.588114,0.00713416,0.894795,0.88691,0.240746
17230.0,56052.128453,0.00713207,0.898331,0.88633,0.232992
17240.0,56084.663252,0.00713051,0.895391,0.932882,0.239623
17250.0,56117.202372,0.00712894,0.903956,0.916277,0.221329
17260.0,56149.734677,0.00712685,0.899758,0.876135,0.230581
17270.0,56182.263003,0.00712528,0.895893,0.911097,0.237256
17280.0,56214.795213,0.00712371,0.907679,0.917885,0.213611
17290.0,56247.327457,0.00712162,0.901016,0.91451,0.225037
17300.0,56279.872924,0.00712006,0.904413,0.930403,0.220149
17310.0,56312.422754,0.00711849,0.896046,0.928548,0.238594
17320.0,56344.968346,0.0071164,0.905533,0.91271,0.215745
17330.0,56377.518577,0.00711483,0.886603,0.888842,0.259553
17340.0,56410.077202,0.00711326,0.888957,0.900647,0.253475
17350.0,56442.638667,0.00711117,0.909834,0.893137,0.208121
17360.0,56475.199481,0.0071096,0.899086,0.909865,0.231342
17370.0,56507.755744,0.00710804,0.899228,0.932245,0.231243
17380.0,56540.319354,0.00710594,0.887727,0.913491,0.255798
17390.0,56572.889589,0.00710438,0.895243,0.908058,0.235397
17400.0,56605.455505,0.00710281,0.90459,0.933268,0.218495
17410.0,56638.020388,0.00710072,0.898039,0.904307,0.234137
17420.0,56670.57907,0.00709915,0.893082,0.943135,0.242104
17430.0,56703.136483,0.00709758,0.906635,0.917726,0.214157
17440.0,56735.699407,0.00709549,0.903298,0.912053,0.221255
17450.0,56768.268393,0.00709392,0.888446,0.907464,0.252911
17460.0,56800.832792,0.00709235,0.890727,0.915258,0.251096
17470.0,56833.395678,0.00709026,0.904183,0.924271,0.219306
17480.0,56865.957693,0.00708869,0.906998,0.89861,0.214668
17490.0,56898.523865,0.00708712,0.904454,0.932485,0.219609
17500.0,56931.090009,0.00708502,0.902462,0.923243,0.225138
17510.0,56963.649032,0.00708346,0.902425,0.905051,0.224438
17520.0,56996.211746,0.00708189,0.908296,0.921849,0.210101
17530.0,57028.776166,0.00707979,0.897799,0.923846,0.232915
17540.0,57061.332889,0.00707822,0.899395,0.901261,0.228885
17550.0,57093.885658,0.00707665,0.907302,0.919505,0.214971
17560.0,57126.417822,0.00707456,0.902153,0.916114,0.223424
17570.0,57158.957418,0.00707299,0.89587,0.930989,0.236652
17580.0,57191.49445,0.00707142,0.905096,0.906417,0.217177
17590.0,57224.027182,0.00706932,0.901324,0.913084,0.225758
17600.0,57256.564042,0.00706775,0.907613,0.925749,0.212813
17610.0,57289.09629,0.00706618,0.908828,0.921082,0.209789
17620.0,57321.627617,0.00706409,0.897123,0.915974,0.233528
17630.0,57354.158143,0.00706252,0.901401,0.899584,0.224294
17640.0,57386.683932,0.00706095,0.900538,0.928008,0.229157
17650.0,57419.213896,0.00705885,0.892895,0.877239,0.245307
17660.0,57451.751593,0.00705728,0.899785,0.901207,0.229201
17670.0,57484.285689,0.00705571,0.899855,0.915132,0.229046
17680.0,57516.824319,0.00705362,0.895265,0.92553,0.239986
17690.0,57549.356115,0.00705204,0.904634,0.922177,0.219401
17700.0,57581.893677,0.00705047,0.875333,0.877662,0.280672
17710.0,57614.438285,0.00704838,0.891375,0.927508,0.248914
17720.0,57646.96176,0.00704681,0.910282,0.919948,0.205296
17730.0,57679.491866,0.00704523,0.900347,0.929449,0.228051
17740.0,57712.018919,0.00704314,0.901323,0.920135,0.224981
17750.0,57744.543836,0.00704157,0.907981,0.929821,0.210369
17760.0,57777.076327,0.00703999,0.898073,0.929258,0.231998
17770.0,57809.616676,0.0070379,0.887995,0.921872,0.251716
17780.0,57842.15545,0.00703633,0.89814,0.919024,0.231237
17790.0,57874.694677,0.00703475,0.901743,0.93036,0.224067
17800.0,57907.22908,0.00703266,0.881357,0.94178,0.26388
17810.0,57939.763996,0.00703108,0.904289,0.908508,0.216989
17820.0,57972.298392,0.00702951,0.896504,0.916028,0.235388
17830.0,58004.839533,0.00702742,0.903666,0.934602,0.220103
17840.0,58037.381102,0.00702584,0.889482,0.891388,0.251249
17850.0,58069.918905,0.00702427,0.898672,0.905239,0.230279
17860.0,58102.455069,0.00702217,0.890967,0.908895,0.247657
17870.0,58134.997569,0.0070206,0.894424,0.923361,0.241946
17880.0,58167.539109,0.00701903,0.896537,0.932452,0.234862
17890.0,58200.072793,0.00701693,0.897181,0.878817,0.233121
17900.0,58232.604861,0.00701536,0.884098,0.892476,0.264238
17910.0,58265.131598,0.00701378,0.901392,0.881146,0.225896
17920.0,58297.666398,0.00701168,0.892454,0.86855,0.243807
17930.0,58330.201039,0.00701011,0.901631,0.894541,0.225323
17940.0,58362.733629,0.00700854,0.907365,0.892147,0.212605
17950.0,58395.270281,0.00700644,0.907446,0.900412,0.213021
17960.0,58427.8065,0.00700486,0.901206,0.907994,0.227633
17970.0,58460.338335,0.00700329,0.879285,0.894356,0.274446
17980.0,58492.864094,0.00700119,0.905143,0.87975,0.217903
17990.0,58525.401418,0.00699962,0.905206,0.891944,0.218329
18000.0,58558.426866,0.00699804,0.903921,0.903105,0.218506
18010.0,58590.956815,0.00699594,0.898078,0.904357,0.230663
18020.0,58623.512701,0.00699437,0.908744,0.912092,0.211399
18030.0,58656.061551,0.00699279,0.913656,0.918471,0.199093
18040.0,58688.613495,0.00699069,0.901582,0.925603,0.225754
18050.0,58721.165738,0.00698912,0.906958,0.894111,0.212973
18060.0,58753.715657,0.00698754,0.9001,0.893474,0.228764
18070.0,58786.264667,0.00698544,0.903771,0.901571,0.22281
18080.0,58818.820297,0.00698387,0.905079,0.89733,0.218514
18090.0,58851.370739,0.00698229,0.899875,0.871477,0.228534
18100.0,58883.921479,0.00698019,0.89872,0.923933,0.231586
18110.0,58916.480569,0.00697862,0.899309,0.909719,0.233855
18120.0,58949.028561,0.00697704,0.89441,0.880086,0.241237
18130.0,58981.590426,0.00697494,0.905282,0.919477,0.218444
18140.0,59014.143814,0.00697337,0.905611,0.90053,0.216821
18150.0,59046.702958,0.00697179,0.89064,0.929725,0.249446
18160.0,59079.255521,0.00696969,0.89982,0.908119,0.229153
18170.0,59111.801804,0.00696811,0.90258,0.906174,0.224058
18180.0,59144.363565,0.00696654,0.896023,0.8952,0.236142
18190.0,59176.921692,0.00696443,0.888748,0.923412,0.253046
18200.0,59209.473443,0.00696286,0.905163,0.894046,0.21642
18210.0,59242.027818,0.00696128,0.897286,0.910682,0.234795
18220.0,59274.584829,0.00695918,0.903851,0.921467,0.220309
18230.0,59307.143314,0.0069576,0.89921,0.938061,0.232024
18240.0,59339.660932,0.00695603,0.909558,0.909642,0.207161
18250.0,59372.183695,0.00695392,0.898208,0.930799,0.234516
18260.0,59404.713531,0.00695235,0.902148,0.908905,0.225036
18270.0,59437.241456,0.00695077,0.90406,0.925187,0.220146
18280.0,59469.766511,0.00694867,0.903554,0.919143,0.219999
18290.0,59502.297742,0.00694709,0.907696,0.904653,0.211475
18300.0,59534.825328,0.00694551,0.90334,0.933539,0.219528
18310.0,59567.35321,0.00694341,0.902691,0.909756,0.222751
18320.0,59599.883214,0.00694183,0.90029,0.936752,0.229405
18330.0,59632.410398,0.00694025,0.906385,0.924519,0.215859
18340.0,59664.933408,0.00693815,0.901424,0.924975,0.228018
18350.0,59697.46528,0.00693657,0.911553,0.922642,0.202832
18360.0,59729.997783,0.00693499,0.901923,0.900415,0.226559
18370.0,59762.528964,0.00693289,0.894888,0.917928,0.243071
18380.0,59795.062976,0.00693131,0.907846,0.912524,0.21199
18390.0,59827.592613,0.00692973,0.901312,0.920981,0.226021
18400.0,59860.119168,0.00692763,0.901729,0.929808,0.224156
18410.0,59892.649596,0.00692605,0.897803,0.917262,0.231394
18420.0,59925.1753,0.00692447,0.886709,0.919026,0.254325
18430.0,59957.703608,0.00692237,0.900395,0.918641,0.2257
18440.0,59990.229633,0.00692079,0.902359,0.919539,0.223028
18450.0,60022.772211,0.00691921,0.906597,0.910914,0.213717
18460.0,60055.294646,0.00691711,0.903602,0.929506,0.22
18470.0,60087.818689,0.00691553,0.90531,0.920706,0.21787
18480.0,60120.351041,0.00691395,0.909771,0.929032,0.207047
18490.0,60152.887623,0.00691184,0.892914,0.938623,0.24315
18500.0,60185.41652,0.00691026,0.893759,0.931565,0.238804
18510.0,60217.935779,0.00690868,0.902626,0.936217,0.22189
18520.0,60250.460737,0.00690658,0.902641,0.921942,0.222325
18530.0,60282.981043,0.006905,0.898687,0.935457,0.231781
18540.0,60315.508165,0.00690342,0.900352,0.890239,0.227088
18550.0,60348.029635,0.00690131,0.90502,0.905741,0.219216
18560.0,60380.563995,0.00689973,0.863049,0.88138,0.306997
18570.0,60413.093444,0.00689815,0.895538,0.927969,0.235549
18580.0,60445.623569,0.00689604,0.904301,0.918346,0.21938
18590.0,60478.151554,0.00689446,0.89715,0.93479,0.238025
18600.0,60510.682423,0.00689288,0.903845,0.906902,0.219888
18610.0,60543.211177,0.00689078,0.893204,0.942127,0.244412
18620.0,60575.742782,0.0068892,0.901592,0.904583,0.224343
18630.0,60608.266552,0.00688761,0.900588,0.860481,0.230592
18640.0,60640.787957,0.00688551,0.896009,0.921323,0.240388
18650.0,60673.316141,0.00688393,0.901353,0.900831,0.225304
18660.0,60705.854819,0.00688235,0.90302,0.916533,0.222433
18670.0,60738.377238,0.00688024,0.897797,0.91185,0.234577
18680.0,60770.904194,0.00687866,0.90262,0.926043,0.223744
18690.0,60803.428874,0.00687707,0.905254,0.924911,0.216648
18700.0,60835.956697,0.00687497,0.905694,0.934799,0.215519
18710.0,60868.490425,0.00687338,0.898618,0.93105,0.231228
18720.0,60901.022524,0.0068718,0.902269,0.893576,0.222203
18730.0,60933.559888,0.00686969,0.90579,0.919949,0.216275
18740.0,60966.090531,0.00686811,0.900506,0.934298,0.225824
18750.0,60998.623017,0.00686653,0.890561,0.915798,0.246558
18760.0,61031.151417,0.00686442,0.892932,0.934613,0.244191
18770.0,61063.679352,0.00686284,0.895644,0.940568,0.236114
18780.0,61096.214483,0.00686126,0.892277,0.939489,0.243029
18790.0,61128.751019,0.00685915,0.905677,0.945114,0.217117
18800.0,61161.281516,0.00685757,0.903934,0.9273,0.219213
18810.0,61193.805547,0.00685598,0.896755,0.904427,0.236258
18820.0,61226.343461,0.00685387,0.905741,0.899549,0.217294
18830.0,61258.873495,0.00685229,0.900376,0.918205,0.227367
18840.0,61291.401591,0.00685071,0.901253,0.923885,0.225008
18850.0,61323.94173,0.0068486,0.896468,0.920441,0.236655
18860.0,61356.471729,0.00684701,0.905934,0.918997,0.216388
18870.0,61389.000725,0.00684543,0.904036,0.90892,0.218279
18880.0,61421.526652,0.00684332,0.901779,0.914683,0.222955
18890.0,61454.054392,0.00684174,0.899025,0.925425,0.228671
18900.0,61486.589189,0.00684015,0.908431,0.903484,0.21163
18910.0,61519.11433,0.00683804,0.889577,0.898014,0.251235
18920.0,61551.637588,0.00683646,0.901986,0.904887,0.223651
18930.0,61584.166712,0.00683487,0.906158,0.906993,0.215699
18940.0,61616.703841,0.00683276,0.902946,0.920884,0.220633
18950.0,61649.234502,0.00683118,0.900686,0.895666,0.229331
18960.0,61681.76622,0.00682959,0.898236,0.915711,0.23322
18970.0,61714.295063,0.00682748,0.911511,0.932079,0.201495
18980.0,61746.818763,0.0068259,0.906324,0.920691,0.212796
18990.0,61779.346419,0.00682431,0.876544,0.884751,0.277242
19000.0,61811.87982,0.0068222,0.904111,0.940082,0.217987
19010.0,61844.400324,0.00682062,0.9079,0.91807,0.208364
19020.0,61876.927083,0.00681903,0.892762,0.921372,0.241635
19030.0,61909.465531,0.00681692,0.899375,0.930444,0.229517
19040.0,61942.003621,0.00681533,0.909246,0.929191,0.209383
19050.0,61974.534795,0.00681375,0.903089,0.934665,0.218044
19060.0,62007.065524,0.00681164,0.900802,0.914818,0.227144
19070.0,62039.60046,0.00681005,0.905437,0.90148,0.214822
19080.0,62072.132772,0.00680847,0.900751,0.924069,0.22464
19090.0,62104.668056,0.00680635,0.899217,0.907804,0.227004
19100.0,62137.201254,0.00680477,0.90179,0.919833,0.224426
19110.0,62169.741024,0.00680318,0.902822,0.934762,0.221439
19120.0,62202.279612,0.00680107,0.905762,0.882456,0.214864
19130.0,62234.816044,0.00679948,0.906503,0.891836,0.216329
19140.0,62267.337987,0.0067979,0.900462,0.932418,0.228903
19150.0,62299.865298,0.00679578,0.908173,0.928305,0.208622
19160.0,62332.399909,0.0067942,0.90262,0.936522,0.223225
19170.0,62364.934235,0.00679261,0.900592,0.903423,0.225533
19180.0,62397.467505,0.00679049,0.913316,0.918471,0.200281
19190.0,62429.999465,0.00678891,0.895996,0.938187,0.238051
19200.0,62462.539725,0.00678732,0.900947,0.91751,0.226836
19210.0,62495.069072,0.00678521,0.900934,0.925757,0.228304
19220.0,62527.602875,0.00678362,0.905831,0.928499,0.218238
19230.0,62560.144086,0.00678203,0.906793,0.934869,0.214017
19240.0,62592.672018,0.00677992,0.896845,0.929873,0.237126
19250.0,62625.202577,0.00677833,0.902616,0.91875,0.222932
19260.0,62657.733099,0.00677674,0.904565,0.934337,0.221563
19270.0,62690.258644,0.00677463,0.905215,0.905815,0.215935
19280.0,62722.784431,0.00677304,0.901615,0.92938,0.227095
19290.0,62755.316169,0.00677145,0.90169,0.86653,0.225296
19300.0,62787.849743,0.00676933,0.902974,0.925961,0.2212
19310.0,62820.381684,0.00676775,0.903593,0.900576,0.221284
19320.0,62852.913489,0.00676616,0.905059,0.906536,0.217737
19330.0,62885.441116,0.00676404,0.905618,0.919826,0.215856
19340.0,62917.970797,0.00676245,0.899635,0.895776,0.228034
19350.0,62950.49931,0.00676087,0.891112,0.935087,0.247608
19360.0,62983.02615,0.00675875,0.906985,0.909436,0.215499
19370.0,63015.559957,0.00675716,0.88597,0.858546,0.266287
19380.0,63048.095948,0.00675557,0.892177,0.935401,0.244764
19390.0,63080.628961,0.00675345,0.903352,0.917512,0.219223
19400.0,63113.155781,0.00675187,0.896419,0.912115,0.237209
19410.0,63145.67809,0.00675028,0.90903,0.920056,0.208286
19420.0,63178.208252,0.00674816,0.908616,0.916435,0.209346
19430.0,63210.733779,0.00674657,0.907909,0.913311,0.209993
19440.0,63243.260239,0.00674498,0.902025,0.906918,0.223236
19450.0,63275.781982,0.00674286,0.901274,0.914301,0.224101
19460.0,63308.307544,0.00674127,0.89489,0.918863,0.238304
19470.0,63340.837451,0.00673968,0.898944,0.915783,0.231743
19480.0,63373.367705,0.00673757,0.910715,0.908291,0.207881
19490.0,63405.886999,0.00673598,0.899724,0.936531,0.228475
19500.0,63438.409153,0.00673439,0.895742,0.87366,0.240006
19510.0,63470.931387,0.00673227,0.895977,0.94086,0.239467
19520.0,63503.45918,0.00673068,0.903391,0.921841,0.221131
19530.0,63535.988161,0.00672909,0.903803,0.904483,0.223268
19540.0,63568.518383,0.00672697,0.89668,0.945769,0.235377
19550.0,63601.043731,0.00672538,0.898152,0.920495,0.231753
19560.0,63633.569492,0.00672379,0.902161,0.91162,0.226294
19570.0,63666.092065,0.00672167,0.908111,0.90929,0.20975
19580.0,63698.616017,0.00672008,0.888889,0.924239,0.254592
19590.0,63731.144009,0.00671849,0.904974,0.877582,0.218322
19600.0,63763.663943,0.00671636,0.891679,0.911344,0.249545
19610.0,63796.19406,0.00671477,0.905893,0.910171,0.215936
19620.0,63828.727626,0.00671318,0.90094,0.921422,0.226306
19630.0,63861.261712,0.00671106,0.899842,0.925501,0.229003
19640.0,63893.78906,0.00670947,0.900398,0.921359,0.227394
19650.0,63926.319083,0.00670788,0.908749,0.923276,0.208807
19660.0,63958.839478,0.00670576,0.907167,0.897916,0.213604
19670.0,63991.364741,0.00670417,0.893604,0.937836,0.241955
19680.0,64023.889523,0.00670258,0.907008,0.931951,0.212553
19690.0,64056.418086,0.00670045,0.903301,0.868195,0.223878
19700.0,64088.943273,0.00669886,0.907935,0.912912,0.209976
19710.0,64121.470498,0.00669727,0.899463,0.930318,0.227988
19720.0,64153.99577,0.00669515,0.906436,0.925756,0.212678
19730.0,64186.521001,0.00669356,0.902475,0.930999,0.223048
19740.0,64219.04574,0.00669196,0.910504,0.920386,0.205813
19750.0,64251.5761,0.00668984,0.899457,0.931456,0.229876
19760.0,64284.100853,0.00668825,0.902084,0.904654,0.223872
19770.0,64316.62685,0.00668666,0.902376,0.934162,0.223058
19780.0,64349.160102,0.00668453,0.900894,0.925024,0.224833
19790.0,64381.693697,0.00668294,0.897556,0.904453,0.233071
19800.0,64414.218652,0.00668135,0.904815,0.909634,0.217667
19810.0,64446.745808,0.00667922,0.902465,0.918878,0.223478
19820.0,64479.270759,0.00667763,0.911364,0.920377,0.205127
19830.0,64511.799258,0.00667604,0.899338,0.914052,0.230051
19840.0,64544.326862,0.00667391,0.899005,0.914831,0.232088
19850.0,64576.857752,0.00667232,0.90269,0.924271,0.222172
19860.0,64609.392578,0.00667073,0.892438,0.896279,0.244062
19870.0,64641.916186,0.0066686,0.90032,0.919143,0.228733
19880.0,64674.446429,0.00666701,0.902406,0.922697,0.22149
19890.0,64706.970984,0.00666542,0.901572,0.932797,0.224693
19900.0,64739.496974,0.00666329,0.901471,0.921101,0.22455
19910.0,64772.016743,0.0066617,0.901704,0.940984,0.223117
19920.0,64804.539473,0.0066601,0.90995,0.92494,0.206849
19930.0,64837.066267,0.00665798,0.905046,0.917951,0.218651
19940.0,64869.592634,0.00665638,0.904617,0.928561,0.216977
19950.0,64902.112606,0.00665479,0.895888,0.8435,0.244317
19960.0,64934.634908,0.00665266,0.911323,0.9058,0.202828
19970.0,64967.153353,0.00665107,0.905491,0.918069,0.216323
19980.0,64999.674993,0.00664947,0.901247,0.902917,0.225641
19990.0,65032.198486,0.00664735,0.90455,0.899763,0.217452
20000.0,65065.224771,0.00664575,0.903465,0.891161,0.219621
20010.0,65097.746746,0.00664416,0.909553,0.908188,0.210522
20020.0,65130.265355,0.00664203,0.900604,0.916314,0.22699
20030.0,65162.783896,0.00664044,0.905986,0.909638,0.21576
20040.0,65195.302848,0.00663884,0.898812,0.911446,0.232943
20050.0,65227.828251,0.00663671,0.900199,0.906476,0.229936
20060.0,65260.353619,0.00663512,0.908289,0.924746,0.210692
20070.0,65292.873663,0.00663352,0.908893,0.913653,0.208994
20080.0,65325.392734,0.00663139,0.910881,0.902081,0.205294
20090.0,65357.912094,0.0066298,0.905425,0.90708,0.216437
20100.0,65390.432033,0.0066282,0.901084,0.900083,0.224146
20110.0,65422.952248,0.00662608,0.889586,0.865767,0.249506
20120.0,65455.478269,0.00662448,0.90244,0.912018,0.225175
20130.0,65488.00008,0.00662288,0.908015,0.940103,0.211684
20140.0,65520.522946,0.00662075,0.913556,0.908836,0.201863
20150.0,65553.042696,0.00661916,0.896592,0.917573,0.233611
20160.0,65585.570888,0.00661756,0.89997,0.917022,0.22689
20170.0,65618.091998,0.00661543,0.899068,0.936921,0.230726
20180.0,65650.614722,0.00661384,0.899985,0.898898,0.228359
20190.0,65683.132671,0.00661224,0.905648,0.916797,0.219031
20200.0,65715.654547,0.00661011,0.907049,0.92769,0.212915
20210.0,65748.181095,0.00660851,0.902163,0.915896,0.22597
20220.0,65780.704976,0.00660692,0.893529,0.903981,0.241385
20230.0,65813.225954,0.00660479,0.909241,0.929326,0.210148
20240.0,65845.751228,0.00660319,0.907515,0.936762,0.212129
20250.0,65878.273857,0.00660159,0.908766,0.911931,0.209204
20260.0,65910.796189,0.00659946,0.912317,0.924005,0.201659
20270.0,65943.317466,0.00659786,0.887692,0.898221,0.255939
20280.0,65975.83705,0.00659627,0.904822,0.911437,0.216736
20290.0,66008.359358,0.00659413,0.909032,0.922232,0.210293
20300.0,66040.885303,0.00659254,0.906593,0.899022,0.213123
20310.0,66073.410797,0.00659094,0.898729,0.930225,0.231127
20320.0,66105.935254,0.00658881,0.906506,0.909902,0.212408
20330.0,66138.456758,0.00658721,0.907504,0.906306,0.211818
20340.0,66170.976001,0.00658561,0.908449,0.91926,0.211452
20350.0,66203.501776,0.00658348,0.90224,0.915991,0.224805
20360.0,66236.02459,0.00658188,0.903558,0.923231,0.219518
20370.0,66268.557228,0.00658028,0.904219,0.930027,0.219209
20380.0,66301.082616,0.00657815,0.901637,0.921533,0.227283
20390.0,66333.611653,0.00657655,0.90131,0.92638,0.222937
20400.0,66366.137102,0.00657495,0.900276,0.932598,0.225386
20410.0,66398.661094,0.00657282,0.902939,0.921143,0.224777
20420.0,66431.188264,0.00657122,0.905426,0.9121,0.217701
20430.0,66463.721491,0.00656962,0.9115,0.920196,0.201626
20440.0,66496.245403,0.00656749,0.891449,0.945869,0.246707
20450.0,66528.767,0.00656589,0.902688,0.915529,0.222778
20460.0,66561.290323,0.00656429,0.908168,0.928603,0.213683
20470.0,66593.80574,0.00656216,0.902989,0.930935,0.221815
20480.0,66626.330605,0.00656056,0.89723,0.935605,0.235127
20490.0,66658.852024,0.00655896,0.904236,0.925381,0.22
20500.0,66691.373521,0.00655682,0.897961,0.944764,0.231476
20510.0,66723.893839,0.00655522,0.911002,0.916629,0.204333
20520.0,66756.408746,0.00655362,0.904034,0.925344,0.219651
20530.0,66788.930048,0.00655149,0.902557,0.911773,0.223409
20540.0,66821.456269,0.00654989,0.905104,0.937911,0.2189
20550.0,66853.983783,0.00654829,0.894468,0.93108,0.242033
20560.0,66886.51221,0.00654615,0.906154,0.921607,0.213914
20570.0,66919.038618,0.00654455,0.894279,0.937046,0.245152
20580.0,66951.566674,0.00654295,0.904924,0.900201,0.217551
20590.0,66984.091759,0.00654081,0.904212,0.913128,0.217699
20600.0,67016.615631,0.00653921,0.907896,0.923139,0.211573
20610.0,67049.136806,0.00653761,0.91259,0.898184,0.200086
20620.0,67081.664554,0.00653548,0.899326,0.898737,0.23326
20630.0,67114.191968,0.00653387,0.90908,0.908523,0.208223
20640.0,67146.723036,0.00653227,0.891101,0.788811,0.255518
20650.0,67179.247357,0.00653014,0.898787,0.869417,0.239608
20660.0,67211.775607,0.00652854,0.903232,0.901428,0.222604
20670.0,67244.300048,0.00652693,0.905613,0.861097,0.21858
20680.0,67276.827335,0.0065248,0.893503,0.819402,0.246449
20690.0,67309.351794,0.00652319,0.911533,0.904295,0.203839
20700.0,67341.883037,0.00652159,0.905905,0.901553,0.214266
20710.0,67374.414372,0.00651946,0.897745,0.918324,0.233396
20720.0,67406.938133,0.00651785,0.898095,0.916741,0.232415
20730.0,67439.458106,0.00651625,0.908337,0.92481,0.21197
20740.0,67471.968123,0.00651411,0.907029,0.916355,0.215183
20750.0,67504.482713,0.00651251,0.900351,0.929921,0.228965
20760.0,67537.003277,0.00651091,0.907358,0.912845,0.212675
20770.0,67569.526122,0.00650877,0.894184,0.918915,0.240753
20780.0,67602.050923,0.00650717,0.891776,0.929822,0.245762
20790.0,67634.575479,0.00650556,0.907561,0.917356,0.211626
20800.0,67667.095711,0.00650343,0.896777,0.924394,0.23728
20810.0,67699.618766,0.00650182,0.908789,0.896037,0.209127
20820.0,67732.139979,0.00650022,0.901033,0.945164,0.227479
20830.0,67764.66043,0.00649808,0.90385,0.915425,0.222082
20840.0,67797.180251,0.00649648,0.90616,0.916436,0.216203
20850.0,67829.701996,0.00649487,0.906392,0.932129,0.214745
20860.0,67862.22005,0.00649273,0.908966,0.913975,0.210129
20870.0,67894.749597,0.00649113,0.898798,0.934096,0.23235
20880.0,67927.275887,0.00648952,0.906251,0.914958,0.214725
20890.0,67959.805545,0.00648738,0.900174,0.945233,0.229836
20900.0,67992.331396,0.00648578,0.903274,0.899709,0.222609
20910.0,68024.857489,0.00648418,0.893225,0.953108,0.24486
20920.0,68057.375806,0.00648204,0.900369,0.934086,0.22795
20930.0,68089.892091,0.00648043,0.908762,0.918933,0.211279
20940.0,68122.414945,0.00647883,0.899225,0.92883,0.230839
20950.0,68154.930445,0.00647669,0.907226,0.922516,0.213926
20960.0,68187.447469,0.00647508,0.90904,0.925436,0.209561
20970.0,68219.967057,0.00647348,0.899344,0.927978,0.230509
20980.0,68252.485317,0.00647133,0.903402,0.919901,0.222363
20990.0,68285.0062,0.00646973,0.903842,0.897763,0.221455
21000.0,68317.529138,0.00646812,0.904431,0.919571,0.218598
21010.0,68350.05095,0.00646598,0.909496,0.922589,0.209771
21020.0,68382.571206,0.00646438,0.904303,0.934782,0.219814
21030.0,68415.087718,0.00646277,0.902726,0.931891,0.224924
21040.0,68447.609219,0.00646063,0.902814,0.920099,0.222762
21050.0,68480.141504,0.00645902,0.907437,0.937577,0.211214
21060.0,68512.667731,0.00645742,0.903897,0.911643,0.221317
21070.0,68545.185913,0.00645527,0.903608,0.952561,0.221988
21080.0,68577.7084,0.00645367,0.908306,0.912324,0.210225
21090.0,68610.228068,0.00645206,0.913317,0.934061,0.201015
21100.0,68642.757236,0.00644992,0.905829,0.925849,0.216119
21110.0,68675.283431,0.00644831,0.898612,0.908593,0.232083
21120.0,68707.819147,0.00644671,0.907889,0.928938,0.213605
21130.0,68740.352528,0.00644456,0.889843,0.939091,0.249465
21140.0,68772.882725,0.00644296,0.909199,0.933287,0.208754
21150.0,68805.414153,0.00644135,0.898233,0.936057,0.232826
21160.0,68837.947551,0.0064392,0.90213,0.941306,0.224245
21170.0,68870.475111,0.0064376,0.907842,0.919408,0.211488
21180.0,68903.006838,0.00643599,0.895573,0.932742,0.238412
21190.0,68935.540048,0.00643385,0.901338,0.904076,0.22522
21200.0,68968.074539,0.00643224,0.895423,0.951378,0.239161
21210.0,69000.603876,0.00643063,0.905458,0.919432,0.215633
21220.0,69033.135423,0.00642849,0.902247,0.907521,0.222528
21230.0,69065.663758,0.00642688,0.897834,0.931591,0.234274
21240.0,69098.191953,0.00642527,0.905682,0.931886,0.214033
21250.0,69130.721563,0.00642312,0.905611,0.926509,0.215715
21260.0,69163.256361,0.00642152,0.903279,0.905551,0.219427
21270.0,69195.779132,0.00641991,0.901385,0.93064,0.224554
21280.0,69228.308214,0.00641776,0.911939,0.913216,0.201887
21290.0,69260.828979,0.00641615,0.910214,0.931587,0.207578
21300.0,69293.367667,0.00641454,0.903118,0.914201,0.222195
21310.0,69325.891731,0.0064124,0.911305,0.917254,0.204658
21320.0,69358.410967,0.00641079,0.893481,0.88684,0.242542
21330.0,69390.941829,0.00640918,0.907558,0.928908,0.211617
21340.0,69423.468384,0.00640703,0.908875,0.946828,0.207937
21350.0,69455.999989,0.00640542,0.902912,0.911045,0.221803
21360.0,69488.530954,0.00640382,0.90338,0.934866,0.221301
21370.0,69521.061254,0.00640167,0.904573,0.925472,0.219284
21380.0,69553.589746,0.00640006,0.905193,0.922156,0.218537
21390.0,69586.127463,0.00639845,0.897683,0.92454,0.231764
21400.0,69618.655986,0.0063963,0.900547,0.92682,0.226116
21410.0,69651.1774,0.00639469,0.90778,0.907301,0.210144
21420.0,69683.695389,0.00639308,0.890707,0.909861,0.247074
21430.0,69716.218408,0.00639093,0.905986,0.917996,0.216296
21440.0,69748.736417,0.00638932,0.911771,0.899101,0.202311
21450.0,69781.259918,0.00638771,0.899016,0.951517,0.230361
21460.0,69813.786997,0.00638556,0.897043,0.916079,0.233649
21470.0,69846.311254,0.00638395,0.908443,0.915409,0.208815
21480.0,69878.83539,0.00638234,0.903934,0.926834,0.220809
21490.0,69911.356691,0.00638019,0.899502,0.912876,0.229399
21500.0,69943.88404,0.00637858,0.907055,0.916069,0.212507
21510.0,69976.409864,0.00637697,0.900587,0.933114,0.230141
21520.0,70008.931572,0.00637482,0.892272,0.935462,0.246726
21530.0,70041.458964,0.00637321,0.90625,0.940152,0.213505
21540.0,70073.979998,0.0063716,0.904017,0.937964,0.218172
21550.0,70106.505655,0.00636945,0.901135,0.932756,0.226017
21560.0,70139.03306,0.00636784,0.907469,0.923758,0.211814
21570.0,70171.558316,0.00636623,0.904169,0.90025,0.218731
21580.0,70204.089225,0.00636408,0.904085,0.933666,0.21908
21590.0,70236.617957,0.00636247,0.906824,0.930426,0.212454
21600.0,70269.143575,0.00636085,0.851501,0.903999,0.321304
21610.0,70301.675913,0.0063587,0.891441,0.947076,0.249902
21620.0,70334.203676,0.00635709,0.908916,0.921918,0.206969
21630.0,70366.734451,0.00635548,0.907277,0.919825,0.211961
21640.0,70399.262506,0.00635333,0.900768,0.927557,0.227724
21650.0,70431.797804,0.00635171,0.89441,0.911581,0.240476
21660.0,70464.328272,0.0063501,0.899811,0.910384,0.227819
21670.0,70496.862081,0.00634795,0.905107,0.926819,0.217308
21680.0,70529.391253,0.00634634,0.911308,0.927151,0.203559
21690.0,70561.917233,0.00634472,0.906745,0.916041,0.213725
21700.0,70594.448588,0.00634257,0.902783,0.924884,0.221443
21710.0,70626.982116,0.00634096,0.90549,0.931256,0.217442
21720.0,70659.517458,0.00633934,0.905572,0.885844,0.215355
21730.0,70692.05135,0.00633719,0.906632,0.927549,0.215317
21740.0,70724.586594,0.00633558,0.910728,0.92033,0.2059
21750.0,70757.126164,0.00633396,0.90615,0.928025,0.214061
21760.0,70789.664982,0.00633181,0.911087,0.921399,0.203546
21770.0,70822.197562,0.0063302,0.904018,0.938127,0.221117
21780.0,70854.73175,0.00632858,0.898808,0.924654,0.230637
21790.0,70887.266557,0.00632643,0.895516,0.886256,0.240365
21800.0,70919.801773,0.00632482,0.906731,0.946716,0.215393
21810.0,70952.335412,0.0063232,0.90632,0.919118,0.217015
21820.0,70984.872568,0.00632105,0.905022,0.928535,0.21878
21830.0,71017.410226,0.00631943,0.907629,0.931713,0.210593
21840.0,71049.949577,0.00631782,0.904323,0.931032,0.218933
21850.0,71082.478835,0.00631566,0.907633,0.927981,0.213925
21860.0,71115.011054,0.00631405,0.910502,0.937416,0.206347
21870.0,71147.547174,0.00631243,0.904821,0.923769,0.218578
21880.0,71180.075901,0.00631028,0.906042,0.932905,0.217286
21890.0,71212.603747,0.00630866,0.905021,0.908502,0.218102
21900.0,71245.129656,0.00630705,0.905593,0.927155,0.216069
21910.0,71277.65904,0.00630489,0.904935,0.928694,0.218821
21920.0,71310.192936,0.00630328,0.897356,0.941984,0.231848
21930.0,71342.731964,0.00630166,0.906552,0.925305,0.21525
21940.0,71375.260092,0.00629951,0.913703,0.913144,0.19889
21950.0,71407.79867,0.00629789,0.909094,0.893211,0.212559
21960.0,71440.331838,0.00629627,0.907831,0.900226,0.213567
21970.0,71472.869547,0.00629412,0.905241,0.89332,0.214653
21980.0,71505.407797,0.0062925,0.903984,0.909858,0.220726
21990.0,71537.950056,0.00629088,0.901817,0.927806,0.225571
22000.0,71570.975915,0.00628873,0.896291,0.907512,0.236267
22010.0,71603.50428,0.00628711,0.911373,0.925472,0.205164
22020.0,71636.032679,0.00628549,0.906451,0.920295,0.216473
22030.0,71668.559834,0.00628334,0.906597,0.920235,0.21412
22040.0,71701.088433,0.00628172,0.901917,0.936888,0.225036
22050.0,71733.62262,0.0062801,0.91419,0.922108,0.197039
22060.0,71766.162718,0.00627795,0.907042,0.930812,0.213524
22070.0,71798.704705,0.00627633,0.906948,0.908049,0.212871
22080.0,71831.244944,0.00627471,0.908312,0.939585,0.210758
22090.0,71863.784011,0.00627255,0.910419,0.915704,0.206055
22100.0,71896.322789,0.00627093,0.910963,0.907035,0.205438
22110.0,71928.861356,0.00626932,0.909662,0.920118,0.210307
22120.0,71961.399235,0.00626716,0.91483,0.912433,0.199006
22130.0,71993.941481,0.00626554,0.910476,0.917268,0.206921
22140.0,72026.482875,0.00626392,0.905277,0.919424,0.21746
22150.0,72059.022854,0.00626176,0.89911,0.920605,0.229886
22160.0,72091.567346,0.00626014,0.906244,0.91052,0.215265
22170.0,72124.108935,0.00625852,0.911488,0.924646,0.205259
22180.0,72156.643065,0.00625637,0.906189,0.925934,0.216095
22190.0,72189.169263,0.00625475,0.904312,0.924453,0.219002
22200.0,72221.691847,0.00625313,0.907521,0.928189,0.213106
22210.0,72254.215706,0.00625097,0.8896,0.913272,0.251635
22220.0,72286.739061,0.00624935,0.898564,0.935674,0.229505
22230.0,72319.26008,0.00624773,0.903809,0.917364,0.220092
22240.0,72351.791539,0.00624557,0.904039,0.938142,0.219885
22250.0,72384.320051,0.00624395,0.90086,0.931659,0.228275
22260.0,72416.866899,0.00624233,0.908717,0.929055,0.209776
22270.0,72449.400505,0.00624017,0.904997,0.935096,0.218949
22280.0,72481.935761,0.00623855,0.902991,0.93866,0.221249
22290.0,72514.472882,0.00623693,0.910681,0.920638,0.205994
22300.0,72547.010297,0.00623477,0.901416,0.934557,0.22408
22310.0,72579.543217,0.00623315,0.879538,0.92218,0.275229
22320.0,72612.074448,0.00623153,0.906121,0.912327,0.215432
22330.0,72644.599887,0.00622937,0.907266,0.918661,0.211931
22340.0,72677.125572,0.00622775,0.906112,0.941481,0.214769
22350.0,72709.652792,0.00622612,0.90469,0.931633,0.21711
22360.0,72742.190465,0.00622396,0.911055,0.911615,0.205136
22370.0,72774.723858,0.00622234,0.909654,0.91805,0.206979
22380.0,72807.260775,0.00622072,0.904155,0.915536,0.219427
22390.0,72839.796739,0.00621856,0.916347,0.936957,0.193319
22400.0,72872.329121,0.00621694,0.904676,0.947992,0.221029
22410.0,72904.855135,0.00621531,0.909192,0.918985,0.207098
22420.0,72937.384494,0.00621315,0.912907,0.936122,0.199803
22430.0,72969.90388,0.00621153,0.897229,0.947854,0.237533
22440.0,73002.437688,0.00620991,0.905656,0.913266,0.216409
22450.0,73034.9624,0.00620775,0.906666,0.926781,0.213737
22460.0,73067.48287,0.00620612,0.904799,0.913211,0.21815
22470.0,73100.014801,0.0062045,0.904791,0.93229,0.216677
22480.0,73132.540692,0.00620234,0.907223,0.933682,0.212929
22490.0,73165.06116,0.00620071,0.914015,0.919957,0.198798
22500.0,73197.589939,0.00619909,0.902659,0.937381,0.221985
22510.0,73230.117783,0.00619693,0.912726,0.922101,0.201158
22520.0,73262.642023,0.0061953,0.907163,0.923301,0.211853
22530.0,73295.177591,0.00619368,0.905505,0.923203,0.217303
22540.0,73327.705339,0.00619152,0.913144,0.931863,0.199985
22550.0,73360.237622,0.00618989,0.913793,0.924422,0.199889
22560.0,73392.772435,0.00618827,0.898523,0.929477,0.230131
22570.0,73425.305125,0.0061861,0.908374,0.913051,0.210769
22580.0,73457.842868,0.00618448,0.912341,0.931024,0.20164
22590.0,73490.370299,0.00618286,0.902853,0.901132,0.222189
22600.0,73522.896824,0.00618069,0.91027,0.918724,0.204393
22610.0,73555.428756,0.00617907,0.909901,0.928362,0.206957
22620.0,73587.962404,0.00617744,0.904969,0.932036,0.217493
22630.0,73620.489629,0.00617528,0.893442,0.924617,0.244619
22640.0,73653.017892,0.00617365,0.901801,0.942398,0.223177
22650.0,73685.553276,0.00617203,0.89787,0.897921,0.232403
22660.0,73718.080789,0.00616986,0.910489,0.915804,0.206699
22670.0,73750.603802,0.00616824,0.90681,0.928049,0.215077
22680.0,73783.125051,0.00616661,0.904895,0.941245,0.218018
22690.0,73815.650653,0.00616445,0.9108,0.929982,0.204712
22700.0,73848.173118,0.00616282,0.910076,0.948266,0.207896
22710.0,73880.70229,0.0061612,0.905493,0.94175,0.216439
22720.0,73913.226365,0.00615903,0.903339,0.940781,0.219554
22730.0,73945.752687,0.0061574,0.905125,0.942085,0.217845
22740.0,73978.281697,0.00615578,0.899742,0.942016,0.228361
22750.0,74010.812891,0.00615361,0.911307,0.922161,0.205538
22760.0,74043.339917,0.00615198,0.89745,0.923015,0.234203
22770.0,74075.868338,0.00615036,0.906095,0.925484,0.21413
22780.0,74108.3972,0.00614819,0.905001,0.91459,0.216397
22790.0,74140.926652,0.00614656,0.909886,0.923837,0.20612
22800.0,74173.456739,0.00614494,0.899203,0.921874,0.229764
22810.0,74205.979988,0.00614277,0.904964,0.929641,0.218287
22820.0,74238.503381,0.00614114,0.906989,0.936298,0.213873
22830.0,74271.030208,0.00613951,0.911233,0.932046,0.205389
22840.0,74303.5494,0.00613735,0.903921,0.905306,0.219259
22850.0,74336.071662,0.00613572,0.901459,0.933956,0.226162
22860.0,74368.595227,0.00613409,0.898314,0.904051,0.233715
22870.0,74401.114766,0.00613192,0.901608,0.930995,0.223674
22880.0,74433.634491,0.00613029,0.88776,0.886767,0.254255
22890.0,74466.156603,0.00612867,0.89899,0.925143,0.231828
22900.0,74498.679868,0.0061265,0.902775,0.928217,0.222036
22910.0,74531.191992,0.00612487,0.904617,0.942491,0.220889
22920.0,74563.70454,0.00612324,0.903812,0.908243,0.220506
22930.0,74596.218393,0.00612107,0.907801,0.9249,0.210962
22940.0,74628.742705,0.00611944,0.908866,0.923146,0.211832
22950.0,74661.264754,0.00611781,0.90693,0.929875,0.215365
22960.0,74693.778048,0.00611564,0.905903,0.93333,0.216772
22970.0,74726.295362,0.00611402,0.900308,0.948438,0.228938
22980.0,74758.814052,0.00611239,0.906782,0.912415,0.214155
22990.0,74791.335828,0.00611022,0.903506,0.925165,0.221809
23000.0,74823.851397,0.00610859,0.90593,0.924325,0.213231
23010.0,74856.372836,0.00610696,0.895055,0.931567,0.239928
23020.0,74888.893498,0.00610479,0.911239,0.918887,0.204906
23030.0,74921.41021,0.00610316,0.904618,0.92744,0.219293
23040.0,74953.923062,0.00610153,0.893352,0.934833,0.246912
23050.0,74986.442805,0.00609935,0.908771,0.912386,0.210036
23060.0,75018.961201,0.00609773,0.908211,0.914831,0.209279
23070.0,75051.480094,0.0060961,0.913458,0.898969,0.199927
23080.0,75083.997215,0.00609392,0.901575,0.930637,0.227266
23090.0,75116.518264,0.00609229,0.907039,0.915708,0.213101
23100.0,75149.0445,0.00609066,0.900765,0.900637,0.227674
23110.0,75181.566316,0.00608849,0.898381,0.915151,0.234077
23120.0,75214.086075,0.00608686,0.908906,0.927372,0.210359
23130.0,75246.603904,0.00608523,0.909044,0.927308,0.208861
23140.0,75279.129934,0.00608305,0.909833,0.922354,0.206596
23150.0,75311.650298,0.00608142,0.909846,0.910786,0.207451
23160.0,75344.167953,0.00607979,0.903154,0.9248,0.221867
23170.0,75376.686994,0.00607762,0.910823,0.926852,0.207698
23180.0,75409.208452,0.00607599,0.909339,0.934463,0.209591
23190.0,75441.728323,0.00607436,0.905219,0.924769,0.219719
23200.0,75474.248133,0.00607218,0.894432,0.941327,0.244924
23210.0,75506.767795,0.00607055,0.472002,0.948337,1.36729
23220.0,75539.292948,0.00606892,0.905173,0.925129,0.217793
23230.0,75571.811335,0.00606674,0.908064,0.935397,0.210755
23240.0,75604.336952,0.00606511,0.90377,0.893449,0.218654
23250.0,75636.887407,0.00606348,0.912334,0.893712,0.203182
23260.0,75669.428976,0.0060613,0.908256,0.926099,0.211261
23270.0,75701.983706,0.00605967,0.909896,0.914841,0.206532
23280.0,75734.533695,0.00605804,0.914112,0.925002,0.197865
23290.0,75767.094433,0.00605586,0.910709,0.93536,0.206241
23300.0,75799.646162,0.00605423,0.912205,0.929966,0.203893
23310.0,75832.195882,0.0060526,0.904606,0.933077,0.218882
23320.0,75864.74937,0.00605042,0.907365,0.939803,0.213567
23330.0,75897.314058,0.00604879,0.90443,0.934921,0.216254
23340.0,75929.859956,0.00604716,0.914861,0.931137,0.196524
23350.0,75962.383165,0.00604498,0.908239,0.93253,0.212287
23360.0,75994.903986,0.00604335,0.909519,0.935647,0.208663
23370.0,76027.438863,0.00604171,0.906226,0.93146,0.216651
23380.0,76059.957513,0.00603954,0.910689,0.920298,0.204266
23390.0,76092.477116,0.0060379,0.902005,0.918252,0.223747
23400.0,76125.013799,0.00603627,0.912269,0.927356,0.202252
23410.0,76157.54149,0.00603409,0.901878,0.933243,0.223495
23420.0,76190.077978,0.00603246,0.90904,0.916108,0.208967
23430.0,76222.615096,0.00603082,0.906643,0.938734,0.216096
23440.0,76255.143541,0.00602864,0.903444,0.943759,0.221993
23450.0,76287.677609,0.00602701,0.903577,0.939934,0.222893
23460.0,76320.203697,0.00602537,0.900993,0.930687,0.228948
23470.0,76352.738058,0.00602319,0.908066,0.914392,0.212269
23480.0,76385.267828,0.00602156,0.895993,0.940175,0.23945
23490.0,76417.793297,0.00601992,0.898427,0.934498,0.233487
23500.0,76450.32159,0.00601775,0.90003,0.926422,0.229467
23510.0,76482.84783,0.00601611,0.896938,0.925383,0.233259
23520.0,76515.380654,0.00601448,0.914035,0.943171,0.198454
23530.0,76547.921483,0.00601229,0.908408,0.928879,0.210077
23540.0,76580.460374,0.00601066,0.905874,0.929135,0.217416
23550.0,76612.993104,0.00600902,0.912513,0.937312,0.200195
23560.0,76645.526958,0.00600684,0.909787,0.923288,0.207107
23570.0,76678.057742,0.00600521,0.907115,0.935014,0.21226
23580.0,76710.582605,0.00600357,0.912189,0.928539,0.20279
23590.0,76743.111639,0.00600139,0.905602,0.930567,0.216088
23600.0,76775.635859,0.00599975,0.909746,0.934371,0.207453
23610.0,76808.156063,0.00599812,0.910696,0.938082,0.205283
23620.0,76840.677848,0.00599594,0.915287,0.930779,0.195813
23630.0,76873.208625,0.0059943,0.902684,0.937792,0.224312
23640.0,76905.739917,0.00599266,0.911695,0.904015,0.203979
23650.0,76938.259577,0.00599048,0.907836,0.927284,0.212217
23660.0,76970.786402,0.00598884,0.910087,0.922377,0.207425
23670.0,77003.314485,0.00598721,0.899954,0.91933,0.230028
23680.0,77035.845014,0.00598502,0.908716,0.934189,0.210403
23690.0,77068.376461,0.00598339,0.902015,0.934343,0.224012
23700.0,77100.908724,0.00598175,0.899408,0.928716,0.228945
23710.0,77133.43917,0.00597957,0.899824,0.940185,0.233114
23720.0,77165.980252,0.00597793,0.908494,0.943466,0.211585
23730.0,77198.517565,0.00597629,0.904893,0.934091,0.218016
23740.0,77231.053271,0.00597411,0.904567,0.912573,0.218847
23750.0,77263.580328,0.00597247,0.904846,0.916041,0.220229
23760.0,77296.10595,0.00597083,0.908746,0.938506,0.210691
23770.0,77328.642092,0.00596865,0.906539,0.914374,0.215633
23780.0,77361.180716,0.00596701,0.902826,0.930395,0.224653
23790.0,77393.71428,0.00596537,0.905559,0.941312,0.21871
23800.0,77426.251486,0.00596318,0.915503,0.925467,0.191579
23810.0,77458.783577,0.00596155,0.906272,0.928423,0.217032
23820.0,77491.316868,0.00595991,0.90861,0.93209,0.21183
23830.0,77523.847485,0.00595772,0.911154,0.928644,0.203975
23840.0,77556.374601,0.00595608,0.908487,0.913874,0.209505
23850.0,77588.896781,0.00595444,0.904195,0.91525,0.219871
23860.0,77621.421978,0.00595226,0.90173,0.900078,0.226602
23870.0,77653.939707,0.00595062,0.912911,0.915639,0.200801
23880.0,77686.464054,0.00594898,0.89878,0.902234,0.236617
23890.0,77718.990708,0.00594679,0.906375,0.934701,0.214907
23900.0,77751.514162,0.00594515,0.906394,0.942217,0.214606
23910.0,77784.033574,0.00594351,0.907612,0.933392,0.213212
23920.0,77816.55387,0.00594133,0.906445,0.931186,0.214262
23930.0,77849.075508,0.00593969,0.908698,0.931033,0.211377
23940.0,77881.595267,0.00593805,0.906266,0.928163,0.216768
23950.0,77914.116151,0.00593586,0.909228,0.941456,0.208436
23960.0,77946.639279,0.00593422,0.902381,0.920533,0.223942
23970.0,77979.165702,0.00593258,0.911542,0.933231,0.203396
23980.0,78011.691369,0.00593039,0.903388,0.937681,0.221079
23990.0,78044.218135,0.00592875,0.911983,0.919292,0.202563
24000.0,78077.233642,0.00592711,0.907964,0.938425,0.212485
24010.0,78109.749857,0.00592492,0.910844,0.890816,0.207073
24020.0,78142.273199,0.00592328,0.907342,0.949206,0.215365
24030.0,78174.798622,0.00592164,0.902214,0.937792,0.226612
24040.0,78207.321048,0.00591945,0.907398,0.926928,0.212212
24050.0,78239.843851,0.0059178,0.904852,0.937944,0.218939
24060.0,78272.37246,0.00591616,0.910791,0.928192,0.203131
24070.0,78304.898306,0.00591397,0.905989,0.939971,0.217328
24080.0,78337.424302,0.00591233,0.908825,0.938345,0.210079
24090.0,78369.95293,0.00591069,0.913819,0.923363,0.198199
24100.0,78402.475098,0.0059085,0.911894,0.932758,0.202741
24110.0,78434.999699,0.00590686,0.909416,0.935077,0.208043
24120.0,78467.519989,0.00590521,0.907258,0.938727,0.211976
24130.0,78500.046154,0.00590302,0.904265,0.928032,0.219201
24140.0,78532.567414,0.00590138,0.909132,0.907149,0.208603
24150.0,78565.08819,0.00589974,0.905026,0.943015,0.218684
24160.0,78597.611978,0.00589755,0.907793,0.891334,0.212938
24170.0,78630.132517,0.0058959,0.899607,0.930628,0.228748
24180.0,78662.653583,0.00589426,0.905964,0.927288,0.213338
24190.0,78695.174564,0.00589207,0.907667,0.930104,0.212289
24200.0,78727.690609,0.00589043,0.906678,0.934634,0.21389
24210.0,78760.205941,0.00588878,0.910638,0.924085,0.204692
24220.0,78792.732005,0.00588659,0.893903,0.933924,0.238632
24230.0,78825.252613,0.00588495,0.906636,0.893674,0.215029
24240.0,78857.779462,0.0058833,0.907158,0.935286,0.21353
24250.0,78890.297188,0.00588111,0.907596,0.912053,0.213011
24260.0,78922.818598,0.00587947,0.899888,0.913806,0.229551
24270.0,78955.341989,0.00587782,0.906938,0.932958,0.211825
24280.0,78987.872939,0.00587563,0.90703,0.930331,0.21283
24290.0,79020.409006,0.00587398,0.905871,0.940677,0.214943
24300.0,79052.948503,0.00587234,0.905969,0.92842,0.215321
24310.0,79085.479001,0.00587014,0.911483,0.926468,0.202559
24320.0,79118.012329,0.0058685,0.906152,0.912225,0.214233
24330.0,79150.546077,0.00586685,0.906482,0.928011,0.214293
24340.0,79183.080933,0.00586466,0.911279,0.936598,0.204286
24350.0,79215.611237,0.00586301,0.912233,0.907102,0.201419
24360.0,79248.146994,0.00586137,0.914493,0.915299,0.197556
24370.0,79280.688585,0.00585917,0.904446,0.941483,0.219033
24380.0,79313.22703,0.00585753,0.90473,0.910893,0.220137
24390.0,79345.765309,0.00585588,0.912303,0.910947,0.201459
24400.0,79378.298821,0.00585369,0.909523,0.926606,0.208345
24410.0,79410.837193,0.00585204,0.906347,0.942481,0.213643
24420.0,79443.375101,0.00585039,0.905249,0.924917,0.216003
24430.0,79475.946734,0.0058482,0.907509,0.928802,0.211921
24440.0,79508.482377,0.00584655,0.899754,0.936897,0.229866
24450.0,79541.011068,0.00584491,0.904492,0.929327,0.220397
24460.0,79573.532858,0.00584271,0.907177,0.935913,0.211369
24470.0,79606.0682,0.00584106,0.909928,0.934967,0.209122
24480.0,79638.608213,0.00583942,0.904593,0.915558,0.219068
24490.0,79671.133593,0.00583722,0.90115,0.922941,0.225596
24500.0,79703.665579,0.00583557,0.914705,0.922537,0.196124
24510.0,79736.200966,0.00583392,0.909011,0.92883,0.209389
24520.0,79768.727611,0.00583173,0.907572,0.922408,0.211769
24530.0,79801.252741,0.00583008,0.906952,0.926086,0.213908
24540.0,79833.782506,0.00582843,0.90928,0.938847,0.209198
24550.0,79866.313121,0.00582623,0.911191,0.928845,0.203981
24560.0,79898.84129,0.00582458,0.904625,0.929198,0.216614
24570.0,79931.36868,0.00582294,0.893985,0.938971,0.241761
24580.0,79963.89823,0.00582074,0.906623,0.926436,0.213011
24590.0,79996.424358,0.00581909,0.909557,0.924356,0.207667
24600.0,80028.951668,0.00581744,0.897487,0.935028,0.235998
24610.0,80061.469659,0.00581524,0.912588,0.911121,0.200604
24620.0,80094.000276,0.00581359,0.914067,0.930825,0.197687
24630.0,80126.530463,0.00581194,0.909619,0.929345,0.206857
24640.0,80159.059812,0.00580975,0.914034,0.935908,0.198919
24650.0,80191.580361,0.0058081,0.912524,0.926899,0.199929
24660.0,80224.109885,0.00580645,0.907259,0.932537,0.21171
24670.0,80256.640374,0.00580425,0.906253,0.936327,0.214616
24680.0,80289.166934,0.0058026,0.906615,0.927341,0.213384
24690.0,80321.69058,0.00580095,0.903515,0.946204,0.223571
24700.0,80354.214572,0.00579875,0.905197,0.928342,0.21421
24710.0,80386.732103,0.0057971,0.905269,0.928373,0.218161
24720.0,80419.247884,0.00579545,0.910877,0.932069,0.205541
24730.0,80451.770838,0.00579325,0.900159,0.934134,0.227251
24740.0,80484.290093,0.00579159,0.902754,0.940505,0.224692
24750.0,80516.811726,0.00578994,0.907399,0.91976,0.212063
24760.0,80549.329239,0.00578774,0.910801,0.933592,0.208699
24770.0,80581.8469,0.00578609,0.903412,0.939501,0.220184
24780.0,80614.368112,0.00578444,0.90765,0.924372,0.213392
24790.0,80646.890446,0.00578224,0.902579,0.928109,0.225675
24800.0,80679.420321,0.00578059,0.907529,0.939503,0.212111
24810.0,80711.940344,0.00577894,0.909071,0.931684,0.209901
24820.0,80744.462973,0.00577673,0.913056,0.916262,0.200142
24830.0,80776.98304,0.00577508,0.908125,0.93438,0.209983
24840.0,80809.513289,0.00577343,0.903659,0.945808,0.220943
24850.0,80842.045193,0.00577123,0.90725,0.924791,0.212959
24860.0,80874.572184,0.00576958,0.910079,0.91742,0.207756
24870.0,80907.096722,0.00576792,0.901835,0.931567,0.224266
24880.0,80939.628358,0.00576572,0.909791,0.936558,0.206317
24890.0,80972.146163,0.00576407,0.905464,0.926913,0.217654
24900.0,81004.667947,0.00576241,0.90689,0.914075,0.212716
24910.0,81037.194814,0.00576021,0.901415,0.934317,0.224044
24920.0,81069.718065,0.00575856,0.906209,0.939139,0.214508
24930.0,81102.249522,0.0057569,0.910085,0.937827,0.205251
24940.0,81134.781424,0.0057547,0.90714,0.91182,0.213589
24950.0,81167.308356,0.00575305,0.909633,0.918173,0.207299
24960.0,81199.835415,0.00575139,0.910195,0.934225,0.207377
24970.0,81232.376161,0.00574919,0.906624,0.922474,0.214192
24980.0,81264.900424,0.00574753,0.903682,0.908132,0.221157
24990.0,81297.421473,0.00574588,0.907796,0.945266,0.211652
25000.0,81329.943577,0.00574368,0.912814,0.936348,0.200608
25010.0,81362.467981,0.00574202,0.912891,0.940796,0.200998
25020.0,81394.995947,0.00574037,0.907423,0.927756,0.2116
25030.0,81427.52614,0.00573816,0.906513,0.930681,0.217074
25040.0,81460.046303,0.00573651,0.909941,0.934536,0.204044
25050.0,81492.577526,0.00573485,0.905747,0.939055,0.217318
25060.0,81525.107816,0.00573265,0.906329,0.932153,0.213598
25070.0,81557.632595,0.00573099,0.90198,0.910241,0.223531
25080.0,81590.160558,0.00572934,0.912934,0.934256,0.201597
25090.0,81622.689036,0.00572713,0.901676,0.939608,0.225051
25100.0,81655.217391,0.00572547,0.901305,0.934229,0.225438
25110.0,81687.748867,0.00572382,0.907758,0.905314,0.211272
25120.0,81720.27386,0.00572161,0.908504,0.928741,0.209985
25130.0,81752.804456,0.00571995,0.910909,0.925681,0.203097
25140.0,81785.333871,0.0057183,0.912385,0.93127,0.203708
25150.0,81817.864571,0.00571609,0.917005,0.935572,0.191595
25160.0,81850.389791,0.00571443,0.906378,0.943465,0.215506
25170.0,81882.91792,0.00571278,0.907321,0.920802,0.212463
25180.0,81915.446284,0.00571057,0.904025,0.94622,0.221756
25190.0,81947.973555,0.00570891,0.905138,0.939539,0.216508
25200.0,81980.497361,0.00570726,0.908298,0.941941,0.210001
25210.0,82013.024737,0.00570505,0.900801,0.942607,0.227745
25220.0,82045.549026,0.00570339,0.906582,0.926943,0.215563
25230.0,82078.076564,0.00570173,0.909405,0.939719,0.207944
25240.0,82110.598223,0.00569952,0.912471,0.934072,0.201849
25250.0,82143.129173,0.00569787,0.909811,0.936626,0.207355
25260.0,82175.660499,0.00569621,0.907525,0.930404,0.211752
25270.0,82208.198576,0.005694,0.910012,0.927398,0.206815
25280.0,82240.736261,0.00569234,0.898196,0.942132,0.232282
25290.0,82273.268359,0.00569068,0.903306,0.940984,0.223454
25300.0,82305.794833,0.00568847,0.902894,0.932986,0.220233
25310.0,82338.325513,0.00568681,0.900816,0.917747,0.229663
25320.0,82370.854507,0.00568516,0.90875,0.932235,0.209903
25330.0,82403.382512,0.00568294,0.90059,0.924884,0.229255
25340.0,82435.916386,0.00568129,0.902394,0.946115,0.223979
25350.0,82468.443219,0.00567963,0.902724,0.946041,0.224993
25360.0,82500.973838,0.00567742,0.900459,0.917694,0.227316
25370.0,82533.496858,0.00567576,0.903605,0.956588,0.223779
25380.0,82566.025296,0.0056741,0.905997,0.942142,0.217894
25390.0,82598.549748,0.00567188,0.903277,0.942122,0.223366
25400.0,82631.082425,0.00567023,0.912217,0.92446,0.202456
25410.0,82663.613119,0.00566857,0.906389,0.924477,0.21593
25420.0,82696.138148,0.00566635,0.899636,0.935829,0.230432
25430.0,82728.672632,0.00566469,0.913546,0.950127,0.200282
25440.0,82761.203488,0.00566303,0.901716,0.948845,0.224695
25450.0,82793.723032,0.00566082,0.901324,0.919321,0.224888
25460.0,82826.243227,0.00565916,0.907821,0.924486,0.211716
25470.0,82858.76625,0.0056575,0.895102,0.918949,0.238698
25480.0,82891.28376,0.00565529,0.909314,0.939642,0.210696
25490.0,82923.81746,0.00565362,0.901434,0.929863,0.225036
25500.0,82956.337363,0.00565196,0.907263,0.933085,0.214729
25510.0,82988.859101,0.00564975,0.905948,0.924456,0.217007
25520.0,83021.382637,0.00564809,0.901042,0.937011,0.225417
25530.0,83053.917872,0.00564643,0.907688,0.933202,0.210301
25540.0,83086.451733,0.00564421,0.908547,0.929012,0.211501
25550.0,83118.980192,0.00564255,0.913222,0.928399,0.199792
25560.0,83151.509895,0.00564089,0.907917,0.934464,0.211038
25570.0,83184.042169,0.00563867,0.911617,0.941038,0.204537
25580.0,83216.57248,0.00563701,0.912207,0.912898,0.202932
25590.0,83249.105001,0.00563535,0.909658,0.933219,0.206811
25600.0,83281.639758,0.00563313,0.893675,0.948841,0.240992
25610.0,83314.167988,0.00563147,0.903099,0.929492,0.222799
25620.0,83346.700547,0.00562981,0.911702,0.933509,0.201742
25630.0,83379.228084,0.00562759,0.899496,0.93803,0.22991
25640.0,83411.758628,0.00562593,0.907105,0.934274,0.212789
25650.0,83444.287921,0.00562427,0.906363,0.93003,0.213433
25660.0,83476.814074,0.00562205,0.908402,0.926889,0.210485
25670.0,83509.342529,0.00562039,0.905506,0.940753,0.217846
25680.0,83541.878235,0.00561872,0.904,0.93279,0.220726
25690.0,83574.411884,0.00561651,0.90222,0.937655,0.223147
25700.0,83606.944062,0.00561484,0.90055,0.940952,0.227735
25710.0,83639.47422,0.00561318,0.910765,0.943318,0.205039
25720.0,83672.004103,0.00561096,0.914471,0.933202,0.197391
25730.0,83704.535082,0.0056093,0.909544,0.938406,0.208406
25740.0,83737.070377,0.00560763,0.911039,0.930428,0.205691
25750.0,83769.606817,0.00560541,0.910001,0.922375,0.206705
25760.0,83802.140252,0.00560375,0.903849,0.924078,0.223113
25770.0,83834.673967,0.00560209,0.908703,0.930789,0.213013
25780.0,83867.200951,0.00559987,0.907281,0.944341,0.214652
25790.0,83899.737388,0.0055982,0.915834,0.929501,0.194724
25800.0,83932.269499,0.00559654,0.908083,0.903334,0.211558
25810.0,83964.79784,0.00559432,0.907025,0.945369,0.215002
25820.0,83997.332667,0.00559265,0.913438,0.915136,0.200282
25830.0,84029.867687,0.00559099,0.90583,0.917281,0.214231
25840.0,84062.397035,0.00558877,0.909844,0.907413,0.208425
25850.0,84094.919135,0.0055871,0.902991,0.920585,0.221495
25860.0,84127.447672,0.00558543,0.902088,0.916323,0.225809
25870.0,84159.982412,0.00558321,0.901137,0.918566,0.225658
25880.0,84192.518526,0.00558155,0.909971,0.924876,0.203893
25890.0,84225.062015,0.00557988,0.90993,0.917572,0.206359
25900.0,84257.592482,0.00557766,0.904058,0.895114,0.222415
25910.0,84290.121091,0.00557599,0.908999,0.940028,0.210482
25920.0,84322.655767,0.00557433,0.912346,0.912576,0.20185
25930.0,84355.184107,0.0055721,0.909103,0.936522,0.210597
25940.0,84387.726363,0.00557044,0.902284,0.933701,0.224302
25950.0,84420.254856,0.00556877,0.912914,0.932713,0.2013
25960.0,84452.791845,0.00556655,0.906588,0.937707,0.214337
25970.0,84485.345338,0.00556488,0.906221,0.945729,0.214113
25980.0,84517.900573,0.00556321,0.899506,0.932458,0.22988
25990.0,84550.459538,0.00556099,0.90949,0.929148,0.208518
26000.0,84583.518148,0.00555932,0.906011,0.941701,0.215999
26010.0,84616.074425,0.00555766,0.905255,0.929089,0.217881
26020.0,84648.604214,0.00555543,0.905945,0.940269,0.216268
26030.0,84681.129629,0.00555376,0.913434,0.941091,0.19803
26040.0,84713.660773,0.0055521,0.910484,0.917713,0.206554
26050.0,84746.191921,0.00554987,0.913021,0.931255,0.200143
26060.0,84778.722158,0.0055482,0.909349,0.934947,0.211063
26070.0,84811.255166,0.00554653,0.912238,0.941038,0.201187
26080.0,84843.786715,0.00554431,0.911752,0.92952,0.202226
26090.0,84876.319198,0.00554264,0.905998,0.940079,0.215858
26100.0,84908.85181,0.00554097,0.915799,0.935757,0.192835
26110.0,84941.377635,0.00553875,0.908873,0.926878,0.208236
26120.0,84973.910711,0.00553708,0.885534,0.934985,0.263036
26130.0,85006.441878,0.00553541,0.906884,0.937497,0.211291
26140.0,85038.974493,0.00553318,0.91016,0.947238,0.206484
26150.0,85071.503701,0.00553151,0.909123,0.945061,0.209838
26160.0,85104.023926,0.00552984,0.91024,0.927139,0.206431
26170.0,85136.554917,0.00552762,0.909083,0.937381,0.209214
26180.0,85169.084099,0.00552595,0.911782,0.930531,0.204348
26190.0,85201.612471,0.00552427,0.903244,0.933332,0.222536
26200.0,85234.152128,0.00552205,0.902043,0.938168,0.2226
26210.0,85266.680951,0.00552038,0.906998,0.919133,0.212246
26220.0,85299.204718,0.00551871,0.907208,0.929888,0.2144
26230.0,85331.741405,0.00551648,0.912616,0.935611,0.202722
26240.0,85364.28405,0.00551481,0.912613,0.936369,0.20218
26250.0,85396.824124,0.00551314,0.90838,0.922324,0.207578
26260.0,85429.356696,0.00551091,0.903758,0.925423,0.219791
26270.0,85461.889892,0.00550924,0.909841,0.932608,0.207117
26280.0,85494.429814,0.00550757,0.908929,0.915681,0.207554
26290.0,85526.949335,0.00550534,0.914135,0.931769,0.197206
26300.0,85559.480328,0.00550366,0.90912,0.923368,0.209882
26310.0,85592.013848,0.00550199,0.908901,0.943205,0.209669
26320.0,85624.557658,0.00549976,0.905084,0.944372,0.221266
26330.0,85657.078716,0.00549809,0.91237,0.918284,0.202185
26340.0,85689.61436,0.00549642,0.911121,0.940725,0.203541
26350.0,85722.154932,0.00549419,0.910208,0.945547,0.205975
26360.0,85754.691275,0.00549252,0.911408,0.934947,0.202632
26370.0,85787.227294,0.00549084,0.909752,0.919542,0.209347
26380.0,85819.762718,0.00548861,0.906634,0.937758,0.211825
26390.0,85852.295998,0.00548694,0.907459,0.926043,0.212039
26400.0,85884.809356,0.00548527,0.905987,0.928825,0.216935
26410.0,85917.337676,0.00548304,0.90967,0.936719,0.20816
26420.0,85949.877331,0.00548136,0.905361,0.944675,0.216241
26430.0,85982.416366,0.00547969,0.902106,0.927769,0.224063
26440.0,86014.949806,0.00547746,0.908352,0.935712,0.207841
26450.0,86047.48673,0.00547578,0.89763,0.941392,0.234228
26460.0,86080.018995,0.00547411,0.914398,0.92679,0.195569
26470.0,86112.552431,0.00547188,0.908123,0.929675,0.211657
26480.0,86145.084499,0.0054702,0.904643,0.937608,0.217321
26490.0,86177.609195,0.00546853,0.905536,0.941628,0.218088
26500.0,86210.147578,0.00546629,0.91461,0.930965,0.197171
26510.0,86242.691265,0.00546462,0.908778,0.939925,0.211297
26520.0,86275.237764,0.00546294,0.896676,0.945187,0.236573
26530.0,86307.776046,0.00546071,0.906693,0.947102,0.214447
26540.0,86340.312437,0.00545904,0.904617,0.954655,0.217639
26550.0,86372.853243,0.00545736,0.906682,0.936332,0.212507
26560.0,86405.393156,0.00545513,0.912199,0.927237,0.201619
26570.0,86437.933054,0.00545345,0.906552,0.931696,0.215408
26580.0,86470.465044,0.00545178,0.909025,0.928509,0.208238
26590.0,86502.99511,0.00544954,0.892526,0.924652,0.243841
26600.0,86535.542757,0.00544786,0.911448,0.915033,0.204343
26610.0,86568.085793,0.00544619,0.907076,0.940587,0.21342
26620.0,86600.625744,0.00544395,0.898461,0.943866,0.232356
26630.0,86633.157742,0.00544228,0.908473,0.919663,0.211168
26640.0,86665.684679,0.0054406,0.908731,0.929727,0.208625
26650.0,86698.212776,0.00543837,0.90731,0.942144,0.212895
26660.0,86730.735747,0.00543669,0.914003,0.921332,0.199419
26670.0,86763.266148,0.00543501,0.904206,0.929974,0.217364
26680.0,86795.790813,0.00543277,0.913275,0.918883,0.200547
26690.0,86828.318257,0.0054311,0.906761,0.934169,0.214663
26700.0,86860.840039,0.00542942,0.910655,0.940505,0.205196
26710.0,86893.377191,0.00542718,0.913872,0.907399,0.200525
26720.0,86925.911739,0.00542551,0.910219,0.917113,0.207227
26730.0,86958.452259,0.00542383,0.909082,0.929785,0.208147
26740.0,86990.983261,0.00542159,0.913928,0.935385,0.196536
26750.0,87023.514388,0.00541991,0.90965,0.905738,0.207224
26760.0,87056.049477,0.00541823,0.909447,0.944328,0.207806
26770.0,87088.583854,0.005416,0.906828,0.93162,0.213861
26780.0,87121.111092,0.00541432,0.889424,0.922806,0.248117
26790.0,87153.641847,0.00541264,0.908545,0.94942,0.210747
26800.0,87186.177215,0.0054104,0.905894,0.918619,0.216553
26810.0,87218.711369,0.00540872,0.905449,0.939973,0.219156
26820.0,87251.24684,0.00540704,0.905863,0.949098,0.216938
26830.0,87283.791618,0.0054048,0.908208,0.943679,0.210489
26840.0,87316.31727,0.00540312,0.908083,0.941568,0.210579
26850.0,87348.852347,0.00540144,0.904973,0.938034,0.218357
26860.0,87381.386575,0.0053992,0.912345,0.944461,0.202317
26870.0,87413.917551,0.00539752,0.907014,0.94637,0.213902
26880.0,87446.449988,0.00539584,0.904821,0.950898,0.220324
26890.0,87478.97649,0.0053936,0.903311,0.946489,0.220491
26900.0,87511.502849,0.00539192,0.91226,0.941372,0.201077
26910.0,87544.037882,0.00539024,0.902587,0.948799,0.223016
26920.0,87576.56758,0.005388,0.912462,0.940097,0.202767
26930.0,87609.102526,0.00538632,0.913642,0.923801,0.198317
26940.0,87641.635901,0.00538464,0.911201,0.937909,0.203173
26950.0,87674.177668,0.0053824,0.907746,0.947106,0.211165
26960.0,87706.717816,0.00538072,0.894933,0.952919,0.241703
26970.0,87739.252219,0.00537904,0.901483,0.947447,0.225939
26980.0,87771.774451,0.00537679,0.900911,0.934793,0.226667
26990.0,87804.308747,0.00537511,0.907237,0.938107,0.2128
27000.0,87836.846784,0.00537343,0.909114,0.938486,0.208819
27010.0,87869.389625,0.00537119,0.908406,0.946371,0.212121
27020.0,87901.920637,0.0053695,0.906523,0.943701,0.213721
27030.0,87934.453342,0.00536782,0.909915,0.943941,0.205976
27040.0,87966.982649,0.00536558,0.902676,0.932316,0.225901
27050.0,87999.520134,0.0053639,0.898649,0.93239,0.230721
27060.0,88032.056674,0.00536221,0.905138,0.941392,0.217882
27070.0,88064.585582,0.00535997,0.910935,0.930742,0.203913
27080.0,88097.117692,0.00535829,0.911082,0.936545,0.204066
27090.0,88129.652813,0.0053566,0.915352,0.929567,0.193635
27100.0,88162.185074,0.00535436,0.907386,0.930366,0.213416
27110.0,88194.714394,0.00535268,0.905952,0.938804,0.215418
27120.0,88227.251087,0.00535099,0.911668,0.921808,0.203169
27130.0,88259.783798,0.00534875,0.907915,0.921514,0.211554
27140.0,88292.320462,0.00534706,0.910905,0.948285,0.204695
27150.0,88324.862751,0.00534538,0.914345,0.941271,0.197048
27160.0,88357.3985,0.00534313,0.907175,0.933008,0.211442
27170.0,88389.934287,0.00534145,0.903764,0.928336,0.219548
27180.0,88422.469476,0.00533977,0.90689,0.935043,0.212299
27190.0,88455.007849,0.00533752,0.901559,0.93975,0.224802
27200.0,88487.535629,0.00533583,0.907848,0.937367,0.210127
27210.0,88520.067716,0.00533415,0.909533,0.928564,0.206817
27220.0,88552.60332,0.0053319,0.911602,0.926936,0.202404
27230.0,88585.139223,0.00533022,0.914094,0.918937,0.198072
27240.0,88617.674914,0.00532853,0.911528,0.925334,0.204486
27250.0,88650.205317,0.00532628,0.913209,0.937378,0.201556
27260.0,88682.745033,0.0053246,0.907277,0.923159,0.211429
27270.0,88715.274307,0.00532291,0.901911,0.865653,0.224513
27280.0,88747.809754,0.00532066,0.909155,0.940416,0.208014
27290.0,88780.350798,0.00531898,0.908876,0.942294,0.209776
27300.0,88812.888324,0.00531729,0.919039,0.924783,0.1871
27310.0,88845.427877,0.00531504,0.902259,0.943613,0.225774
27320.0,88877.963192,0.00531336,0.911682,0.92726,0.204737
27330.0,88910.496493,0.00531167,0.911717,0.938906,0.203264
27340.0,88943.034145,0.00530942,0.903529,0.939398,0.220428
27350.0,88975.572607,0.00530773,0.908529,0.927864,0.211602
27360.0,89008.111486,0.00530605,0.907176,0.929448,0.21579
27370.0,89040.641215,0.0053038,0.911318,0.935338,0.204908
27380.0,89073.171723,0.00530211,0.914942,0.934387,0.195402
27390.0,89105.705138,0.00530042,0.90593,0.945811,0.218656
27400.0,89138.233098,0.00529817,0.906843,0.940237,0.213389
27410.0,89170.767194,0.00529648,0.910763,0.935249,0.20542
27420.0,89203.31023,0.0052948,0.910219,0.924024,0.210121
27430.0,89235.84959,0.00529255,0.908015,0.935455,0.215298
27440.0,89268.387191,0.00529086,0.903603,0.932953,0.221603
27450.0,89300.924127,0.00528917,0.910743,0.943974,0.20698
27460.0,89333.463977,0.00528692,0.906606,0.928206,0.217975
27470.0,89366.001796,0.00528523,0.912261,0.905794,0.205052
27480.0,89398.542206,0.00528354,0.908127,0.941526,0.212676
27490.0,89431.079404,0.00528129,0.907043,0.931361,0.213779
27500.0,89463.613588,0.0052796,0.902926,0.93424,0.22259
27510.0,89496.148205,0.00527791,0.910161,0.942162,0.208474
27520.0,89528.682985,0.00527566,0.902623,0.936506,0.22438
27530.0,89561.213948,0.00527397,0.905241,0.944334,0.216073
27540.0,89593.749906,0.00527228,0.908302,0.945224,0.209858
27550.0,89626.286709,0.00527002,0.904389,0.932757,0.219349
27560.0,89658.821829,0.00526833,0.909652,0.926999,0.205505
27570.0,89691.355427,0.00526664,0.91261,0.927551,0.201415
27580.0,89723.891979,0.00526439,0.906249,0.940256,0.215293
27590.0,89756.428226,0.0052627,0.90534,0.913273,0.217564
27600.0,89788.970575,0.00526101,0.902896,0.934367,0.223836
27610.0,89821.513132,0.00525875,0.915285,0.928006,0.19583
27620.0,89854.048142,0.00525706,0.905818,0.941688,0.215365
27630.0,89886.587322,0.00525537,0.887297,0.947411,0.254142
27640.0,89919.123744,0.00525312,0.907372,0.933238,0.212688
27650.0,89951.665012,0.00525142,0.911484,0.928122,0.20304
27660.0,89984.197606,0.00524973,0.906018,0.939376,0.215399
27670.0,90016.721909,0.00524748,0.909905,0.928318,0.204844
27680.0,90049.253904,0.00524578,0.914353,0.926618,0.196452
27690.0,90081.785223,0.00524409,0.914359,0.936533,0.194365
27700.0,90114.313611,0.00524184,0.894732,0.947252,0.240046
27710.0,90146.845895,0.00524014,0.913324,0.922975,0.200576
27720.0,90179.37783,0.00523845,0.907172,0.926135,0.21295
27730.0,90211.90113,0.00523619,0.905039,0.938272,0.219605
27740.0,90244.430395,0.0052345,0.911312,0.93931,0.203684
27750.0,90276.961187,0.00523281,0.905326,0.945489,0.219345
27760.0,90309.491934,0.00523055,0.906164,0.93729,0.21574
27770.0,90342.034392,0.00522886,0.910601,0.923571,0.20617
27780.0,90374.567168,0.00522716,0.905849,0.944376,0.215425
27790.0,90407.094455,0.00522491,0.906542,0.947535,0.214671
27800.0,90439.631843,0.00522321,0.908163,0.932078,0.209196
27810.0,90472.153862,0.00522152,0.908054,0.948225,0.209453
27820.0,90504.687763,0.00521926,0.903454,0.935198,0.218972
27830.0,90537.232139,0.00521757,0.906958,0.943933,0.21314
27840.0,90569.769007,0.00521587,0.90905,0.939169,0.208787
27850.0,90602.303311,0.00521361,0.908546,0.959085,0.211662
27860.0,90634.837065,0.00521192,0.908876,0.940684,0.20978
27870.0,90667.371627,0.00521022,0.905779,0.949081,0.216944
27880.0,90699.906407,0.00520796,0.906836,0.948068,0.216407
27890.0,90732.443236,0.00520627,0.913486,0.946349,0.199065
27900.0,90764.971324,0.00520457,0.909309,0.952807,0.211691
27910.0,90797.503226,0.00520231,0.90646,0.942087,0.215818
27920.0,90830.036229,0.00520062,0.903199,0.949995,0.222812
27930.0,90862.569126,0.00519892,0.911212,0.942532,0.205114
27940.0,90895.110953,0.00519666,0.904859,0.926953,0.214658
27950.0,90927.652499,0.00519496,0.903147,0.942915,0.223912
27960.0,90960.185605,0.00519327,0.909481,0.931626,0.205829
27970.0,90992.717435,0.005191,0.905962,0.932468,0.213838
27980.0,91025.253044,0.00518931,0.901414,0.927116,0.224782
27990.0,91057.795314,0.00518761,0.913193,0.946262,0.200614
28000.0,91090.83041,0.00518535,0.899537,0.944254,0.229424
28010.0,91123.385394,0.00518365,0.909421,0.934196,0.206745
28020.0,91155.926496,0.00518195,0.908706,0.949492,0.210412
28030.0,91188.466504,0.00517969,0.912248,0.922132,0.19969
28040.0,91221.00154,0.00517799,0.914615,0.940892,0.197113
28050.0,91253.538645,0.0051763,0.908497,0.935128,0.208658
28060.0,91286.075513,0.00517403,0.906898,0.930555,0.213878
28070.0,91318.607095,0.00517233,0.906462,0.950658,0.21234
28080.0,91351.143579,0.00517064,0.912986,0.949977,0.199359
28090.0,91383.673142,0.00516837,0.907523,0.917265,0.213427
28100.0,91416.19985,0.00516667,0.908056,0.936576,0.21187
28110.0,91448.727872,0.00516497,0.900671,0.930819,0.225163
28120.0,91481.257332,0.00516271,0.905357,0.943074,0.217158
28130.0,91513.786853,0.00516101,0.912104,0.935172,0.201746
28140.0,91546.317577,0.00515931,0.906791,0.944267,0.21366
28150.0,91578.848072,0.00515705,0.911652,0.937296,0.202599
28160.0,91611.380312,0.00515535,0.907268,0.937823,0.212665
28170.0,91643.912111,0.00515365,0.904611,0.925252,0.217725
28180.0,91676.44952,0.00515138,0.903364,0.939479,0.222723
28190.0,91708.984048,0.00514968,0.907532,0.933989,0.212239
28200.0,91741.506163,0.00514798,0.911109,0.939333,0.202255
28210.0,91774.022877,0.00514571,0.906077,0.923927,0.218538
28220.0,91806.551842,0.00514401,0.910742,0.938321,0.205842
28230.0,91839.082977,0.00514231,0.914418,0.940905,0.197024
28240.0,91871.612062,0.00514005,0.907142,0.93508,0.211224
28250.0,91904.141303,0.00513835,0.908171,0.942875,0.209719
28260.0,91936.667756,0.00513664,0.91259,0.939054,0.201484
28270.0,91969.195955,0.00513438,0.904788,0.935708,0.220346
28280.0,92001.727708,0.00513268,0.90621,0.940035,0.214609
28290.0,92034.253394,0.00513097,0.913901,0.942441,0.197785
28300.0,92066.781156,0.00512871,0.90082,0.920342,0.22727
28310.0,92099.307789,0.005127,0.901427,0.946854,0.224526
28320.0,92131.836687,0.0051253,0.907475,0.932401,0.214305
28330.0,92164.362144,0.00512303,0.902948,0.930334,0.221771
28340.0,92196.885303,0.00512133,0.912182,0.937995,0.204176
28350.0,92229.412095,0.00511963,0.904746,0.949234,0.220142
28360.0,92261.933936,0.00511736,0.916428,0.925373,0.19207
28370.0,92294.467059,0.00511566,0.901396,0.938078,0.226453
28380.0,92326.994038,0.00511395,0.916138,0.938135,0.194844
28390.0,92359.525463,0.00511168,0.913803,0.92679,0.199192
28400.0,92392.050671,0.00510998,0.909932,0.947808,0.206963
28410.0,92424.577798,0.00510828,0.906151,0.927976,0.215269
28420.0,92457.106465,0.005106,0.906335,0.927714,0.217297
28430.0,92489.632808,0.0051043,0.909772,0.939882,0.20701
28440.0,92522.16085,0.0051026,0.901986,0.922766,0.222336
28450.0,92554.686898,0.00510033,0.907743,0.938923,0.211418
28460.0,92587.21439,0.00509862,0.907372,0.939277,0.211854
28470.0,92619.741696,0.00509692,0.91236,0.936404,0.201386
28480.0,92652.267959,0.00509465,0.91092,0.92909,0.203957
28490.0,92684.795597,0.00509294,0.91074,0.938025,0.20446
28500.0,92717.321984,0.00509124,0.908977,0.940057,0.209869
28510.0,92749.846056,0.00508896,0.906365,0.925392,0.214488
28520.0,92782.382355,0.00508726,0.909906,0.94511,0.206254
28530.0,92814.912225,0.00508555,0.909067,0.935474,0.208548
28540.0,92847.433705,0.00508328,0.907581,0.941565,0.211651
28550.0,92879.958544,0.00508157,0.906106,0.949262,0.215541
28560.0,92912.491287,0.00507987,0.905402,0.951,0.21619
28570.0,92945.026297,0.00507759,0.906495,0.937853,0.212141
28580.0,92977.563126,0.00507589,0.905275,0.940134,0.219322
28590.0,93010.097631,0.00507418,0.906798,0.93537,0.211726
28600.0,93042.631508,0.00507191,0.902299,0.946838,0.223007
28610.0,93075.163607,0.0050702,0.90122,0.9503,0.225575
28620.0,93107.704323,0.00506849,0.904821,0.933801,0.21701
28630.0,93140.238382,0.00506622,0.914078,0.931097,0.19588
28640.0,93172.777763,0.00506451,0.90858,0.93568,0.210189
28650.0,93205.311983,0.0050628,0.902073,0.948521,0.225389
28660.0,93237.846975,0.00506053,0.90893,0.925977,0.209497
28670.0,93270.375713,0.00505882,0.90783,0.93856,0.211467
SEMTEM_membranes_TrainedNet/5fm/log/caffe.bin.ip-172-31-27-45.ubuntu.log.INFO.20180605-225940.547150000644001645100001440003474372513337124763027424 0ustar mhaberlusersLog file created at: 2018/06/05 22:59:40
Running on machine: ip-172-31-27-45
Log line format: [IWEF]mmdd hh:mm:ss.uuuuuu threadid file:line] msg
I0605 22:59:40.763371 54715 caffe.cpp:93] FLAGS_gpu.size() = 1
I0605 22:59:40.763492 54715 caffe.cpp:96] FLAGS_strings.size() = 1
I0605 22:59:40.763506 54715 caffe.cpp:186] Using GPUs 2
I0605 22:59:54.863592 54715 solver.cpp:48] Initializing solver from parameters:
test_iter: 20
test_interval: 10
base_lr: 0.01
display: 3
max_iter: 50000
lr_policy: "poly"
power: 0.8
momentum: 0.9
weight_decay: 0.0005
snapshot: 2000
snapshot_prefix: "/home/ubuntu/membraneTraining_SEMTEM/5fm/trainedmodel/5fm_classifer"
solver_mode: GPU
device_id: 2
net: "train_val.prototxt"
average_loss: 16
iter_size: 8
snapshot_format: BINARYPROTO
I0605 22:59:54.863683 54715 solver.cpp:91] Creating training net from net file: train_val.prototxt
I0605 22:59:54.865272 54715 net.cpp:322] The NetState phase (0) differed from the phase (1) specified by a rule in layer data
I0605 22:59:54.865363 54715 net.cpp:322] The NetState phase (0) differed from the phase (1) specified by a rule in layer accuracy_conv
I0605 22:59:54.866425 54715 net.cpp:49] Initializing net from parameters:
state {
phase: TRAIN
}
layer {
name: "data"
type: "PatchData"
top: "data"
top: "label"
include {
phase: TRAIN
}
patch_sampler_param {
batch_size: 5
data_patch_shape {
dim: 320
dim: 320
dim: 5
}
label_patch_shape {
dim: 320
dim: 320
dim: 1
}
patches_per_data_batch: 7999999
}
transform_nd_param {
mirror: true
padding: true
pad_method: ZERO
}
data_provider_param {
data_source: "/home/ubuntu/membraneTraining_SEMTEM/train_file.txt"
hdf5_file_shuffle: true
batch_size: 16
backend: HDF5
}
label_select_param {
balance: true
num_labels: 2
num_top_label_balance: 2
reorder_label: false
class_prob_mapping_file: "label_class_selection.prototxt"
}
}
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data"
top: "conv1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
pad: 1
pad: 1
pad: 1
kernel_size: 3
kernel_size: 3
kernel_size: 3
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv1_1"
type: "BatchNorm"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "scale_conv1_1"
type: "Scale"
bottom: "conv1_1"
top: "conv1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu1_1"
type: "ReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "conv1_2"
type: "Convolution"
bottom: "conv1_1"
top: "conv1_2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 1
pad: 1
pad: 0
kernel_size: 3
kernel_size: 3
kernel_size: 3
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv1_2"
type: "BatchNorm"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "scale_conv1_2"
type: "Scale"
bottom: "conv1_2"
top: "conv1_2"
scale_param {
bias_term: true
}
}
layer {
name: "relu1_2"
type: "ReLU"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "reshape"
type: "Reshape"
bottom: "conv1_2"
top: "conv1_2"
reshape_param {
shape {
dim: 0
dim: 0
dim: 0
dim: 0
}
}
}
layer {
name: "reshape"
type: "Reshape"
bottom: "label"
top: "label"
reshape_param {
shape {
dim: 0
dim: 0
dim: 0
dim: 0
}
}
}
layer {
name: "conv2_1b"
type: "Convolution"
bottom: "conv1_2"
top: "conv2_1b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_1b"
type: "BatchNorm"
bottom: "conv2_1b"
top: "conv2_1b"
}
layer {
name: "scale_conv2_1b"
type: "Scale"
bottom: "conv2_1b"
top: "conv2_1b"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_1b"
type: "ReLU"
bottom: "conv2_1b"
top: "conv2_1b"
}
layer {
name: "conv2_1b_3x3"
type: "Convolution"
bottom: "conv2_1b"
top: "conv2_1b_3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 96
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_1b_3x3"
type: "BatchNorm"
bottom: "conv2_1b_3x3"
top: "conv2_1b_3x3"
}
layer {
name: "scale_conv2_1b_3x3"
type: "Scale"
bottom: "conv2_1b_3x3"
top: "conv2_1b_3x3"
scale_param {
bias_term: true
}
}
layer {
name: "conv2_1x1"
type: "Convolution"
bottom: "conv1_2"
top: "conv2_1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_1x1"
type: "BatchNorm"
bottom: "conv2_1x1"
top: "conv2_1x1"
}
layer {
name: "scale_conv2_1x1"
type: "Scale"
bottom: "conv2_1x1"
top: "conv2_1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_1x1"
type: "ReLU"
bottom: "conv2_1x1"
top: "conv2_1x1"
}
layer {
name: "conv2_1x7"
type: "Convolution"
bottom: "conv2_1x1"
top: "conv2_1x7"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 3
pad_w: 0
kernel_h: 7
kernel_w: 1
}
}
layer {
name: "bn_conv2_1x7"
type: "BatchNorm"
bottom: "conv2_1x7"
top: "conv2_1x7"
}
layer {
name: "scale_conv2_1x7"
type: "Scale"
bottom: "conv2_1x7"
top: "conv2_1x7"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_1x7"
type: "ReLU"
bottom: "conv2_1x7"
top: "conv2_1x7"
}
layer {
name: "conv2_7x1"
type: "Convolution"
bottom: "conv2_1x7"
top: "conv2_7x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 0
pad_w: 3
kernel_h: 1
kernel_w: 7
}
}
layer {
name: "bn_conv2_7x1"
type: "BatchNorm"
bottom: "conv2_7x1"
top: "conv2_7x1"
}
layer {
name: "scale_conv2_7x1"
type: "Scale"
bottom: "conv2_7x1"
top: "conv2_7x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_7x1"
type: "ReLU"
bottom: "conv2_7x1"
top: "conv2_7x1"
}
layer {
name: "conv2_3x3"
type: "Convolution"
bottom: "conv2_7x1"
top: "conv2_3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 96
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_3x3"
type: "BatchNorm"
bottom: "conv2_3x3"
top: "conv2_3x3"
}
layer {
name: "scale_conv2_3x3"
type: "Scale"
bottom: "conv2_3x3"
top: "conv2_3x3"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_3x3"
type: "ReLU"
bottom: "conv2_3x3"
top: "conv2_3x3"
}
layer {
name: "concat_stem_1"
type: "Concat"
bottom: "conv2_1b_3x3"
bottom: "conv2_3x3"
top: "concat_stem_1"
}
layer {
name: "stem_concat_conv_3x3"
type: "Convolution"
bottom: "concat_stem_1"
top: "stem_concat_conv_3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 192
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_stem_concat_conv_3x3"
type: "BatchNorm"
bottom: "stem_concat_conv_3x3"
top: "stem_concat_conv_3x3"
}
layer {
name: "scale_stem_concat_conv_3x3"
type: "Scale"
bottom: "stem_concat_conv_3x3"
top: "stem_concat_conv_3x3"
scale_param {
bias_term: true
}
}
layer {
name: "relu_stem_concat_conv_3x3"
type: "ReLU"
bottom: "stem_concat_conv_3x3"
top: "stem_concat_conv_3x3"
}
layer {
name: "pool_stem_concat"
type: "Pooling"
bottom: "concat_stem_1"
top: "pool_stem_concat"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "concat_stem_2"
type: "Concat"
bottom: "pool_stem_concat"
bottom: "stem_concat_conv_3x3"
top: "concat_stem_2"
}
layer {
name: "conv3_1b"
type: "Convolution"
bottom: "concat_stem_2"
top: "conv3_1b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv3_1b"
type: "BatchNorm"
bottom: "conv3_1b"
top: "conv3_1b"
}
layer {
name: "scale_conv3_1b"
type: "Scale"
bottom: "conv3_1b"
top: "conv3_1b"
scale_param {
bias_term: true
}
}
layer {
name: "relu3_1b"
type: "ReLU"
bottom: "conv3_1b"
top: "conv3_1b"
}
layer {
name: "ira_A_1_conv1x1"
type: "Convolution"
bottom: "conv3_1b"
top: "ira_A_1_conv1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_1_conv1x1"
type: "BatchNorm"
bottom: "ira_A_1_conv1x1"
top: "ira_A_1_conv1x1"
}
layer {
name: "scale_ira_A_1_conv1x1"
type: "Scale"
bottom: "ira_A_1_conv1x1"
top: "ira_A_1_conv1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_1_conv1x1"
type: "ReLU"
bottom: "ira_A_1_conv1x1"
top: "ira_A_1_conv1x1"
}
layer {
name: "ira_A_2_conv1x1"
type: "Convolution"
bottom: "conv3_1b"
top: "ira_A_2_conv1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_2_conv1x1"
type: "BatchNorm"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv1x1"
}
layer {
name: "scale_ira_A_2_conv1x1"
type: "Scale"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_2_conv1x1"
type: "ReLU"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv1x1"
}
layer {
name: "ira_A_2_conv3x3"
type: "Convolution"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_2_conv3x3"
type: "BatchNorm"
bottom: "ira_A_2_conv3x3"
top: "ira_A_2_conv3x3"
}
layer {
name: "scale_ira_A_2_conv3x3"
type: "Scale"
bottom: "ira_A_2_conv3x3"
top: "ira_A_2_conv3x3"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_2_conv3x3"
type: "ReLU"
bottom: "ira_A_2_conv3x3"
top: "ira_A_2_conv3x3"
}
layer {
name: "ira_A_3_conv1x1"
type: "Convolution"
bottom: "conv3_1b"
top: "ira_A_3_conv1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_3_conv1x1"
type: "BatchNorm"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv1x1"
}
layer {
name: "scale_ira_A_3_conv1x1"
type: "Scale"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_3_conv1x1"
type: "ReLU"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv1x1"
}
layer {
name: "ira_A_3_conv3x3_1"
type: "Convolution"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 48
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_3_conv3x3_1"
type: "BatchNorm"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_1"
}
layer {
name: "scale_ira_A_3_conv3x3_1"
type: "Scale"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_3_conv3x3_1"
type: "ReLU"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_1"
}
layer {
name: "ira_A_3_conv3x3_2"
type: "Convolution"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_3_conv3x3_2"
type: "BatchNorm"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_3_conv3x3_2"
}
layer {
name: "scale_ira_A_3_conv3x3_2"
type: "Scale"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_3_conv3x3_2"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_3_conv3x3_2"
type: "ReLU"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_3_conv3x3_2"
}
layer {
name: "ira_A_concat"
type: "Concat"
bottom: "ira_A_1_conv1x1"
bottom: "ira_A_2_conv3x3"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_concat"
}
layer {
name: "ira_A_concat_top_conv_1x1"
type: "Convolution"
bottom: "ira_A_concat"
top: "ira_A_concat_top_conv_1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ra_A_concat_top_conv_1x1"
type: "BatchNorm"
bottom: "ira_A_concat_top_conv_1x1"
top: "ira_A_concat_top_conv_1x1"
}
layer {
name: "scale_ra_A_concat_top_conv_1x1"
type: "Scale"
bottom: "ira_A_concat_top_conv_1x1"
top: "ira_A_concat_top_conv_1x1"
scale_param {
bias_term: true
}
}
layer {
name: "conv3_sum"
type: "Eltwise"
bottom: "conv3_1b"
bottom: "ira_A_concat_top_conv_1x1"
top: "conv3_sum"
eltwise_param {
operation: SUM
coeff: 1
coeff: 0.1
}
}
layer {
name: "relu3_sum"
type: "ReLU"
bottom: "conv3_sum"
top: "conv3_sum"
}
layer {
name: "ira_v4_reduction_A/pool"
type: "Pooling"
bottom: "conv3_sum"
top: "ira_v4_reduction_A/pool"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "ira_v4_reduction_A/conv3x3_reduction_b"
type: "Convolution"
bottom: "conv3_sum"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv3x3_reduction_b"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
}
layer {
name: "scale_ira_v4_reduction_A/conv3x3_reduction_b"
type: "Scale"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv3x3_reduction_b"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
}
layer {
name: "ira_v4_reduction_A/conv1x1_c"
type: "Convolution"
bottom: "conv3_sum"
top: "ira_v4_reduction_A/conv1x1_c"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv1x1_c"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv1x1_c"
}
layer {
name: "scale_ira_v4_reduction_A/conv1x1_c"
type: "Scale"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv1x1_c"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv1x1_c"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv1x1_c"
}
layer {
name: "ira_v4_reduction_A/conv3x3_c"
type: "Convolution"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv3x3_c"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv3x3_c"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_c"
}
layer {
name: "scale_ira_v4_reduction_A/conv3x3_c"
type: "Scale"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_c"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv3x3_c"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_c"
}
layer {
name: "ira_v4_reduction_A/conv3x3_reduction_c"
type: "Convolution"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv3x3_reduction_c"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
}
layer {
name: "scale_ira_v4_reduction_A/conv3x3_reduction_c"
type: "Scale"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv3x3_reduction_c"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
}
layer {
name: "ira_v4_reduction_A/concat"
type: "Concat"
bottom: "ira_v4_reduction_A/pool"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/concat"
}
layer {
name: "conv4_1b"
type: "Convolution"
bottom: "ira_v4_reduction_A/concat"
top: "conv4_1b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 1154
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv4_1b"
type: "BatchNorm"
bottom: "conv4_1b"
top: "conv4_1b"
}
layer {
name: "scale_conv4_1b"
type: "Scale"
bottom: "conv4_1b"
top: "conv4_1b"
scale_param {
bias_term: true
}
}
layer {
name: "relu4_1b"
type: "ReLU"
bottom: "conv4_1b"
top: "conv4_1b"
}
layer {
name: "ira_Inception_B_block_1/a_conv1x1_1"
type: "Convolution"
bottom: "conv4_1b"
top: "ira_Inception_B_block_1/a_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 192
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Inception_B_block_1/a_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
top: "ira_Inception_B_block_1/a_conv1x1_1"
}
layer {
name: "scale_ira_Inception_B_block_1/a_conv1x1_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
top: "ira_Inception_B_block_1/a_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/a_conv1x1_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
top: "ira_Inception_B_block_1/a_conv1x1_1"
}
layer {
name: "ira_Inception_B_block_1/b_conv1x1_1"
type: "Convolution"
bottom: "conv4_1b"
top: "ira_Inception_B_block_1/b_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 128
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Inception_B_block_1/b_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x1_1"
}
layer {
name: "scale_ira_Inception_B_block_1/b_conv1x1_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/b_conv1x1_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x1_1"
}
layer {
name: "ira_Inception_B_block_1/b_conv1x7_1"
type: "Convolution"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 160
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 0
pad_w: 3
kernel_h: 1
kernel_w: 7
}
}
layer {
name: "bn_ira_Inception_B_block_1/b_conv1x7_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
}
layer {
name: "scale_ira_Inception_B_block_1/b_conv1x7_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/b_conv1x7_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
}
layer {
name: "ira_Inception_B_block_1/b_conv7x1_1"
type: "Convolution"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 192
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 3
pad_w: 0
kernel_h: 7
kernel_w: 1
}
}
layer {
name: "bn_ira_Inception_B_block_1/b_conv7x1_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
}
layer {
name: "scale_ira_Inception_B_block_1/b_conv7x1_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/b_conv7x1_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
}
layer {
name: "ira_Inception_B_block_1/concat"
type: "Concat"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/concat"
}
layer {
name: "ira_Inception_B_block_1/top_conv_1x1"
type: "Convolution"
bottom: "ira_Inception_B_block_1/concat"
top: "ira_Inception_B_block_1/top_conv_1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 1154
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Inception_B_block_1/top_conv_1x1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/top_conv_1x1"
top: "ira_Inception_B_block_1/top_conv_1x1"
}
layer {
name: "scale_ira_Inception_B_block_1/top_conv_1x1"
type: "Scale"
bottom: "ira_Inception_B_block_1/top_conv_1x1"
top: "ira_Inception_B_block_1/top_conv_1x1"
scale_param {
bias_term: true
}
}
layer {
name: "conv4_sum"
type: "Eltwise"
bottom: "conv4_1b"
bottom: "ira_Inception_B_block_1/top_conv_1x1"
top: "conv4_sum"
eltwise_param {
operation: SUM
coeff: 1
coeff: 0.1
}
}
layer {
name: "relu_conv4_sum"
type: "ReLU"
bottom: "conv4_sum"
top: "conv4_sum"
}
layer {
name: "ira_Reduction_B_block_1/a_pool"
type: "Pooling"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/a_pool"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "ira_Reduction_B_block_1/b_conv1x1_1"
type: "Convolution"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/b_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/b_conv1x1_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/b_conv1x1_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
}
layer {
name: "ira_Reduction_B_block_1/b_conv3x3_1"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/b_conv3x3_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/b_conv3x3_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/b_conv3x3_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/b_conv3x3_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/b_conv3x3_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/b_conv3x3_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
}
layer {
name: "ira_Reduction_B_block_1/c_conv1x1_1"
type: "Convolution"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/c_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/c_conv1x1_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/c_conv1x1_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
}
layer {
name: "ira_Reduction_B_block_1/c_conv3x3_1"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 288
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/c_conv3x3_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/c_conv3x3_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/c_conv3x3_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/c_conv3x3_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/c_conv3x3_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/c_conv3x3_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
}
layer {
name: "ira_Reduction_B_block_1/d_conv1x1_1"
type: "Convolution"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/d_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/d_conv1x1_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/d_conv1x1_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
}
layer {
name: "ira_Reduction_B_block_1/d_conv3x3_1"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 288
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/d_conv3x3_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/d_conv3x3_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/d_conv3x3_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/d_conv3x3_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/d_conv3x3_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/d_conv3x3_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
}
layer {
name: "ira_Reduction_B_block_1/d_conv3x3_2"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/d_c
I0605 22:59:54.867182 54715 layer_factory.hpp:77] Creating layer data
I0605 22:59:54.867233 54715 data_provider.cpp:28] Loading list of HDF5 filenames from: /home/ubuntu/membraneTraining_SEMTEM/train_file.txt
I0605 22:59:54.867265 54715 data_provider.cpp:42] Number of HDF5 files: 16
I0605 22:59:59.064508 54715 sample_selector.cpp:58] read prob from file : label_class_selection.prototxt
I0605 22:59:59.064602 54715 sample_selector.cpp:78] rest_of_label_mapping_ = 0 1
I0605 22:59:59.064622 54715 sample_selector.cpp:93] label map :0--->0
I0605 22:59:59.064627 54715 sample_selector.cpp:93] label map :1--->1
I0605 22:59:59.064632 54715 sample_selector.cpp:95] label_prob_map_ size =2
I0605 22:59:59.064648 54715 sample_selector.cpp:116] scale_factor = 3.33333
I0605 22:59:59.064666 54715 sample_selector.cpp:117] bottom_prob = 0.3
I0605 22:59:59.064672 54715 sample_selector.cpp:118] label_prob_vec.size = 2
I0605 22:59:59.064677 54715 sample_selector.cpp:164] size of prob = 1
I0605 22:59:59.064692 54715 sample_selector.cpp:19] lable class [0] weight =0.25
I0605 22:59:59.064698 54715 sample_selector.cpp:19] lable class [1] weight =1
I0605 22:59:59.064790 54715 patch_sampler.cpp:57] runner setup done ... count =0
I0605 22:59:59.064812 54715 net.cpp:106] Creating Layer data
I0605 22:59:59.064823 54715 net.cpp:411] data -> data
I0605 22:59:59.064855 54715 net.cpp:411] data -> label
I0605 22:59:59.064960 54715 patch_sampler.cpp:121] loading batch patch_count = 0
I0605 22:59:59.065886 54715 hdf5.cpp:32] Datatype class: H5T_FLOAT
I0605 22:59:59.227720 54766 patch_sampler.cpp:315] phase =train and solover_count =1
I0605 22:59:59.227761 54766 patch_sampler.cpp:319] solver_count = 1 size of queue pairs = 1
I0605 22:59:59.227767 54766 patch_sampler.cpp:323] size of queue is now = 0
I0605 22:59:59.783180 54715 data_provider.cpp:108] d_size =3
I0605 22:59:59.783231 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 22:59:59.783237 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 22:59:59.783241 54715 data_provider.cpp:111] loaded data shape : 100
I0605 22:59:59.783246 54715 data_provider.cpp:113]
I0605 22:59:59.783248 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 22:59:59.783253 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 22:59:59.783257 54715 data_provider.cpp:115] loaded label shape : 100
I0605 22:59:59.783373 54715 data_provider.cpp:144] d_size =5
I0605 22:59:59.783381 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 22:59:59.783385 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 22:59:59.783390 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 22:59:59.783393 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 22:59:59.783396 54715 data_provider.cpp:147] data shape after prependig : 100
I0605 22:59:59.783401 54715 data_provider.cpp:149]
I0605 22:59:59.783406 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 22:59:59.783409 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 22:59:59.783412 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 22:59:59.783417 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 22:59:59.783421 54715 data_provider.cpp:151] label shape after prependig : 100
I0605 22:59:59.783424 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v13.h5
I0605 22:59:59.928299 54715 data_provider.cpp:108] d_size =3
I0605 22:59:59.928335 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 22:59:59.928340 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 22:59:59.928344 54715 data_provider.cpp:111] loaded data shape : 20
I0605 22:59:59.928349 54715 data_provider.cpp:113]
I0605 22:59:59.928352 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 22:59:59.928356 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 22:59:59.928360 54715 data_provider.cpp:115] loaded label shape : 20
I0605 22:59:59.928468 54715 data_provider.cpp:144] d_size =5
I0605 22:59:59.928475 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 22:59:59.928479 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 22:59:59.928483 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 22:59:59.928486 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 22:59:59.928491 54715 data_provider.cpp:147] data shape after prependig : 20
I0605 22:59:59.928495 54715 data_provider.cpp:149]
I0605 22:59:59.928498 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 22:59:59.928503 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 22:59:59.928506 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 22:59:59.928510 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 22:59:59.928514 54715 data_provider.cpp:151] label shape after prependig : 20
I0605 22:59:59.928517 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v4.h5
I0605 23:00:00.079970 54715 data_provider.cpp:108] d_size =3
I0605 23:00:00.080003 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.080008 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.080013 54715 data_provider.cpp:111] loaded data shape : 21
I0605 23:00:00.080016 54715 data_provider.cpp:113]
I0605 23:00:00.080020 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.080024 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.080027 54715 data_provider.cpp:115] loaded label shape : 21
I0605 23:00:00.080157 54715 data_provider.cpp:144] d_size =5
I0605 23:00:00.080166 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.080170 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.080184 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.080199 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.080202 54715 data_provider.cpp:147] data shape after prependig : 21
I0605 23:00:00.080206 54715 data_provider.cpp:149]
I0605 23:00:00.080209 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.080214 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.080219 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.080221 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.080225 54715 data_provider.cpp:151] label shape after prependig : 21
I0605 23:00:00.080229 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v5.h5
I0605 23:00:00.225827 54715 data_provider.cpp:108] d_size =3
I0605 23:00:00.225862 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.225867 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.225872 54715 data_provider.cpp:111] loaded data shape : 20
I0605 23:00:00.225877 54715 data_provider.cpp:113]
I0605 23:00:00.225879 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.225883 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.225888 54715 data_provider.cpp:115] loaded label shape : 20
I0605 23:00:00.226001 54715 data_provider.cpp:144] d_size =5
I0605 23:00:00.226008 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.226011 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.226016 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.226019 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.226023 54715 data_provider.cpp:147] data shape after prependig : 20
I0605 23:00:00.226027 54715 data_provider.cpp:149]
I0605 23:00:00.226032 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.226035 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.226038 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.226042 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.226047 54715 data_provider.cpp:151] label shape after prependig : 20
I0605 23:00:00.226050 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v9.h5
I0605 23:00:00.377504 54715 data_provider.cpp:108] d_size =3
I0605 23:00:00.377538 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.377544 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.377548 54715 data_provider.cpp:111] loaded data shape : 21
I0605 23:00:00.377552 54715 data_provider.cpp:113]
I0605 23:00:00.377555 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.377559 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.377563 54715 data_provider.cpp:115] loaded label shape : 21
I0605 23:00:00.377674 54715 data_provider.cpp:144] d_size =5
I0605 23:00:00.377681 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.377686 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.377688 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.377692 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.377696 54715 data_provider.cpp:147] data shape after prependig : 21
I0605 23:00:00.377701 54715 data_provider.cpp:149]
I0605 23:00:00.377703 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.377707 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.377710 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.377715 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.377718 54715 data_provider.cpp:151] label shape after prependig : 21
I0605 23:00:00.377733 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v8.h5
I0605 23:00:00.531622 54715 data_provider.cpp:108] d_size =3
I0605 23:00:00.531661 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.531664 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:00.531668 54715 data_provider.cpp:111] loaded data shape : 21
I0605 23:00:00.531672 54715 data_provider.cpp:113]
I0605 23:00:00.531677 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.531680 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:00.531683 54715 data_provider.cpp:115] loaded label shape : 21
I0605 23:00:00.531800 54715 data_provider.cpp:144] d_size =5
I0605 23:00:00.531806 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.531810 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:00.531814 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.531817 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:00.531822 54715 data_provider.cpp:147] data shape after prependig : 21
I0605 23:00:00.531826 54715 data_provider.cpp:149]
I0605 23:00:00.531829 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.531833 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:00.531837 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.531841 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:00.531844 54715 data_provider.cpp:151] label shape after prependig : 21
I0605 23:00:00.531847 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v14.h5
I0605 23:00:01.248548 54715 data_provider.cpp:108] d_size =3
I0605 23:00:01.248585 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:01.248590 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:01.248594 54715 data_provider.cpp:111] loaded data shape : 100
I0605 23:00:01.248598 54715 data_provider.cpp:113]
I0605 23:00:01.248601 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:01.248605 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:01.248610 54715 data_provider.cpp:115] loaded label shape : 100
I0605 23:00:01.248721 54715 data_provider.cpp:144] d_size =5
I0605 23:00:01.248728 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:01.248731 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:01.248735 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:01.248740 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:01.248744 54715 data_provider.cpp:147] data shape after prependig : 100
I0605 23:00:01.248747 54715 data_provider.cpp:149]
I0605 23:00:01.248750 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:01.248755 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:01.248759 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:01.248762 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:01.248765 54715 data_provider.cpp:151] label shape after prependig : 100
I0605 23:00:01.248770 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v7.h5
I0605 23:00:01.308517 54715 data_provider.cpp:108] d_size =3
I0605 23:00:01.308554 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:01.308559 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:01.308564 54715 data_provider.cpp:111] loaded data shape : 8
I0605 23:00:01.308568 54715 data_provider.cpp:113]
I0605 23:00:01.308571 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:01.308574 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:01.308579 54715 data_provider.cpp:115] loaded label shape : 8
I0605 23:00:01.308691 54715 data_provider.cpp:144] d_size =5
I0605 23:00:01.308698 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:01.308719 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:01.308724 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:01.308728 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:01.308732 54715 data_provider.cpp:147] data shape after prependig : 8
I0605 23:00:01.308734 54715 data_provider.cpp:149]
I0605 23:00:01.308739 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:01.308743 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:01.308746 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:01.308749 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:01.308754 54715 data_provider.cpp:151] label shape after prependig : 8
I0605 23:00:01.308758 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v10.h5
I0605 23:00:01.369343 54715 data_provider.cpp:108] d_size =3
I0605 23:00:01.369379 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:01.369385 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:01.369390 54715 data_provider.cpp:111] loaded data shape : 8
I0605 23:00:01.369392 54715 data_provider.cpp:113]
I0605 23:00:01.369396 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:01.369400 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:01.369405 54715 data_provider.cpp:115] loaded label shape : 8
I0605 23:00:01.369518 54715 data_provider.cpp:144] d_size =5
I0605 23:00:01.369524 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:01.369529 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:01.369531 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:01.369535 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:01.369539 54715 data_provider.cpp:147] data shape after prependig : 8
I0605 23:00:01.369544 54715 data_provider.cpp:149]
I0605 23:00:01.369547 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:01.369550 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:01.369554 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:01.369559 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:01.369562 54715 data_provider.cpp:151] label shape after prependig : 8
I0605 23:00:01.369565 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v15.h5
I0605 23:00:02.096803 54715 data_provider.cpp:108] d_size =3
I0605 23:00:02.096840 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:02.096845 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:02.096849 54715 data_provider.cpp:111] loaded data shape : 100
I0605 23:00:02.096853 54715 data_provider.cpp:113]
I0605 23:00:02.096858 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:02.096863 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:02.096865 54715 data_provider.cpp:115] loaded label shape : 100
I0605 23:00:02.096979 54715 data_provider.cpp:144] d_size =5
I0605 23:00:02.096987 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:02.096990 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:02.096994 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:02.096997 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:02.097002 54715 data_provider.cpp:147] data shape after prependig : 100
I0605 23:00:02.097005 54715 data_provider.cpp:149]
I0605 23:00:02.097009 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:02.097013 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:02.097018 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:02.097021 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:02.097034 54715 data_provider.cpp:151] label shape after prependig : 100
I0605 23:00:02.097045 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v3.h5
I0605 23:00:02.326133 54715 data_provider.cpp:108] d_size =3
I0605 23:00:02.326171 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:02.326176 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:02.326180 54715 data_provider.cpp:111] loaded data shape : 20
I0605 23:00:02.326184 54715 data_provider.cpp:113]
I0605 23:00:02.326189 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:02.326191 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:02.326195 54715 data_provider.cpp:115] loaded label shape : 20
I0605 23:00:02.326313 54715 data_provider.cpp:144] d_size =5
I0605 23:00:02.326318 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:02.326323 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:02.326325 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:02.326330 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:02.326334 54715 data_provider.cpp:147] data shape after prependig : 20
I0605 23:00:02.326337 54715 data_provider.cpp:149]
I0605 23:00:02.326341 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:02.326345 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:02.326349 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:02.326352 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:02.326356 54715 data_provider.cpp:151] label shape after prependig : 20
I0605 23:00:02.326361 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v12.h5
I0605 23:00:03.043710 54715 data_provider.cpp:108] d_size =3
I0605 23:00:03.043750 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:03.043754 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:03.043759 54715 data_provider.cpp:111] loaded data shape : 100
I0605 23:00:03.043762 54715 data_provider.cpp:113]
I0605 23:00:03.043766 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:03.043769 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:03.043774 54715 data_provider.cpp:115] loaded label shape : 100
I0605 23:00:03.043889 54715 data_provider.cpp:144] d_size =5
I0605 23:00:03.043896 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:03.043900 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:03.043905 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:03.043908 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:03.043911 54715 data_provider.cpp:147] data shape after prependig : 100
I0605 23:00:03.043915 54715 data_provider.cpp:149]
I0605 23:00:03.043920 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:03.043923 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:03.043926 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:03.043931 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:03.043934 54715 data_provider.cpp:151] label shape after prependig : 100
I0605 23:00:03.043938 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v16.h5
I0605 23:00:03.187278 54715 data_provider.cpp:108] d_size =3
I0605 23:00:03.187312 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:03.187319 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:03.187321 54715 data_provider.cpp:111] loaded data shape : 20
I0605 23:00:03.187325 54715 data_provider.cpp:113]
I0605 23:00:03.187330 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:03.187333 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:03.187337 54715 data_provider.cpp:115] loaded label shape : 20
I0605 23:00:03.187461 54715 data_provider.cpp:144] d_size =5
I0605 23:00:03.187476 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:03.187481 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:03.187484 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:03.187489 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:03.187491 54715 data_provider.cpp:147] data shape after prependig : 20
I0605 23:00:03.187495 54715 data_provider.cpp:149]
I0605 23:00:03.187500 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:03.187502 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:03.187505 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:03.187510 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:03.187513 54715 data_provider.cpp:151] label shape after prependig : 20
I0605 23:00:03.187517 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v2.h5
I0605 23:00:03.333523 54715 data_provider.cpp:108] d_size =3
I0605 23:00:03.333564 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:03.333567 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:03.333571 54715 data_provider.cpp:111] loaded data shape : 20
I0605 23:00:03.333575 54715 data_provider.cpp:113]
I0605 23:00:03.333580 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:03.333583 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:03.333587 54715 data_provider.cpp:115] loaded label shape : 20
I0605 23:00:03.333703 54715 data_provider.cpp:144] d_size =5
I0605 23:00:03.333710 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:03.333714 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:03.333717 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:03.333721 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:03.333725 54715 data_provider.cpp:147] data shape after prependig : 20
I0605 23:00:03.333729 54715 data_provider.cpp:149]
I0605 23:00:03.333734 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:03.333736 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:03.333741 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:03.333745 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:03.333748 54715 data_provider.cpp:151] label shape after prependig : 20
I0605 23:00:03.333752 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v11.h5
I0605 23:00:04.041816 54715 data_provider.cpp:108] d_size =3
I0605 23:00:04.041851 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:04.041857 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:04.041859 54715 data_provider.cpp:111] loaded data shape : 100
I0605 23:00:04.041864 54715 data_provider.cpp:113]
I0605 23:00:04.041868 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:04.041872 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:04.041875 54715 data_provider.cpp:115] loaded label shape : 100
I0605 23:00:04.041988 54715 data_provider.cpp:144] d_size =5
I0605 23:00:04.041995 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:04.041998 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:04.042001 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:04.042006 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:04.042009 54715 data_provider.cpp:147] data shape after prependig : 100
I0605 23:00:04.042013 54715 data_provider.cpp:149]
I0605 23:00:04.042017 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:04.042021 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:04.042026 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:04.042045 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:04.042049 54715 data_provider.cpp:151] label shape after prependig : 100
I0605 23:00:04.042054 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v1.h5
I0605 23:00:04.098595 54715 data_provider.cpp:108] d_size =3
I0605 23:00:04.098629 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:04.098634 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:04.098639 54715 data_provider.cpp:111] loaded data shape : 8
I0605 23:00:04.098642 54715 data_provider.cpp:113]
I0605 23:00:04.098646 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:04.098649 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:04.098654 54715 data_provider.cpp:115] loaded label shape : 8
I0605 23:00:04.098765 54715 data_provider.cpp:144] d_size =5
I0605 23:00:04.098772 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:04.098775 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:04.098779 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:04.098783 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:04.098788 54715 data_provider.cpp:147] data shape after prependig : 8
I0605 23:00:04.098790 54715 data_provider.cpp:149]
I0605 23:00:04.098795 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:04.098798 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:04.098803 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:04.098805 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:04.098810 54715 data_provider.cpp:151] label shape after prependig : 8
I0605 23:00:04.098814 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v6.h5
I0605 23:00:04.125149 54715 patch_data_layer.cpp:43] reshape top data = 5
I0605 23:00:04.125180 54715 patch_data_layer.cpp:43] reshape top data = 1
I0605 23:00:04.125185 54715 patch_data_layer.cpp:43] reshape top data = 320
I0605 23:00:04.125190 54715 patch_data_layer.cpp:43] reshape top data = 320
I0605 23:00:04.125192 54715 patch_data_layer.cpp:43] reshape top data = 5
I0605 23:00:04.126579 54715 patch_data_layer.cpp:48] reshape prefetch_[0].data_
I0605 23:00:04.126600 54715 patch_data_layer.cpp:48] reshape prefetch_[1].data_
I0605 23:00:04.126617 54715 patch_data_layer.cpp:48] reshape prefetch_[2].data_
I0605 23:00:04.126624 54715 patch_data_layer.cpp:57] reshape top label = 5
I0605 23:00:04.126628 54715 patch_data_layer.cpp:57] reshape top label = 1
I0605 23:00:04.126633 54715 patch_data_layer.cpp:57] reshape top label = 320
I0605 23:00:04.126636 54715 patch_data_layer.cpp:57] reshape top label = 320
I0605 23:00:04.126641 54715 patch_data_layer.cpp:57] reshape top label = 1
I0605 23:00:04.152034 54715 net.cpp:150] Setting up data
I0605 23:00:04.152074 54715 net.cpp:157] Top shape: 5 1 320 320 5 (2560000)
I0605 23:00:04.152082 54715 net.cpp:157] Top shape: 5 1 320 320 1 (512000)
I0605 23:00:04.152086 54715 net.cpp:165] Memory required for data: 12288000
I0605 23:00:04.152096 54715 layer_factory.hpp:77] Creating layer conv1_1
I0605 23:00:04.152118 54715 net.cpp:106] Creating Layer conv1_1
I0605 23:00:04.152125 54715 net.cpp:454] conv1_1 <- data
I0605 23:00:04.152155 54715 net.cpp:411] conv1_1 -> conv1_1
I0605 23:00:04.155110 54715 net.cpp:150] Setting up conv1_1
I0605 23:00:04.155128 54715 net.cpp:157] Top shape: 5 32 160 160 3 (12288000)
I0605 23:00:04.155133 54715 net.cpp:165] Memory required for data: 61440000
I0605 23:00:04.155155 54715 layer_factory.hpp:77] Creating layer bn_conv1_1
I0605 23:00:04.155166 54715 net.cpp:106] Creating Layer bn_conv1_1
I0605 23:00:04.155171 54715 net.cpp:454] bn_conv1_1 <- conv1_1
I0605 23:00:04.155179 54715 net.cpp:397] bn_conv1_1 -> conv1_1 (in-place)
I0605 23:00:04.155516 54715 net.cpp:150] Setting up bn_conv1_1
I0605 23:00:04.155535 54715 net.cpp:157] Top shape: 5 32 160 160 3 (12288000)
I0605 23:00:04.155549 54715 net.cpp:165] Memory required for data: 110592000
I0605 23:00:04.155561 54715 layer_factory.hpp:77] Creating layer scale_conv1_1
I0605 23:00:04.155570 54715 net.cpp:106] Creating Layer scale_conv1_1
I0605 23:00:04.155575 54715 net.cpp:454] scale_conv1_1 <- conv1_1
I0605 23:00:04.155581 54715 net.cpp:397] scale_conv1_1 -> conv1_1 (in-place)
I0605 23:00:04.155624 54715 layer_factory.hpp:77] Creating layer scale_conv1_1
I0605 23:00:04.155906 54715 net.cpp:150] Setting up scale_conv1_1
I0605 23:00:04.155915 54715 net.cpp:157] Top shape: 5 32 160 160 3 (12288000)
I0605 23:00:04.155920 54715 net.cpp:165] Memory required for data: 159744000
I0605 23:00:04.155927 54715 layer_factory.hpp:77] Creating layer relu1_1
I0605 23:00:04.155936 54715 net.cpp:106] Creating Layer relu1_1
I0605 23:00:04.155939 54715 net.cpp:454] relu1_1 <- conv1_1
I0605 23:00:04.155946 54715 net.cpp:397] relu1_1 -> conv1_1 (in-place)
I0605 23:00:04.155953 54715 net.cpp:150] Setting up relu1_1
I0605 23:00:04.155958 54715 net.cpp:157] Top shape: 5 32 160 160 3 (12288000)
I0605 23:00:04.155962 54715 net.cpp:165] Memory required for data: 208896000
I0605 23:00:04.155966 54715 layer_factory.hpp:77] Creating layer conv1_2
I0605 23:00:04.155975 54715 net.cpp:106] Creating Layer conv1_2
I0605 23:00:04.155979 54715 net.cpp:454] conv1_2 <- conv1_1
I0605 23:00:04.155987 54715 net.cpp:411] conv1_2 -> conv1_2
I0605 23:00:04.159015 54715 net.cpp:150] Setting up conv1_2
I0605 23:00:04.159036 54715 net.cpp:157] Top shape: 5 64 160 160 1 (8192000)
I0605 23:00:04.159041 54715 net.cpp:165] Memory required for data: 241664000
I0605 23:00:04.159052 54715 layer_factory.hpp:77] Creating layer bn_conv1_2
I0605 23:00:04.159062 54715 net.cpp:106] Creating Layer bn_conv1_2
I0605 23:00:04.159067 54715 net.cpp:454] bn_conv1_2 <- conv1_2
I0605 23:00:04.159075 54715 net.cpp:397] bn_conv1_2 -> conv1_2 (in-place)
I0605 23:00:04.159495 54715 net.cpp:150] Setting up bn_conv1_2
I0605 23:00:04.159507 54715 net.cpp:157] Top shape: 5 64 160 160 1 (8192000)
I0605 23:00:04.159510 54715 net.cpp:165] Memory required for data: 274432000
I0605 23:00:04.159519 54715 layer_factory.hpp:77] Creating layer scale_conv1_2
I0605 23:00:04.159528 54715 net.cpp:106] Creating Layer scale_conv1_2
I0605 23:00:04.159533 54715 net.cpp:454] scale_conv1_2 <- conv1_2
I0605 23:00:04.159538 54715 net.cpp:397] scale_conv1_2 -> conv1_2 (in-place)
I0605 23:00:04.159576 54715 layer_factory.hpp:77] Creating layer scale_conv1_2
I0605 23:00:04.159708 54715 net.cpp:150] Setting up scale_conv1_2
I0605 23:00:04.159719 54715 net.cpp:157] Top shape: 5 64 160 160 1 (8192000)
I0605 23:00:04.159723 54715 net.cpp:165] Memory required for data: 307200000
I0605 23:00:04.159729 54715 layer_factory.hpp:77] Creating layer relu1_2
I0605 23:00:04.159739 54715 net.cpp:106] Creating Layer relu1_2
I0605 23:00:04.159744 54715 net.cpp:454] relu1_2 <- conv1_2
I0605 23:00:04.159749 54715 net.cpp:397] relu1_2 -> conv1_2 (in-place)
I0605 23:00:04.159755 54715 net.cpp:150] Setting up relu1_2
I0605 23:00:04.159761 54715 net.cpp:157] Top shape: 5 64 160 160 1 (8192000)
I0605 23:00:04.159766 54715 net.cpp:165] Memory required for data: 339968000
I0605 23:00:04.159770 54715 layer_factory.hpp:77] Creating layer reshape
I0605 23:00:04.159778 54715 net.cpp:106] Creating Layer reshape
I0605 23:00:04.159782 54715 net.cpp:454] reshape <- conv1_2
I0605 23:00:04.159788 54715 net.cpp:397] reshape -> conv1_2 (in-place)
I0605 23:00:04.159801 54715 net.cpp:150] Setting up reshape
I0605 23:00:04.159806 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.159811 54715 net.cpp:165] Memory required for data: 372736000
I0605 23:00:04.159816 54715 layer_factory.hpp:77] Creating layer conv1_2_reshape_0_split
I0605 23:00:04.159822 54715 net.cpp:106] Creating Layer conv1_2_reshape_0_split
I0605 23:00:04.159826 54715 net.cpp:454] conv1_2_reshape_0_split <- conv1_2
I0605 23:00:04.159833 54715 net.cpp:411] conv1_2_reshape_0_split -> conv1_2_reshape_0_split_0
I0605 23:00:04.159850 54715 net.cpp:411] conv1_2_reshape_0_split -> conv1_2_reshape_0_split_1
I0605 23:00:04.159895 54715 net.cpp:150] Setting up conv1_2_reshape_0_split
I0605 23:00:04.159904 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.159909 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.159914 54715 net.cpp:165] Memory required for data: 438272000
I0605 23:00:04.159917 54715 layer_factory.hpp:77] Creating layer reshape
I0605 23:00:04.159924 54715 net.cpp:106] Creating Layer reshape
I0605 23:00:04.159929 54715 net.cpp:454] reshape <- label
I0605 23:00:04.159935 54715 net.cpp:397] reshape -> label (in-place)
I0605 23:00:04.159943 54715 net.cpp:150] Setting up reshape
I0605 23:00:04.159948 54715 net.cpp:157] Top shape: 5 1 320 320 (512000)
I0605 23:00:04.159951 54715 net.cpp:165] Memory required for data: 440320000
I0605 23:00:04.159956 54715 layer_factory.hpp:77] Creating layer conv2_1b
I0605 23:00:04.159966 54715 net.cpp:106] Creating Layer conv2_1b
I0605 23:00:04.159970 54715 net.cpp:454] conv2_1b <- conv1_2_reshape_0_split_0
I0605 23:00:04.159978 54715 net.cpp:411] conv2_1b -> conv2_1b
I0605 23:00:04.161518 54715 net.cpp:150] Setting up conv2_1b
I0605 23:00:04.161535 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.161540 54715 net.cpp:165] Memory required for data: 473088000
I0605 23:00:04.161547 54715 layer_factory.hpp:77] Creating layer bn_conv2_1b
I0605 23:00:04.161556 54715 net.cpp:106] Creating Layer bn_conv2_1b
I0605 23:00:04.161561 54715 net.cpp:454] bn_conv2_1b <- conv2_1b
I0605 23:00:04.161568 54715 net.cpp:397] bn_conv2_1b -> conv2_1b (in-place)
I0605 23:00:04.161751 54715 net.cpp:150] Setting up bn_conv2_1b
I0605 23:00:04.161759 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.161763 54715 net.cpp:165] Memory required for data: 505856000
I0605 23:00:04.161777 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b
I0605 23:00:04.161783 54715 net.cpp:106] Creating Layer scale_conv2_1b
I0605 23:00:04.161788 54715 net.cpp:454] scale_conv2_1b <- conv2_1b
I0605 23:00:04.161794 54715 net.cpp:397] scale_conv2_1b -> conv2_1b (in-place)
I0605 23:00:04.161833 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b
I0605 23:00:04.161965 54715 net.cpp:150] Setting up scale_conv2_1b
I0605 23:00:04.161975 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.161979 54715 net.cpp:165] Memory required for data: 538624000
I0605 23:00:04.161985 54715 layer_factory.hpp:77] Creating layer relu2_1b
I0605 23:00:04.161993 54715 net.cpp:106] Creating Layer relu2_1b
I0605 23:00:04.161998 54715 net.cpp:454] relu2_1b <- conv2_1b
I0605 23:00:04.162003 54715 net.cpp:397] relu2_1b -> conv2_1b (in-place)
I0605 23:00:04.162009 54715 net.cpp:150] Setting up relu2_1b
I0605 23:00:04.162015 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.162019 54715 net.cpp:165] Memory required for data: 571392000
I0605 23:00:04.162024 54715 layer_factory.hpp:77] Creating layer conv2_1b_3x3
I0605 23:00:04.162034 54715 net.cpp:106] Creating Layer conv2_1b_3x3
I0605 23:00:04.162039 54715 net.cpp:454] conv2_1b_3x3 <- conv2_1b
I0605 23:00:04.162047 54715 net.cpp:411] conv2_1b_3x3 -> conv2_1b_3x3
I0605 23:00:04.162572 54715 net.cpp:150] Setting up conv2_1b_3x3
I0605 23:00:04.162581 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.162585 54715 net.cpp:165] Memory required for data: 620544000
I0605 23:00:04.162592 54715 layer_factory.hpp:77] Creating layer bn_conv2_1b_3x3
I0605 23:00:04.162600 54715 net.cpp:106] Creating Layer bn_conv2_1b_3x3
I0605 23:00:04.162605 54715 net.cpp:454] bn_conv2_1b_3x3 <- conv2_1b_3x3
I0605 23:00:04.162611 54715 net.cpp:397] bn_conv2_1b_3x3 -> conv2_1b_3x3 (in-place)
I0605 23:00:04.162798 54715 net.cpp:150] Setting up bn_conv2_1b_3x3
I0605 23:00:04.162806 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.162809 54715 net.cpp:165] Memory required for data: 669696000
I0605 23:00:04.162817 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b_3x3
I0605 23:00:04.162832 54715 net.cpp:106] Creating Layer scale_conv2_1b_3x3
I0605 23:00:04.162842 54715 net.cpp:454] scale_conv2_1b_3x3 <- conv2_1b_3x3
I0605 23:00:04.162848 54715 net.cpp:397] scale_conv2_1b_3x3 -> conv2_1b_3x3 (in-place)
I0605 23:00:04.162887 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b_3x3
I0605 23:00:04.163027 54715 net.cpp:150] Setting up scale_conv2_1b_3x3
I0605 23:00:04.163035 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.163039 54715 net.cpp:165] Memory required for data: 718848000
I0605 23:00:04.163046 54715 layer_factory.hpp:77] Creating layer conv2_1x1
I0605 23:00:04.163056 54715 net.cpp:106] Creating Layer conv2_1x1
I0605 23:00:04.163060 54715 net.cpp:454] conv2_1x1 <- conv1_2_reshape_0_split_1
I0605 23:00:04.163069 54715 net.cpp:411] conv2_1x1 -> conv2_1x1
I0605 23:00:04.163314 54715 net.cpp:150] Setting up conv2_1x1
I0605 23:00:04.163324 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.163327 54715 net.cpp:165] Memory required for data: 751616000
I0605 23:00:04.163334 54715 layer_factory.hpp:77] Creating layer bn_conv2_1x1
I0605 23:00:04.163341 54715 net.cpp:106] Creating Layer bn_conv2_1x1
I0605 23:00:04.163347 54715 net.cpp:454] bn_conv2_1x1 <- conv2_1x1
I0605 23:00:04.163352 54715 net.cpp:397] bn_conv2_1x1 -> conv2_1x1 (in-place)
I0605 23:00:04.163532 54715 net.cpp:150] Setting up bn_conv2_1x1
I0605 23:00:04.163538 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.163543 54715 net.cpp:165] Memory required for data: 784384000
I0605 23:00:04.163555 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x1
I0605 23:00:04.163563 54715 net.cpp:106] Creating Layer scale_conv2_1x1
I0605 23:00:04.163566 54715 net.cpp:454] scale_conv2_1x1 <- conv2_1x1
I0605 23:00:04.163574 54715 net.cpp:397] scale_conv2_1x1 -> conv2_1x1 (in-place)
I0605 23:00:04.163612 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x1
I0605 23:00:04.163750 54715 net.cpp:150] Setting up scale_conv2_1x1
I0605 23:00:04.163759 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.163764 54715 net.cpp:165] Memory required for data: 817152000
I0605 23:00:04.163770 54715 layer_factory.hpp:77] Creating layer relu2_1x1
I0605 23:00:04.163776 54715 net.cpp:106] Creating Layer relu2_1x1
I0605 23:00:04.163781 54715 net.cpp:454] relu2_1x1 <- conv2_1x1
I0605 23:00:04.163789 54715 net.cpp:397] relu2_1x1 -> conv2_1x1 (in-place)
I0605 23:00:04.163794 54715 net.cpp:150] Setting up relu2_1x1
I0605 23:00:04.163800 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.163803 54715 net.cpp:165] Memory required for data: 849920000
I0605 23:00:04.163808 54715 layer_factory.hpp:77] Creating layer conv2_1x7
I0605 23:00:04.163816 54715 net.cpp:106] Creating Layer conv2_1x7
I0605 23:00:04.163822 54715 net.cpp:454] conv2_1x7 <- conv2_1x1
I0605 23:00:04.163830 54715 net.cpp:411] conv2_1x7 -> conv2_1x7
I0605 23:00:04.165480 54715 net.cpp:150] Setting up conv2_1x7
I0605 23:00:04.165496 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.165501 54715 net.cpp:165] Memory required for data: 882688000
I0605 23:00:04.165509 54715 layer_factory.hpp:77] Creating layer bn_conv2_1x7
I0605 23:00:04.165519 54715 net.cpp:106] Creating Layer bn_conv2_1x7
I0605 23:00:04.165524 54715 net.cpp:454] bn_conv2_1x7 <- conv2_1x7
I0605 23:00:04.165530 54715 net.cpp:397] bn_conv2_1x7 -> conv2_1x7 (in-place)
I0605 23:00:04.165725 54715 net.cpp:150] Setting up bn_conv2_1x7
I0605 23:00:04.165735 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.165737 54715 net.cpp:165] Memory required for data: 915456000
I0605 23:00:04.165746 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x7
I0605 23:00:04.165753 54715 net.cpp:106] Creating Layer scale_conv2_1x7
I0605 23:00:04.165758 54715 net.cpp:454] scale_conv2_1x7 <- conv2_1x7
I0605 23:00:04.165765 54715 net.cpp:397] scale_conv2_1x7 -> conv2_1x7 (in-place)
I0605 23:00:04.165803 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x7
I0605 23:00:04.165936 54715 net.cpp:150] Setting up scale_conv2_1x7
I0605 23:00:04.165954 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.165966 54715 net.cpp:165] Memory required for data: 948224000
I0605 23:00:04.165972 54715 layer_factory.hpp:77] Creating layer relu2_1x7
I0605 23:00:04.165980 54715 net.cpp:106] Creating Layer relu2_1x7
I0605 23:00:04.165985 54715 net.cpp:454] relu2_1x7 <- conv2_1x7
I0605 23:00:04.165992 54715 net.cpp:397] relu2_1x7 -> conv2_1x7 (in-place)
I0605 23:00:04.165997 54715 net.cpp:150] Setting up relu2_1x7
I0605 23:00:04.166003 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.166007 54715 net.cpp:165] Memory required for data: 980992000
I0605 23:00:04.166012 54715 layer_factory.hpp:77] Creating layer conv2_7x1
I0605 23:00:04.166020 54715 net.cpp:106] Creating Layer conv2_7x1
I0605 23:00:04.166024 54715 net.cpp:454] conv2_7x1 <- conv2_1x7
I0605 23:00:04.166033 54715 net.cpp:411] conv2_7x1 -> conv2_7x1
I0605 23:00:04.166411 54715 net.cpp:150] Setting up conv2_7x1
I0605 23:00:04.166420 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.166424 54715 net.cpp:165] Memory required for data: 1013760000
I0605 23:00:04.166431 54715 layer_factory.hpp:77] Creating layer bn_conv2_7x1
I0605 23:00:04.166440 54715 net.cpp:106] Creating Layer bn_conv2_7x1
I0605 23:00:04.166443 54715 net.cpp:454] bn_conv2_7x1 <- conv2_7x1
I0605 23:00:04.166450 54715 net.cpp:397] bn_conv2_7x1 -> conv2_7x1 (in-place)
I0605 23:00:04.166635 54715 net.cpp:150] Setting up bn_conv2_7x1
I0605 23:00:04.166642 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.166646 54715 net.cpp:165] Memory required for data: 1046528000
I0605 23:00:04.166654 54715 layer_factory.hpp:77] Creating layer scale_conv2_7x1
I0605 23:00:04.166661 54715 net.cpp:106] Creating Layer scale_conv2_7x1
I0605 23:00:04.166666 54715 net.cpp:454] scale_conv2_7x1 <- conv2_7x1
I0605 23:00:04.166671 54715 net.cpp:397] scale_conv2_7x1 -> conv2_7x1 (in-place)
I0605 23:00:04.166709 54715 layer_factory.hpp:77] Creating layer scale_conv2_7x1
I0605 23:00:04.166838 54715 net.cpp:150] Setting up scale_conv2_7x1
I0605 23:00:04.166846 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.166851 54715 net.cpp:165] Memory required for data: 1079296000
I0605 23:00:04.166857 54715 layer_factory.hpp:77] Creating layer relu2_7x1
I0605 23:00:04.166863 54715 net.cpp:106] Creating Layer relu2_7x1
I0605 23:00:04.166868 54715 net.cpp:454] relu2_7x1 <- conv2_7x1
I0605 23:00:04.166874 54715 net.cpp:397] relu2_7x1 -> conv2_7x1 (in-place)
I0605 23:00:04.166880 54715 net.cpp:150] Setting up relu2_7x1
I0605 23:00:04.166887 54715 net.cpp:157] Top shape: 5 64 160 160 (8192000)
I0605 23:00:04.166890 54715 net.cpp:165] Memory required for data: 1112064000
I0605 23:00:04.166894 54715 layer_factory.hpp:77] Creating layer conv2_3x3
I0605 23:00:04.166903 54715 net.cpp:106] Creating Layer conv2_3x3
I0605 23:00:04.166908 54715 net.cpp:454] conv2_3x3 <- conv2_7x1
I0605 23:00:04.166914 54715 net.cpp:411] conv2_3x3 -> conv2_3x3
I0605 23:00:04.167434 54715 net.cpp:150] Setting up conv2_3x3
I0605 23:00:04.167443 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.167448 54715 net.cpp:165] Memory required for data: 1161216000
I0605 23:00:04.167454 54715 layer_factory.hpp:77] Creating layer bn_conv2_3x3
I0605 23:00:04.167464 54715 net.cpp:106] Creating Layer bn_conv2_3x3
I0605 23:00:04.167469 54715 net.cpp:454] bn_conv2_3x3 <- conv2_3x3
I0605 23:00:04.167475 54715 net.cpp:397] bn_conv2_3x3 -> conv2_3x3 (in-place)
I0605 23:00:04.167663 54715 net.cpp:150] Setting up bn_conv2_3x3
I0605 23:00:04.167671 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.167675 54715 net.cpp:165] Memory required for data: 1210368000
I0605 23:00:04.167683 54715 layer_factory.hpp:77] Creating layer scale_conv2_3x3
I0605 23:00:04.167690 54715 net.cpp:106] Creating Layer scale_conv2_3x3
I0605 23:00:04.167695 54715 net.cpp:454] scale_conv2_3x3 <- conv2_3x3
I0605 23:00:04.167701 54715 net.cpp:397] scale_conv2_3x3 -> conv2_3x3 (in-place)
I0605 23:00:04.167739 54715 layer_factory.hpp:77] Creating layer scale_conv2_3x3
I0605 23:00:04.167878 54715 net.cpp:150] Setting up scale_conv2_3x3
I0605 23:00:04.167892 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.167897 54715 net.cpp:165] Memory required for data: 1259520000
I0605 23:00:04.167904 54715 layer_factory.hpp:77] Creating layer relu2_3x3
I0605 23:00:04.167912 54715 net.cpp:106] Creating Layer relu2_3x3
I0605 23:00:04.167915 54715 net.cpp:454] relu2_3x3 <- conv2_3x3
I0605 23:00:04.167922 54715 net.cpp:397] relu2_3x3 -> conv2_3x3 (in-place)
I0605 23:00:04.167929 54715 net.cpp:150] Setting up relu2_3x3
I0605 23:00:04.167934 54715 net.cpp:157] Top shape: 5 96 160 160 (12288000)
I0605 23:00:04.167938 54715 net.cpp:165] Memory required for data: 1308672000
I0605 23:00:04.167943 54715 layer_factory.hpp:77] Creating layer concat_stem_1
I0605 23:00:04.167949 54715 net.cpp:106] Creating Layer concat_stem_1
I0605 23:00:04.167953 54715 net.cpp:454] concat_stem_1 <- conv2_1b_3x3
I0605 23:00:04.167958 54715 net.cpp:454] concat_stem_1 <- conv2_3x3
I0605 23:00:04.167963 54715 net.cpp:411] concat_stem_1 -> concat_stem_1
I0605 23:00:04.167990 54715 net.cpp:150] Setting up concat_stem_1
I0605 23:00:04.167997 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168001 54715 net.cpp:165] Memory required for data: 1406976000
I0605 23:00:04.168005 54715 layer_factory.hpp:77] Creating layer concat_stem_1_concat_stem_1_0_split
I0605 23:00:04.168015 54715 net.cpp:106] Creating Layer concat_stem_1_concat_stem_1_0_split
I0605 23:00:04.168018 54715 net.cpp:454] concat_stem_1_concat_stem_1_0_split <- concat_stem_1
I0605 23:00:04.168025 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_0
I0605 23:00:04.168033 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_1
I0605 23:00:04.168041 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_2
I0605 23:00:04.168048 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_3
I0605 23:00:04.168058 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_4
I0605 23:00:04.168066 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_5
I0605 23:00:04.168073 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_6
I0605 23:00:04.168184 54715 net.cpp:150] Setting up concat_stem_1_concat_stem_1_0_split
I0605 23:00:04.168195 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168200 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168205 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168210 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168215 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168220 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168225 54715 net.cpp:157] Top shape: 5 192 160 160 (24576000)
I0605 23:00:04.168228 54715 net.cpp:165] Memory required for data: 2095104000
I0605 23:00:04.168232 54715 layer_factory.hpp:77] Creating layer stem_concat_conv_3x3
I0605 23:00:04.168242 54715 net.cpp:106] Creating Layer stem_concat_conv_3x3
I0605 23:00:04.168248 54715 net.cpp:454] stem_concat_conv_3x3 <- concat_stem_1_concat_stem_1_0_split_0
I0605 23:00:04.168257 54715 net.cpp:411] stem_concat_conv_3x3 -> stem_concat_conv_3x3
I0605 23:00:04.172731 54715 net.cpp:150] Setting up stem_concat_conv_3x3
I0605 23:00:04.172749 54715 net.cpp:157] Top shape: 5 192 80 80 (6144000)
I0605 23:00:04.172755 54715 net.cpp:165] Memory required for data: 2119680000
I0605 23:00:04.172762 54715 layer_factory.hpp:77] Creating layer bn_stem_concat_conv_3x3
I0605 23:00:04.172771 54715 net.cpp:106] Creating Layer bn_stem_concat_conv_3x3
I0605 23:00:04.172776 54715 net.cpp:454] bn_stem_concat_conv_3x3 <- stem_concat_conv_3x3
I0605 23:00:04.172785 54715 net.cpp:397] bn_stem_concat_conv_3x3 -> stem_concat_conv_3x3 (in-place)
I0605 23:00:04.172971 54715 net.cpp:150] Setting up bn_stem_concat_conv_3x3
I0605 23:00:04.172991 54715 net.cpp:157] Top shape: 5 192 80 80 (6144000)
I0605 23:00:04.172994 54715 net.cpp:165] Memory required for data: 2144256000
I0605 23:00:04.173004 54715 layer_factory.hpp:77] Creating layer scale_stem_concat_conv_3x3
I0605 23:00:04.173012 54715 net.cpp:106] Creating Layer scale_stem_concat_conv_3x3
I0605 23:00:04.173017 54715 net.cpp:454] scale_stem_concat_conv_3x3 <- stem_concat_conv_3x3
I0605 23:00:04.173022 54715 net.cpp:397] scale_stem_concat_conv_3x3 -> stem_concat_conv_3x3 (in-place)
I0605 23:00:04.173065 54715 layer_factory.hpp:77] Creating layer scale_stem_concat_conv_3x3
I0605 23:00:04.173177 54715 net.cpp:150] Setting up scale_stem_concat_conv_3x3
I0605 23:00:04.173184 54715 net.cpp:157] Top shape: 5 192 80 80 (6144000)
I0605 23:00:04.173188 54715 net.cpp:165] Memory required for data: 2168832000
I0605 23:00:04.173197 54715 layer_factory.hpp:77] Creating layer relu_stem_concat_conv_3x3
I0605 23:00:04.173202 54715 net.cpp:106] Creating Layer relu_stem_concat_conv_3x3
I0605 23:00:04.173207 54715 net.cpp:454] relu_stem_concat_conv_3x3 <- stem_concat_conv_3x3
I0605 23:00:04.173213 54715 net.cpp:397] relu_stem_concat_conv_3x3 -> stem_concat_conv_3x3 (in-place)
I0605 23:00:04.173220 54715 net.cpp:150] Setting up relu_stem_concat_conv_3x3
I0605 23:00:04.173225 54715 net.cpp:157] Top shape: 5 192 80 80 (6144000)
I0605 23:00:04.173229 54715 net.cpp:165] Memory required for data: 2193408000
I0605 23:00:04.173233 54715 layer_factory.hpp:77] Creating layer pool_stem_concat
I0605 23:00:04.173243 54715 net.cpp:106] Creating Layer pool_stem_concat
I0605 23:00:04.173247 54715 net.cpp:454] pool_stem_concat <- concat_stem_1_concat_stem_1_0_split_1
I0605 23:00:04.173254 54715 net.cpp:411] pool_stem_concat -> pool_stem_concat
I0605 23:00:04.173302 54715 net.cpp:150] Setting up pool_stem_concat
I0605 23:00:04.173311 54715 net.cpp:157] Top shape: 5 192 80 80 (6144000)
I0605 23:00:04.173316 54715 net.cpp:165] Memory required for data: 2217984000
I0605 23:00:04.173319 54715 layer_factory.hpp:77] Creating layer concat_stem_2
I0605 23:00:04.173326 54715 net.cpp:106] Creating Layer concat_stem_2
I0605 23:00:04.173331 54715 net.cpp:454] concat_stem_2 <- pool_stem_concat
I0605 23:00:04.173336 54715 net.cpp:454] concat_stem_2 <- stem_concat_conv_3x3
I0605 23:00:04.173343 54715 net.cpp:411] concat_stem_2 -> concat_stem_2
I0605 23:00:04.173367 54715 net.cpp:150] Setting up concat_stem_2
I0605 23:00:04.173374 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.173378 54715 net.cpp:165] Memory required for data: 2267136000
I0605 23:00:04.173382 54715 layer_factory.hpp:77] Creating layer conv3_1b
I0605 23:00:04.173393 54715 net.cpp:106] Creating Layer conv3_1b
I0605 23:00:04.173398 54715 net.cpp:454] conv3_1b <- concat_stem_2
I0605 23:00:04.173405 54715 net.cpp:411] conv3_1b -> conv3_1b
I0605 23:00:04.174414 54715 net.cpp:150] Setting up conv3_1b
I0605 23:00:04.174423 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174428 54715 net.cpp:165] Memory required for data: 2316288000
I0605 23:00:04.174444 54715 layer_factory.hpp:77] Creating layer bn_conv3_1b
I0605 23:00:04.174451 54715 net.cpp:106] Creating Layer bn_conv3_1b
I0605 23:00:04.174456 54715 net.cpp:454] bn_conv3_1b <- conv3_1b
I0605 23:00:04.174463 54715 net.cpp:397] bn_conv3_1b -> conv3_1b (in-place)
I0605 23:00:04.174631 54715 net.cpp:150] Setting up bn_conv3_1b
I0605 23:00:04.174638 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174643 54715 net.cpp:165] Memory required for data: 2365440000
I0605 23:00:04.174651 54715 layer_factory.hpp:77] Creating layer scale_conv3_1b
I0605 23:00:04.174659 54715 net.cpp:106] Creating Layer scale_conv3_1b
I0605 23:00:04.174662 54715 net.cpp:454] scale_conv3_1b <- conv3_1b
I0605 23:00:04.174669 54715 net.cpp:397] scale_conv3_1b -> conv3_1b (in-place)
I0605 23:00:04.174705 54715 layer_factory.hpp:77] Creating layer scale_conv3_1b
I0605 23:00:04.174808 54715 net.cpp:150] Setting up scale_conv3_1b
I0605 23:00:04.174816 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174829 54715 net.cpp:165] Memory required for data: 2414592000
I0605 23:00:04.174839 54715 layer_factory.hpp:77] Creating layer relu3_1b
I0605 23:00:04.174844 54715 net.cpp:106] Creating Layer relu3_1b
I0605 23:00:04.174849 54715 net.cpp:454] relu3_1b <- conv3_1b
I0605 23:00:04.174855 54715 net.cpp:397] relu3_1b -> conv3_1b (in-place)
I0605 23:00:04.174862 54715 net.cpp:150] Setting up relu3_1b
I0605 23:00:04.174867 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174871 54715 net.cpp:165] Memory required for data: 2463744000
I0605 23:00:04.174875 54715 layer_factory.hpp:77] Creating layer conv3_1b_relu3_1b_0_split
I0605 23:00:04.174882 54715 net.cpp:106] Creating Layer conv3_1b_relu3_1b_0_split
I0605 23:00:04.174886 54715 net.cpp:454] conv3_1b_relu3_1b_0_split <- conv3_1b
I0605 23:00:04.174892 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_0
I0605 23:00:04.174899 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_1
I0605 23:00:04.174908 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_2
I0605 23:00:04.174916 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_3
I0605 23:00:04.174974 54715 net.cpp:150] Setting up conv3_1b_relu3_1b_0_split
I0605 23:00:04.174983 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174988 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174993 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.174996 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.175000 54715 net.cpp:165] Memory required for data: 2660352000
I0605 23:00:04.175005 54715 layer_factory.hpp:77] Creating layer ira_A_1_conv1x1
I0605 23:00:04.175014 54715 net.cpp:106] Creating Layer ira_A_1_conv1x1
I0605 23:00:04.175017 54715 net.cpp:454] ira_A_1_conv1x1 <- conv3_1b_relu3_1b_0_split_0
I0605 23:00:04.175025 54715 net.cpp:411] ira_A_1_conv1x1 -> ira_A_1_conv1x1
I0605 23:00:04.175307 54715 net.cpp:150] Setting up ira_A_1_conv1x1
I0605 23:00:04.175315 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.175319 54715 net.cpp:165] Memory required for data: 2664448000
I0605 23:00:04.175325 54715 layer_factory.hpp:77] Creating layer bn_ira_A_1_conv1x1
I0605 23:00:04.175333 54715 net.cpp:106] Creating Layer bn_ira_A_1_conv1x1
I0605 23:00:04.175338 54715 net.cpp:454] bn_ira_A_1_conv1x1 <- ira_A_1_conv1x1
I0605 23:00:04.175344 54715 net.cpp:397] bn_ira_A_1_conv1x1 -> ira_A_1_conv1x1 (in-place)
I0605 23:00:04.176813 54715 net.cpp:150] Setting up bn_ira_A_1_conv1x1
I0605 23:00:04.176827 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.176831 54715 net.cpp:165] Memory required for data: 2668544000
I0605 23:00:04.176839 54715 layer_factory.hpp:77] Creating layer scale_ira_A_1_conv1x1
I0605 23:00:04.176847 54715 net.cpp:106] Creating Layer scale_ira_A_1_conv1x1
I0605 23:00:04.176852 54715 net.cpp:454] scale_ira_A_1_conv1x1 <- ira_A_1_conv1x1
I0605 23:00:04.176861 54715 net.cpp:397] scale_ira_A_1_conv1x1 -> ira_A_1_conv1x1 (in-place)
I0605 23:00:04.176900 54715 layer_factory.hpp:77] Creating layer scale_ira_A_1_conv1x1
I0605 23:00:04.177009 54715 net.cpp:150] Setting up scale_ira_A_1_conv1x1
I0605 23:00:04.177018 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.177022 54715 net.cpp:165] Memory required for data: 2672640000
I0605 23:00:04.177028 54715 layer_factory.hpp:77] Creating layer relu_ira_A_1_conv1x1
I0605 23:00:04.177036 54715 net.cpp:106] Creating Layer relu_ira_A_1_conv1x1
I0605 23:00:04.177040 54715 net.cpp:454] relu_ira_A_1_conv1x1 <- ira_A_1_conv1x1
I0605 23:00:04.177047 54715 net.cpp:397] relu_ira_A_1_conv1x1 -> ira_A_1_conv1x1 (in-place)
I0605 23:00:04.177052 54715 net.cpp:150] Setting up relu_ira_A_1_conv1x1
I0605 23:00:04.177058 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.177062 54715 net.cpp:165] Memory required for data: 2676736000
I0605 23:00:04.177067 54715 layer_factory.hpp:77] Creating layer ira_A_2_conv1x1
I0605 23:00:04.177081 54715 net.cpp:106] Creating Layer ira_A_2_conv1x1
I0605 23:00:04.177091 54715 net.cpp:454] ira_A_2_conv1x1 <- conv3_1b_relu3_1b_0_split_1
I0605 23:00:04.177101 54715 net.cpp:411] ira_A_2_conv1x1 -> ira_A_2_conv1x1
I0605 23:00:04.177388 54715 net.cpp:150] Setting up ira_A_2_conv1x1
I0605 23:00:04.177397 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.177400 54715 net.cpp:165] Memory required for data: 2680832000
I0605 23:00:04.177408 54715 layer_factory.hpp:77] Creating layer bn_ira_A_2_conv1x1
I0605 23:00:04.177415 54715 net.cpp:106] Creating Layer bn_ira_A_2_conv1x1
I0605 23:00:04.177420 54715 net.cpp:454] bn_ira_A_2_conv1x1 <- ira_A_2_conv1x1
I0605 23:00:04.177426 54715 net.cpp:397] bn_ira_A_2_conv1x1 -> ira_A_2_conv1x1 (in-place)
I0605 23:00:04.177605 54715 net.cpp:150] Setting up bn_ira_A_2_conv1x1
I0605 23:00:04.177613 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.177616 54715 net.cpp:165] Memory required for data: 2684928000
I0605 23:00:04.177624 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv1x1
I0605 23:00:04.177633 54715 net.cpp:106] Creating Layer scale_ira_A_2_conv1x1
I0605 23:00:04.177636 54715 net.cpp:454] scale_ira_A_2_conv1x1 <- ira_A_2_conv1x1
I0605 23:00:04.177644 54715 net.cpp:397] scale_ira_A_2_conv1x1 -> ira_A_2_conv1x1 (in-place)
I0605 23:00:04.177680 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv1x1
I0605 23:00:04.177789 54715 net.cpp:150] Setting up scale_ira_A_2_conv1x1
I0605 23:00:04.177796 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.177800 54715 net.cpp:165] Memory required for data: 2689024000
I0605 23:00:04.177806 54715 layer_factory.hpp:77] Creating layer relu_ira_A_2_conv1x1
I0605 23:00:04.177814 54715 net.cpp:106] Creating Layer relu_ira_A_2_conv1x1
I0605 23:00:04.177819 54715 net.cpp:454] relu_ira_A_2_conv1x1 <- ira_A_2_conv1x1
I0605 23:00:04.177825 54715 net.cpp:397] relu_ira_A_2_conv1x1 -> ira_A_2_conv1x1 (in-place)
I0605 23:00:04.177831 54715 net.cpp:150] Setting up relu_ira_A_2_conv1x1
I0605 23:00:04.177837 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.177841 54715 net.cpp:165] Memory required for data: 2693120000
I0605 23:00:04.177845 54715 layer_factory.hpp:77] Creating layer ira_A_2_conv3x3
I0605 23:00:04.177853 54715 net.cpp:106] Creating Layer ira_A_2_conv3x3
I0605 23:00:04.177858 54715 net.cpp:454] ira_A_2_conv3x3 <- ira_A_2_conv1x1
I0605 23:00:04.177865 54715 net.cpp:411] ira_A_2_conv3x3 -> ira_A_2_conv3x3
I0605 23:00:04.178131 54715 net.cpp:150] Setting up ira_A_2_conv3x3
I0605 23:00:04.178139 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.178144 54715 net.cpp:165] Memory required for data: 2697216000
I0605 23:00:04.178150 54715 layer_factory.hpp:77] Creating layer bn_ira_A_2_conv3x3
I0605 23:00:04.178158 54715 net.cpp:106] Creating Layer bn_ira_A_2_conv3x3
I0605 23:00:04.178161 54715 net.cpp:454] bn_ira_A_2_conv3x3 <- ira_A_2_conv3x3
I0605 23:00:04.178169 54715 net.cpp:397] bn_ira_A_2_conv3x3 -> ira_A_2_conv3x3 (in-place)
I0605 23:00:04.178344 54715 net.cpp:150] Setting up bn_ira_A_2_conv3x3
I0605 23:00:04.178350 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.178354 54715 net.cpp:165] Memory required for data: 2701312000
I0605 23:00:04.178364 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv3x3
I0605 23:00:04.178370 54715 net.cpp:106] Creating Layer scale_ira_A_2_conv3x3
I0605 23:00:04.178375 54715 net.cpp:454] scale_ira_A_2_conv3x3 <- ira_A_2_conv3x3
I0605 23:00:04.178380 54715 net.cpp:397] scale_ira_A_2_conv3x3 -> ira_A_2_conv3x3 (in-place)
I0605 23:00:04.178419 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv3x3
I0605 23:00:04.178525 54715 net.cpp:150] Setting up scale_ira_A_2_conv3x3
I0605 23:00:04.178534 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.178537 54715 net.cpp:165] Memory required for data: 2705408000
I0605 23:00:04.178544 54715 layer_factory.hpp:77] Creating layer relu_ira_A_2_conv3x3
I0605 23:00:04.178551 54715 net.cpp:106] Creating Layer relu_ira_A_2_conv3x3
I0605 23:00:04.178561 54715 net.cpp:454] relu_ira_A_2_conv3x3 <- ira_A_2_conv3x3
I0605 23:00:04.178573 54715 net.cpp:397] relu_ira_A_2_conv3x3 -> ira_A_2_conv3x3 (in-place)
I0605 23:00:04.178580 54715 net.cpp:150] Setting up relu_ira_A_2_conv3x3
I0605 23:00:04.178586 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.178589 54715 net.cpp:165] Memory required for data: 2709504000
I0605 23:00:04.178593 54715 layer_factory.hpp:77] Creating layer ira_A_3_conv1x1
I0605 23:00:04.178602 54715 net.cpp:106] Creating Layer ira_A_3_conv1x1
I0605 23:00:04.178606 54715 net.cpp:454] ira_A_3_conv1x1 <- conv3_1b_relu3_1b_0_split_2
I0605 23:00:04.178614 54715 net.cpp:411] ira_A_3_conv1x1 -> ira_A_3_conv1x1
I0605 23:00:04.178899 54715 net.cpp:150] Setting up ira_A_3_conv1x1
I0605 23:00:04.178907 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.178911 54715 net.cpp:165] Memory required for data: 2713600000
I0605 23:00:04.178917 54715 layer_factory.hpp:77] Creating layer bn_ira_A_3_conv1x1
I0605 23:00:04.178925 54715 net.cpp:106] Creating Layer bn_ira_A_3_conv1x1
I0605 23:00:04.178930 54715 net.cpp:454] bn_ira_A_3_conv1x1 <- ira_A_3_conv1x1
I0605 23:00:04.178936 54715 net.cpp:397] bn_ira_A_3_conv1x1 -> ira_A_3_conv1x1 (in-place)
I0605 23:00:04.179113 54715 net.cpp:150] Setting up bn_ira_A_3_conv1x1
I0605 23:00:04.179121 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.179126 54715 net.cpp:165] Memory required for data: 2717696000
I0605 23:00:04.179133 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv1x1
I0605 23:00:04.179139 54715 net.cpp:106] Creating Layer scale_ira_A_3_conv1x1
I0605 23:00:04.179143 54715 net.cpp:454] scale_ira_A_3_conv1x1 <- ira_A_3_conv1x1
I0605 23:00:04.179152 54715 net.cpp:397] scale_ira_A_3_conv1x1 -> ira_A_3_conv1x1 (in-place)
I0605 23:00:04.179188 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv1x1
I0605 23:00:04.179296 54715 net.cpp:150] Setting up scale_ira_A_3_conv1x1
I0605 23:00:04.179303 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.179308 54715 net.cpp:165] Memory required for data: 2721792000
I0605 23:00:04.179318 54715 layer_factory.hpp:77] Creating layer relu_ira_A_3_conv1x1
I0605 23:00:04.179324 54715 net.cpp:106] Creating Layer relu_ira_A_3_conv1x1
I0605 23:00:04.179329 54715 net.cpp:454] relu_ira_A_3_conv1x1 <- ira_A_3_conv1x1
I0605 23:00:04.179337 54715 net.cpp:397] relu_ira_A_3_conv1x1 -> ira_A_3_conv1x1 (in-place)
I0605 23:00:04.179342 54715 net.cpp:150] Setting up relu_ira_A_3_conv1x1
I0605 23:00:04.179348 54715 net.cpp:157] Top shape: 5 32 80 80 (1024000)
I0605 23:00:04.179352 54715 net.cpp:165] Memory required for data: 2725888000
I0605 23:00:04.179356 54715 layer_factory.hpp:77] Creating layer ira_A_3_conv3x3_1
I0605 23:00:04.179373 54715 net.cpp:106] Creating Layer ira_A_3_conv3x3_1
I0605 23:00:04.179378 54715 net.cpp:454] ira_A_3_conv3x3_1 <- ira_A_3_conv1x1
I0605 23:00:04.179384 54715 net.cpp:411] ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1
I0605 23:00:04.179684 54715 net.cpp:150] Setting up ira_A_3_conv3x3_1
I0605 23:00:04.179693 54715 net.cpp:157] Top shape: 5 48 80 80 (1536000)
I0605 23:00:04.179697 54715 net.cpp:165] Memory required for data: 2732032000
I0605 23:00:04.179704 54715 layer_factory.hpp:77] Creating layer bn_ira_A_3_conv3x3_1
I0605 23:00:04.179713 54715 net.cpp:106] Creating Layer bn_ira_A_3_conv3x3_1
I0605 23:00:04.179718 54715 net.cpp:454] bn_ira_A_3_conv3x3_1 <- ira_A_3_conv3x3_1
I0605 23:00:04.179724 54715 net.cpp:397] bn_ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1 (in-place)
I0605 23:00:04.179901 54715 net.cpp:150] Setting up bn_ira_A_3_conv3x3_1
I0605 23:00:04.179909 54715 net.cpp:157] Top shape: 5 48 80 80 (1536000)
I0605 23:00:04.179913 54715 net.cpp:165] Memory required for data: 2738176000
I0605 23:00:04.179921 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_1
I0605 23:00:04.179927 54715 net.cpp:106] Creating Layer scale_ira_A_3_conv3x3_1
I0605 23:00:04.179932 54715 net.cpp:454] scale_ira_A_3_conv3x3_1 <- ira_A_3_conv3x3_1
I0605 23:00:04.179939 54715 net.cpp:397] scale_ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1 (in-place)
I0605 23:00:04.179988 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_1
I0605 23:00:04.180095 54715 net.cpp:150] Setting up scale_ira_A_3_conv3x3_1
I0605 23:00:04.180104 54715 net.cpp:157] Top shape: 5 48 80 80 (1536000)
I0605 23:00:04.180109 54715 net.cpp:165] Memory required for data: 2744320000
I0605 23:00:04.180115 54715 layer_factory.hpp:77] Creating layer relu_ira_A_3_conv3x3_1
I0605 23:00:04.180121 54715 net.cpp:106] Creating Layer relu_ira_A_3_conv3x3_1
I0605 23:00:04.180126 54715 net.cpp:454] relu_ira_A_3_conv3x3_1 <- ira_A_3_conv3x3_1
I0605 23:00:04.180133 54715 net.cpp:397] relu_ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1 (in-place)
I0605 23:00:04.180157 54715 net.cpp:150] Setting up relu_ira_A_3_conv3x3_1
I0605 23:00:04.180166 54715 net.cpp:157] Top shape: 5 48 80 80 (1536000)
I0605 23:00:04.180171 54715 net.cpp:165] Memory required for data: 2750464000
I0605 23:00:04.180173 54715 layer_factory.hpp:77] Creating layer ira_A_3_conv3x3_2
I0605 23:00:04.180182 54715 net.cpp:106] Creating Layer ira_A_3_conv3x3_2
I0605 23:00:04.180186 54715 net.cpp:454] ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_1
I0605 23:00:04.180194 54715 net.cpp:411] ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2
I0605 23:00:04.180583 54715 net.cpp:150] Setting up ira_A_3_conv3x3_2
I0605 23:00:04.180590 54715 net.cpp:157] Top shape: 5 64 80 80 (2048000)
I0605 23:00:04.180594 54715 net.cpp:165] Memory required for data: 2758656000
I0605 23:00:04.180601 54715 layer_factory.hpp:77] Creating layer bn_ira_A_3_conv3x3_2
I0605 23:00:04.180609 54715 net.cpp:106] Creating Layer bn_ira_A_3_conv3x3_2
I0605 23:00:04.180613 54715 net.cpp:454] bn_ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_2
I0605 23:00:04.180620 54715 net.cpp:397] bn_ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2 (in-place)
I0605 23:00:04.180800 54715 net.cpp:150] Setting up bn_ira_A_3_conv3x3_2
I0605 23:00:04.180807 54715 net.cpp:157] Top shape: 5 64 80 80 (2048000)
I0605 23:00:04.180811 54715 net.cpp:165] Memory required for data: 2766848000
I0605 23:00:04.180819 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_2
I0605 23:00:04.180826 54715 net.cpp:106] Creating Layer scale_ira_A_3_conv3x3_2
I0605 23:00:04.180830 54715 net.cpp:454] scale_ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_2
I0605 23:00:04.180837 54715 net.cpp:397] scale_ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2 (in-place)
I0605 23:00:04.180877 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_2
I0605 23:00:04.180986 54715 net.cpp:150] Setting up scale_ira_A_3_conv3x3_2
I0605 23:00:04.180994 54715 net.cpp:157] Top shape: 5 64 80 80 (2048000)
I0605 23:00:04.180999 54715 net.cpp:165] Memory required for data: 2775040000
I0605 23:00:04.181005 54715 layer_factory.hpp:77] Creating layer relu_ira_A_3_conv3x3_2
I0605 23:00:04.181011 54715 net.cpp:106] Creating Layer relu_ira_A_3_conv3x3_2
I0605 23:00:04.181016 54715 net.cpp:454] relu_ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_2
I0605 23:00:04.181022 54715 net.cpp:397] relu_ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2 (in-place)
I0605 23:00:04.181030 54715 net.cpp:150] Setting up relu_ira_A_3_conv3x3_2
I0605 23:00:04.181035 54715 net.cpp:157] Top shape: 5 64 80 80 (2048000)
I0605 23:00:04.181040 54715 net.cpp:165] Memory required for data: 2783232000
I0605 23:00:04.181042 54715 layer_factory.hpp:77] Creating layer ira_A_concat
I0605 23:00:04.181049 54715 net.cpp:106] Creating Layer ira_A_concat
I0605 23:00:04.181054 54715 net.cpp:454] ira_A_concat <- ira_A_1_conv1x1
I0605 23:00:04.181059 54715 net.cpp:454] ira_A_concat <- ira_A_2_conv3x3
I0605 23:00:04.181064 54715 net.cpp:454] ira_A_concat <- ira_A_3_conv3x3_2
I0605 23:00:04.181071 54715 net.cpp:411] ira_A_concat -> ira_A_concat
I0605 23:00:04.181097 54715 net.cpp:150] Setting up ira_A_concat
I0605 23:00:04.181102 54715 net.cpp:157] Top shape: 5 128 80 80 (4096000)
I0605 23:00:04.181107 54715 net.cpp:165] Memory required for data: 2799616000
I0605 23:00:04.181110 54715 layer_factory.hpp:77] Creating layer ira_A_concat_top_conv_1x1
I0605 23:00:04.181120 54715 net.cpp:106] Creating Layer ira_A_concat_top_conv_1x1
I0605 23:00:04.181129 54715 net.cpp:454] ira_A_concat_top_conv_1x1 <- ira_A_concat
I0605 23:00:04.181143 54715 net.cpp:411] ira_A_concat_top_conv_1x1 -> ira_A_concat_top_conv_1x1
I0605 23:00:04.181653 54715 net.cpp:150] Setting up ira_A_concat_top_conv_1x1
I0605 23:00:04.181663 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.181668 54715 net.cpp:165] Memory required for data: 2848768000
I0605 23:00:04.181674 54715 layer_factory.hpp:77] Creating layer bn_ra_A_concat_top_conv_1x1
I0605 23:00:04.181681 54715 net.cpp:106] Creating Layer bn_ra_A_concat_top_conv_1x1
I0605 23:00:04.181686 54715 net.cpp:454] bn_ra_A_concat_top_conv_1x1 <- ira_A_concat_top_conv_1x1
I0605 23:00:04.181694 54715 net.cpp:397] bn_ra_A_concat_top_conv_1x1 -> ira_A_concat_top_conv_1x1 (in-place)
I0605 23:00:04.181864 54715 net.cpp:150] Setting up bn_ra_A_concat_top_conv_1x1
I0605 23:00:04.181872 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.181879 54715 net.cpp:165] Memory required for data: 2897920000
I0605 23:00:04.181886 54715 layer_factory.hpp:77] Creating layer scale_ra_A_concat_top_conv_1x1
I0605 23:00:04.181893 54715 net.cpp:106] Creating Layer scale_ra_A_concat_top_conv_1x1
I0605 23:00:04.181897 54715 net.cpp:454] scale_ra_A_concat_top_conv_1x1 <- ira_A_concat_top_conv_1x1
I0605 23:00:04.181905 54715 net.cpp:397] scale_ra_A_concat_top_conv_1x1 -> ira_A_concat_top_conv_1x1 (in-place)
I0605 23:00:04.181938 54715 layer_factory.hpp:77] Creating layer scale_ra_A_concat_top_conv_1x1
I0605 23:00:04.182046 54715 net.cpp:150] Setting up scale_ra_A_concat_top_conv_1x1
I0605 23:00:04.182054 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182059 54715 net.cpp:165] Memory required for data: 2947072000
I0605 23:00:04.182065 54715 layer_factory.hpp:77] Creating layer conv3_sum
I0605 23:00:04.182073 54715 net.cpp:106] Creating Layer conv3_sum
I0605 23:00:04.182078 54715 net.cpp:454] conv3_sum <- conv3_1b_relu3_1b_0_split_3
I0605 23:00:04.182085 54715 net.cpp:454] conv3_sum <- ira_A_concat_top_conv_1x1
I0605 23:00:04.182091 54715 net.cpp:411] conv3_sum -> conv3_sum
I0605 23:00:04.182121 54715 net.cpp:150] Setting up conv3_sum
I0605 23:00:04.182127 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182132 54715 net.cpp:165] Memory required for data: 2996224000
I0605 23:00:04.182137 54715 layer_factory.hpp:77] Creating layer relu3_sum
I0605 23:00:04.182143 54715 net.cpp:106] Creating Layer relu3_sum
I0605 23:00:04.182147 54715 net.cpp:454] relu3_sum <- conv3_sum
I0605 23:00:04.182155 54715 net.cpp:397] relu3_sum -> conv3_sum (in-place)
I0605 23:00:04.182162 54715 net.cpp:150] Setting up relu3_sum
I0605 23:00:04.182166 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182170 54715 net.cpp:165] Memory required for data: 3045376000
I0605 23:00:04.182175 54715 layer_factory.hpp:77] Creating layer conv3_sum_relu3_sum_0_split
I0605 23:00:04.182183 54715 net.cpp:106] Creating Layer conv3_sum_relu3_sum_0_split
I0605 23:00:04.182186 54715 net.cpp:454] conv3_sum_relu3_sum_0_split <- conv3_sum
I0605 23:00:04.182193 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_0
I0605 23:00:04.182204 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_1
I0605 23:00:04.182211 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_2
I0605 23:00:04.182219 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_3
I0605 23:00:04.182227 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_4
I0605 23:00:04.182235 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_5
I0605 23:00:04.182243 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_6
I0605 23:00:04.182250 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_7
I0605 23:00:04.182350 54715 net.cpp:150] Setting up conv3_sum_relu3_sum_0_split
I0605 23:00:04.182358 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182368 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182379 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182384 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182389 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182394 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182399 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182404 54715 net.cpp:157] Top shape: 5 384 80 80 (12288000)
I0605 23:00:04.182409 54715 net.cpp:165] Memory required for data: 3438592000
I0605 23:00:04.182413 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/pool
I0605 23:00:04.182421 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/pool
I0605 23:00:04.182426 54715 net.cpp:454] ira_v4_reduction_A/pool <- conv3_sum_relu3_sum_0_split_0
I0605 23:00:04.182435 54715 net.cpp:411] ira_v4_reduction_A/pool -> ira_v4_reduction_A/pool
I0605 23:00:04.182474 54715 net.cpp:150] Setting up ira_v4_reduction_A/pool
I0605 23:00:04.182482 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.182485 54715 net.cpp:165] Memory required for data: 3450880000
I0605 23:00:04.182490 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.182499 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.182504 54715 net.cpp:454] ira_v4_reduction_A/conv3x3_reduction_b <- conv3_sum_relu3_sum_0_split_1
I0605 23:00:04.182512 54715 net.cpp:411] ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193280 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193305 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.193310 54715 net.cpp:165] Memory required for data: 3463168000
I0605 23:00:04.193320 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193331 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193338 54715 net.cpp:454] bn_ira_v4_reduction_A/conv3x3_reduction_b <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193346 54715 net.cpp:397] bn_ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b (in-place)
I0605 23:00:04.193536 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193544 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.193548 54715 net.cpp:165] Memory required for data: 3475456000
I0605 23:00:04.193557 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193565 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193570 54715 net.cpp:454] scale_ira_v4_reduction_A/conv3x3_reduction_b <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193578 54715 net.cpp:397] scale_ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b (in-place)
I0605 23:00:04.193615 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193734 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193743 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.193748 54715 net.cpp:165] Memory required for data: 3487744000
I0605 23:00:04.193754 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193763 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193768 54715 net.cpp:454] relu_ira_v4_reduction_A/conv3x3_reduction_b <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193775 54715 net.cpp:397] relu_ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b (in-place)
I0605 23:00:04.193783 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.193789 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.193792 54715 net.cpp:165] Memory required for data: 3500032000
I0605 23:00:04.193805 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.193823 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.193830 54715 net.cpp:454] ira_v4_reduction_A/conv1x1_c <- conv3_sum_relu3_sum_0_split_2
I0605 23:00:04.193840 54715 net.cpp:411] ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194659 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194669 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.194672 54715 net.cpp:165] Memory required for data: 3532800000
I0605 23:00:04.194680 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194687 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194692 54715 net.cpp:454] bn_ira_v4_reduction_A/conv1x1_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194700 54715 net.cpp:397] bn_ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c (in-place)
I0605 23:00:04.194877 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194885 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.194888 54715 net.cpp:165] Memory required for data: 3565568000
I0605 23:00:04.194916 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194923 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194928 54715 net.cpp:454] scale_ira_v4_reduction_A/conv1x1_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.194936 54715 net.cpp:397] scale_ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c (in-place)
I0605 23:00:04.194977 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195088 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195097 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.195101 54715 net.cpp:165] Memory required for data: 3598336000
I0605 23:00:04.195107 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195116 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195119 54715 net.cpp:454] relu_ira_v4_reduction_A/conv1x1_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195127 54715 net.cpp:397] relu_ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c (in-place)
I0605 23:00:04.195132 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195139 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.195142 54715 net.cpp:165] Memory required for data: 3631104000
I0605 23:00:04.195147 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.195155 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.195161 54715 net.cpp:454] ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:04.195168 54715 net.cpp:411] ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200107 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200129 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.200135 54715 net.cpp:165] Memory required for data: 3663872000
I0605 23:00:04.200158 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200170 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200176 54715 net.cpp:454] bn_ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200184 54715 net.cpp:397] bn_ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c (in-place)
I0605 23:00:04.200364 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200372 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.200376 54715 net.cpp:165] Memory required for data: 3696640000
I0605 23:00:04.200386 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200393 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200413 54715 net.cpp:454] scale_ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200420 54715 net.cpp:397] scale_ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c (in-place)
I0605 23:00:04.200465 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200573 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200582 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.200585 54715 net.cpp:165] Memory required for data: 3729408000
I0605 23:00:04.200593 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200600 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200605 54715 net.cpp:454] relu_ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200613 54715 net.cpp:397] relu_ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c (in-place)
I0605 23:00:04.200620 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200625 54715 net.cpp:157] Top shape: 5 256 80 80 (8192000)
I0605 23:00:04.200629 54715 net.cpp:165] Memory required for data: 3762176000
I0605 23:00:04.200633 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.200644 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.200647 54715 net.cpp:454] ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:04.200656 54715 net.cpp:411] ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207634 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207669 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.207672 54715 net.cpp:165] Memory required for data: 3774464000
I0605 23:00:04.207682 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207693 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207701 54715 net.cpp:454] bn_ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207710 54715 net.cpp:397] bn_ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c (in-place)
I0605 23:00:04.207901 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207909 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.207914 54715 net.cpp:165] Memory required for data: 3786752000
I0605 23:00:04.207922 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207931 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207937 54715 net.cpp:454] scale_ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.207943 54715 net.cpp:397] scale_ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c (in-place)
I0605 23:00:04.207983 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208103 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208112 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.208117 54715 net.cpp:165] Memory required for data: 3799040000
I0605 23:00:04.208122 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208132 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208137 54715 net.cpp:454] relu_ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208165 54715 net.cpp:397] relu_ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c (in-place)
I0605 23:00:04.208173 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208179 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.208200 54715 net.cpp:165] Memory required for data: 3811328000
I0605 23:00:04.208206 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/concat
I0605 23:00:04.208214 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/concat
I0605 23:00:04.208218 54715 net.cpp:454] ira_v4_reduction_A/concat <- ira_v4_reduction_A/pool
I0605 23:00:04.208225 54715 net.cpp:454] ira_v4_reduction_A/concat <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:04.208230 54715 net.cpp:454] ira_v4_reduction_A/concat <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:04.208236 54715 net.cpp:411] ira_v4_reduction_A/concat -> ira_v4_reduction_A/concat
I0605 23:00:04.208268 54715 net.cpp:150] Setting up ira_v4_reduction_A/concat
I0605 23:00:04.208276 54715 net.cpp:157] Top shape: 5 1152 40 40 (9216000)
I0605 23:00:04.208281 54715 net.cpp:165] Memory required for data: 3848192000
I0605 23:00:04.208284 54715 layer_factory.hpp:77] Creating layer conv4_1b
I0605 23:00:04.208294 54715 net.cpp:106] Creating Layer conv4_1b
I0605 23:00:04.208299 54715 net.cpp:454] conv4_1b <- ira_v4_reduction_A/concat
I0605 23:00:04.208308 54715 net.cpp:411] conv4_1b -> conv4_1b
I0605 23:00:04.218451 54715 net.cpp:150] Setting up conv4_1b
I0605 23:00:04.218474 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.218478 54715 net.cpp:165] Memory required for data: 3885120000
I0605 23:00:04.218489 54715 layer_factory.hpp:77] Creating layer bn_conv4_1b
I0605 23:00:04.218499 54715 net.cpp:106] Creating Layer bn_conv4_1b
I0605 23:00:04.218506 54715 net.cpp:454] bn_conv4_1b <- conv4_1b
I0605 23:00:04.218513 54715 net.cpp:397] bn_conv4_1b -> conv4_1b (in-place)
I0605 23:00:04.218713 54715 net.cpp:150] Setting up bn_conv4_1b
I0605 23:00:04.218721 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.218725 54715 net.cpp:165] Memory required for data: 3922048000
I0605 23:00:04.218734 54715 layer_factory.hpp:77] Creating layer scale_conv4_1b
I0605 23:00:04.218744 54715 net.cpp:106] Creating Layer scale_conv4_1b
I0605 23:00:04.218750 54715 net.cpp:454] scale_conv4_1b <- conv4_1b
I0605 23:00:04.218755 54715 net.cpp:397] scale_conv4_1b -> conv4_1b (in-place)
I0605 23:00:04.218801 54715 layer_factory.hpp:77] Creating layer scale_conv4_1b
I0605 23:00:04.218924 54715 net.cpp:150] Setting up scale_conv4_1b
I0605 23:00:04.218933 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.218937 54715 net.cpp:165] Memory required for data: 3958976000
I0605 23:00:04.218945 54715 layer_factory.hpp:77] Creating layer relu4_1b
I0605 23:00:04.218952 54715 net.cpp:106] Creating Layer relu4_1b
I0605 23:00:04.218957 54715 net.cpp:454] relu4_1b <- conv4_1b
I0605 23:00:04.218963 54715 net.cpp:397] relu4_1b -> conv4_1b (in-place)
I0605 23:00:04.218971 54715 net.cpp:150] Setting up relu4_1b
I0605 23:00:04.218977 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.218981 54715 net.cpp:165] Memory required for data: 3995904000
I0605 23:00:04.218984 54715 layer_factory.hpp:77] Creating layer conv4_1b_relu4_1b_0_split
I0605 23:00:04.218991 54715 net.cpp:106] Creating Layer conv4_1b_relu4_1b_0_split
I0605 23:00:04.218997 54715 net.cpp:454] conv4_1b_relu4_1b_0_split <- conv4_1b
I0605 23:00:04.219002 54715 net.cpp:411] conv4_1b_relu4_1b_0_split -> conv4_1b_relu4_1b_0_split_0
I0605 23:00:04.219012 54715 net.cpp:411] conv4_1b_relu4_1b_0_split -> conv4_1b_relu4_1b_0_split_1
I0605 23:00:04.219018 54715 net.cpp:411] conv4_1b_relu4_1b_0_split -> conv4_1b_relu4_1b_0_split_2
I0605 23:00:04.219071 54715 net.cpp:150] Setting up conv4_1b_relu4_1b_0_split
I0605 23:00:04.219079 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.219084 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.219087 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.219092 54715 net.cpp:165] Memory required for data: 4106688000
I0605 23:00:04.219096 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.219106 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.219127 54715 net.cpp:454] ira_Inception_B_block_1/a_conv1x1_1 <- conv4_1b_relu4_1b_0_split_0
I0605 23:00:04.219138 54715 net.cpp:411] ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222476 54715 net.cpp:150] Setting up ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222494 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.222498 54715 net.cpp:165] Memory required for data: 4112832000
I0605 23:00:04.222507 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222517 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222522 54715 net.cpp:454] bn_ira_Inception_B_block_1/a_conv1x1_1 <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222529 54715 net.cpp:397] bn_ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1 (in-place)
I0605 23:00:04.222726 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222734 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.222738 54715 net.cpp:165] Memory required for data: 4118976000
I0605 23:00:04.222746 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222756 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222760 54715 net.cpp:454] scale_ira_Inception_B_block_1/a_conv1x1_1 <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222766 54715 net.cpp:397] scale_ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1 (in-place)
I0605 23:00:04.222808 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222930 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222939 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.222942 54715 net.cpp:165] Memory required for data: 4125120000
I0605 23:00:04.222949 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222957 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222961 54715 net.cpp:454] relu_ira_Inception_B_block_1/a_conv1x1_1 <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222967 54715 net.cpp:397] relu_ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1 (in-place)
I0605 23:00:04.222975 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.222980 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.222985 54715 net.cpp:165] Memory required for data: 4131264000
I0605 23:00:04.222987 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.222996 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.223002 54715 net.cpp:454] ira_Inception_B_block_1/b_conv1x1_1 <- conv4_1b_relu4_1b_0_split_1
I0605 23:00:04.223011 54715 net.cpp:411] ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224035 54715 net.cpp:150] Setting up ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224045 54715 net.cpp:157] Top shape: 5 128 40 40 (1024000)
I0605 23:00:04.224050 54715 net.cpp:165] Memory required for data: 4135360000
I0605 23:00:04.224056 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224064 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224068 54715 net.cpp:454] bn_ira_Inception_B_block_1/b_conv1x1_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224076 54715 net.cpp:397] bn_ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.224284 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224294 54715 net.cpp:157] Top shape: 5 128 40 40 (1024000)
I0605 23:00:04.224298 54715 net.cpp:165] Memory required for data: 4139456000
I0605 23:00:04.224308 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224328 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224333 54715 net.cpp:454] scale_ira_Inception_B_block_1/b_conv1x1_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224339 54715 net.cpp:397] scale_ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.224382 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224493 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224501 54715 net.cpp:157] Top shape: 5 128 40 40 (1024000)
I0605 23:00:04.224505 54715 net.cpp:165] Memory required for data: 4143552000
I0605 23:00:04.224512 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224519 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224524 54715 net.cpp:454] relu_ira_Inception_B_block_1/b_conv1x1_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224530 54715 net.cpp:397] relu_ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.224537 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224544 54715 net.cpp:157] Top shape: 5 128 40 40 (1024000)
I0605 23:00:04.224547 54715 net.cpp:165] Memory required for data: 4147648000
I0605 23:00:04.224550 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.224560 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.224563 54715 net.cpp:454] ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:04.224570 54715 net.cpp:411] ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225584 54715 net.cpp:150] Setting up ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225595 54715 net.cpp:157] Top shape: 5 160 40 40 (1280000)
I0605 23:00:04.225600 54715 net.cpp:165] Memory required for data: 4152768000
I0605 23:00:04.225605 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225613 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225618 54715 net.cpp:454] bn_ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225625 54715 net.cpp:397] bn_ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1 (in-place)
I0605 23:00:04.225816 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225822 54715 net.cpp:157] Top shape: 5 160 40 40 (1280000)
I0605 23:00:04.225827 54715 net.cpp:165] Memory required for data: 4157888000
I0605 23:00:04.225836 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225842 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225847 54715 net.cpp:454] scale_ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.225853 54715 net.cpp:397] scale_ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1 (in-place)
I0605 23:00:04.225894 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226014 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226022 54715 net.cpp:157] Top shape: 5 160 40 40 (1280000)
I0605 23:00:04.226027 54715 net.cpp:165] Memory required for data: 4163008000
I0605 23:00:04.226033 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226040 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226044 54715 net.cpp:454] relu_ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226052 54715 net.cpp:397] relu_ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1 (in-place)
I0605 23:00:04.226063 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226075 54715 net.cpp:157] Top shape: 5 160 40 40 (1280000)
I0605 23:00:04.226079 54715 net.cpp:165] Memory required for data: 4168128000
I0605 23:00:04.226084 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.226091 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.226096 54715 net.cpp:454] ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:04.226104 54715 net.cpp:411] ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227599 54715 net.cpp:150] Setting up ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227608 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.227612 54715 net.cpp:165] Memory required for data: 4174272000
I0605 23:00:04.227618 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227627 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227632 54715 net.cpp:454] bn_ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227638 54715 net.cpp:397] bn_ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1 (in-place)
I0605 23:00:04.227831 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227839 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.227843 54715 net.cpp:165] Memory required for data: 4180416000
I0605 23:00:04.227851 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227859 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227864 54715 net.cpp:454] scale_ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.227869 54715 net.cpp:397] scale_ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1 (in-place)
I0605 23:00:04.227910 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228030 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228039 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.228044 54715 net.cpp:165] Memory required for data: 4186560000
I0605 23:00:04.228050 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228056 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228062 54715 net.cpp:454] relu_ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228068 54715 net.cpp:397] relu_ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1 (in-place)
I0605 23:00:04.228075 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228080 54715 net.cpp:157] Top shape: 5 192 40 40 (1536000)
I0605 23:00:04.228085 54715 net.cpp:165] Memory required for data: 4192704000
I0605 23:00:04.228088 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/concat
I0605 23:00:04.228094 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/concat
I0605 23:00:04.228098 54715 net.cpp:454] ira_Inception_B_block_1/concat <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:04.228104 54715 net.cpp:454] ira_Inception_B_block_1/concat <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:04.228111 54715 net.cpp:411] ira_Inception_B_block_1/concat -> ira_Inception_B_block_1/concat
I0605 23:00:04.228152 54715 net.cpp:150] Setting up ira_Inception_B_block_1/concat
I0605 23:00:04.228161 54715 net.cpp:157] Top shape: 5 384 40 40 (3072000)
I0605 23:00:04.228166 54715 net.cpp:165] Memory required for data: 4204992000
I0605 23:00:04.228170 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.228180 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.228185 54715 net.cpp:454] ira_Inception_B_block_1/top_conv_1x1 <- ira_Inception_B_block_1/concat
I0605 23:00:04.228204 54715 net.cpp:411] ira_Inception_B_block_1/top_conv_1x1 -> ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.232498 54715 net.cpp:150] Setting up ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.232517 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.232520 54715 net.cpp:165] Memory required for data: 4241920000
I0605 23:00:04.232529 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.232539 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.232544 54715 net.cpp:454] bn_ira_Inception_B_block_1/top_conv_1x1 <- ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.232551 54715 net.cpp:397] bn_ira_Inception_B_block_1/top_conv_1x1 -> ira_Inception_B_block_1/top_conv_1x1 (in-place)
I0605 23:00:04.234025 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234035 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234038 54715 net.cpp:165] Memory required for data: 4278848000
I0605 23:00:04.234046 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234056 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234061 54715 net.cpp:454] scale_ira_Inception_B_block_1/top_conv_1x1 <- ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234068 54715 net.cpp:397] scale_ira_Inception_B_block_1/top_conv_1x1 -> ira_Inception_B_block_1/top_conv_1x1 (in-place)
I0605 23:00:04.234113 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234236 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234244 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234248 54715 net.cpp:165] Memory required for data: 4315776000
I0605 23:00:04.234256 54715 layer_factory.hpp:77] Creating layer conv4_sum
I0605 23:00:04.234266 54715 net.cpp:106] Creating Layer conv4_sum
I0605 23:00:04.234272 54715 net.cpp:454] conv4_sum <- conv4_1b_relu4_1b_0_split_2
I0605 23:00:04.234277 54715 net.cpp:454] conv4_sum <- ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:04.234284 54715 net.cpp:411] conv4_sum -> conv4_sum
I0605 23:00:04.234313 54715 net.cpp:150] Setting up conv4_sum
I0605 23:00:04.234321 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234325 54715 net.cpp:165] Memory required for data: 4352704000
I0605 23:00:04.234329 54715 layer_factory.hpp:77] Creating layer relu_conv4_sum
I0605 23:00:04.234338 54715 net.cpp:106] Creating Layer relu_conv4_sum
I0605 23:00:04.234342 54715 net.cpp:454] relu_conv4_sum <- conv4_sum
I0605 23:00:04.234349 54715 net.cpp:397] relu_conv4_sum -> conv4_sum (in-place)
I0605 23:00:04.234355 54715 net.cpp:150] Setting up relu_conv4_sum
I0605 23:00:04.234362 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234365 54715 net.cpp:165] Memory required for data: 4389632000
I0605 23:00:04.234369 54715 layer_factory.hpp:77] Creating layer conv4_sum_relu_conv4_sum_0_split
I0605 23:00:04.234377 54715 net.cpp:106] Creating Layer conv4_sum_relu_conv4_sum_0_split
I0605 23:00:04.234382 54715 net.cpp:454] conv4_sum_relu_conv4_sum_0_split <- conv4_sum
I0605 23:00:04.234390 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_0
I0605 23:00:04.234397 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_1
I0605 23:00:04.234405 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_2
I0605 23:00:04.234431 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_3
I0605 23:00:04.234438 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_4
I0605 23:00:04.234446 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_5
I0605 23:00:04.234452 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_6
I0605 23:00:04.234469 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_7
I0605 23:00:04.234484 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_8
I0605 23:00:04.234603 54715 net.cpp:150] Setting up conv4_sum_relu_conv4_sum_0_split
I0605 23:00:04.234611 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234616 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234622 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234627 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234632 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234637 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234640 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234645 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234649 54715 net.cpp:157] Top shape: 5 1154 40 40 (9232000)
I0605 23:00:04.234654 54715 net.cpp:165] Memory required for data: 4721984000
I0605 23:00:04.234658 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/a_pool
I0605 23:00:04.234666 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/a_pool
I0605 23:00:04.234670 54715 net.cpp:454] ira_Reduction_B_block_1/a_pool <- conv4_sum_relu_conv4_sum_0_split_0
I0605 23:00:04.234679 54715 net.cpp:411] ira_Reduction_B_block_1/a_pool -> ira_Reduction_B_block_1/a_pool
I0605 23:00:04.234719 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/a_pool
I0605 23:00:04.234725 54715 net.cpp:157] Top shape: 5 1154 20 20 (2308000)
I0605 23:00:04.234730 54715 net.cpp:165] Memory required for data: 4731216000
I0605 23:00:04.234735 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.234743 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.234748 54715 net.cpp:454] ira_Reduction_B_block_1/b_conv1x1_1 <- conv4_sum_relu_conv4_sum_0_split_1
I0605 23:00:04.234755 54715 net.cpp:411] ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236629 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236640 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.236644 54715 net.cpp:165] Memory required for data: 4739408000
I0605 23:00:04.236651 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236660 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236665 54715 net.cpp:454] bn_ira_Reduction_B_block_1/b_conv1x1_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236672 54715 net.cpp:397] bn_ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.236858 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236869 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.236874 54715 net.cpp:165] Memory required for data: 4747600000
I0605 23:00:04.236882 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236915 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236922 54715 net.cpp:454] scale_ira_Reduction_B_block_1/b_conv1x1_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.236927 54715 net.cpp:397] scale_ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.236969 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237082 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237092 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.237095 54715 net.cpp:165] Memory required for data: 4755792000
I0605 23:00:04.237102 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237109 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237120 54715 net.cpp:454] relu_ira_Reduction_B_block_1/b_conv1x1_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237133 54715 net.cpp:397] relu_ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.237140 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237146 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.237150 54715 net.cpp:165] Memory required for data: 4763984000
I0605 23:00:04.237154 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.237164 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.237167 54715 net.cpp:454] ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:04.237176 54715 net.cpp:411] ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244177 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244207 54715 net.cpp:157] Top shape: 5 384 20 20 (768000)
I0605 23:00:04.244211 54715 net.cpp:165] Memory required for data: 4767056000
I0605 23:00:04.244222 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244233 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244240 54715 net.cpp:454] bn_ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244248 54715 net.cpp:397] bn_ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1 (in-place)
I0605 23:00:04.244439 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244446 54715 net.cpp:157] Top shape: 5 384 20 20 (768000)
I0605 23:00:04.244451 54715 net.cpp:165] Memory required for data: 4770128000
I0605 23:00:04.244459 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244469 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244473 54715 net.cpp:454] scale_ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244480 54715 net.cpp:397] scale_ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1 (in-place)
I0605 23:00:04.244529 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244637 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244645 54715 net.cpp:157] Top shape: 5 384 20 20 (768000)
I0605 23:00:04.244650 54715 net.cpp:165] Memory required for data: 4773200000
I0605 23:00:04.244657 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244665 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244670 54715 net.cpp:454] relu_ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244678 54715 net.cpp:397] relu_ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1 (in-place)
I0605 23:00:04.244684 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.244690 54715 net.cpp:157] Top shape: 5 384 20 20 (768000)
I0605 23:00:04.244694 54715 net.cpp:165] Memory required for data: 4776272000
I0605 23:00:04.244699 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.244709 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.244714 54715 net.cpp:454] ira_Reduction_B_block_1/c_conv1x1_1 <- conv4_sum_relu_conv4_sum_0_split_2
I0605 23:00:04.244721 54715 net.cpp:411] ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.247970 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.247987 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.247992 54715 net.cpp:165] Memory required for data: 4784464000
I0605 23:00:04.248000 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248026 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248033 54715 net.cpp:454] bn_ira_Reduction_B_block_1/c_conv1x1_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248040 54715 net.cpp:397] bn_ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1 (in-place)
I0605 23:00:04.248262 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248272 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.248276 54715 net.cpp:165] Memory required for data: 4792656000
I0605 23:00:04.248286 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248294 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248299 54715 net.cpp:454] scale_ira_Reduction_B_block_1/c_conv1x1_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248306 54715 net.cpp:397] scale_ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1 (in-place)
I0605 23:00:04.248353 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248472 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248481 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.248484 54715 net.cpp:165] Memory required for data: 4800848000
I0605 23:00:04.248492 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248499 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248503 54715 net.cpp:454] relu_ira_Reduction_B_block_1/c_conv1x1_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248510 54715 net.cpp:397] relu_ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1 (in-place)
I0605 23:00:04.248517 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248523 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.248528 54715 net.cpp:165] Memory required for data: 4809040000
I0605 23:00:04.248531 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.248541 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.248546 54715 net.cpp:454] ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:04.248554 54715 net.cpp:411] ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.253978 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254001 54715 net.cpp:157] Top shape: 5 288 20 20 (576000)
I0605 23:00:04.254006 54715 net.cpp:165] Memory required for data: 4811344000
I0605 23:00:04.254014 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254025 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254032 54715 net.cpp:454] bn_ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254040 54715 net.cpp:397] bn_ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1 (in-place)
I0605 23:00:04.254240 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254247 54715 net.cpp:157] Top shape: 5 288 20 20 (576000)
I0605 23:00:04.254252 54715 net.cpp:165] Memory required for data: 4813648000
I0605 23:00:04.254261 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254269 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254274 54715 net.cpp:454] scale_ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254281 54715 net.cpp:397] scale_ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1 (in-place)
I0605 23:00:04.254328 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254451 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254474 54715 net.cpp:157] Top shape: 5 288 20 20 (576000)
I0605 23:00:04.254480 54715 net.cpp:165] Memory required for data: 4815952000
I0605 23:00:04.254487 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254494 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254499 54715 net.cpp:454] relu_ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254506 54715 net.cpp:397] relu_ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1 (in-place)
I0605 23:00:04.254513 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.254519 54715 net.cpp:157] Top shape: 5 288 20 20 (576000)
I0605 23:00:04.254523 54715 net.cpp:165] Memory required for data: 4818256000
I0605 23:00:04.254528 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.254539 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.254544 54715 net.cpp:454] ira_Reduction_B_block_1/d_conv1x1_1 <- conv4_sum_relu_conv4_sum_0_split_3
I0605 23:00:04.254551 54715 net.cpp:411] ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.257791 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.257808 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.257812 54715 net.cpp:165] Memory required for data: 4826448000
I0605 23:00:04.257820 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.257831 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.257836 54715 net.cpp:454] bn_ira_Reduction_B_block_1/d_conv1x1_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.257844 54715 net.cpp:397] bn_ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1 (in-place)
I0605 23:00:04.258038 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258046 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.258050 54715 net.cpp:165] Memory required for data: 4834640000
I0605 23:00:04.258059 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258066 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258072 54715 net.cpp:454] scale_ira_Reduction_B_block_1/d_conv1x1_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258080 54715 net.cpp:397] scale_ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1 (in-place)
I0605 23:00:04.258123 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258239 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258249 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.258252 54715 net.cpp:165] Memory required for data: 4842832000
I0605 23:00:04.258258 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258267 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258272 54715 net.cpp:454] relu_ira_Reduction_B_block_1/d_conv1x1_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258280 54715 net.cpp:397] relu_ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1 (in-place)
I0605 23:00:04.258286 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258291 54715 net.cpp:157] Top shape: 5 256 40 40 (2048000)
I0605 23:00:04.258296 54715 net.cpp:165] Memory required for data: 4851024000
I0605 23:00:04.258299 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.258308 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.258312 54715 net.cpp:454] ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:04.258330 54715 net.cpp:411] ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.263793 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.263815 54715 net.cpp:157] Top shape: 5 288 40 40 (2304000)
I0605 23:00:04.263819 54715 net.cpp:165] Memory required for data: 4860240000
I0605 23:00:04.263829 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.263839 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.263846 54715 net.cpp:454] bn_ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.263855 54715 net.cpp:397] bn_ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1 (in-place)
I0605 23:00:04.264075 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264083 54715 net.cpp:157] Top shape: 5 288 40 40 (2304000)
I0605 23:00:04.264087 54715 net.cpp:165] Memory required for data: 4869456000
I0605 23:00:04.264096 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264106 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264109 54715 net.cpp:454] scale_ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264117 54715 net.cpp:397] scale_ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1 (in-place)
I0605 23:00:04.264184 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264315 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264324 54715 net.cpp:157] Top shape: 5 288 40 40 (2304000)
I0605 23:00:04.264328 54715 net.cpp:165] Memory required for data: 4878672000
I0605 23:00:04.264334 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264345 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264349 54715 net.cpp:454] relu_ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264356 54715 net.cpp:397] relu_ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1 (in-place)
I0605 23:00:04.264364 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264370 54715 net.cpp:157] Top shape: 5 288 40 40 (2304000)
I0605 23:00:04.264374 54715 net.cpp:165] Memory required for data: 4887888000
I0605 23:00:04.264377 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.264387 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.264392 54715 net.cpp:454] ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:04.264401 54715 net.cpp:411] ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271018 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271040 54715 net.cpp:157] Top shape: 5 320 20 20 (640000)
I0605 23:00:04.271045 54715 net.cpp:165] Memory required for data: 4890448000
I0605 23:00:04.271054 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271065 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271071 54715 net.cpp:454] bn_ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271080 54715 net.cpp:397] bn_ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2 (in-place)
I0605 23:00:04.271286 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271294 54715 net.cpp:157] Top shape: 5 320 20 20 (640000)
I0605 23:00:04.271298 54715 net.cpp:165] Memory required for data: 4893008000
I0605 23:00:04.271307 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271317 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271330 54715 net.cpp:454] scale_ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271345 54715 net.cpp:397] scale_ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2 (in-place)
I0605 23:00:04.271397 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271522 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271530 54715 net.cpp:157] Top shape: 5 320 20 20 (640000)
I0605 23:00:04.271534 54715 net.cpp:165] Memory required for data: 4895568000
I0605 23:00:04.271541 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271550 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271555 54715 net.cpp:454] relu_ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271561 54715 net.cpp:397] relu_ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2 (in-place)
I0605 23:00:04.271569 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271574 54715 net.cpp:157] Top shape: 5 320 20 20 (640000)
I0605 23:00:04.271579 54715 net.cpp:165] Memory required for data: 4898128000
I0605 23:00:04.271582 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/concat
I0605 23:00:04.271589 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/concat
I0605 23:00:04.271595 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/a_pool
I0605 23:00:04.271601 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:04.271606 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:04.271612 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:04.271620 54715 net.cpp:411] ira_Reduction_B_block_1/concat -> ira_Reduction_B_block_1/concat
I0605 23:00:04.271649 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/concat
I0605 23:00:04.271656 54715 net.cpp:157] Top shape: 5 2146 20 20 (4292000)
I0605 23:00:04.271661 54715 net.cpp:165] Memory required for data: 4915296000
I0605 23:00:04.271664 54715 layer_factory.hpp:77] Creating layer conv5_1b
I0605 23:00:04.271675 54715 net.cpp:106] Creating Layer conv5_1b
I0605 23:00:04.271680 54715 net.cpp:454] conv5_1b <- ira_Reduction_B_block_1/concat
I0605 23:00:04.271690 54715 net.cpp:411] conv5_1b -> conv5_1b
I0605 23:00:04.305212 54715 net.cpp:150] Setting up conv5_1b
I0605 23:00:04.305236 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305241 54715 net.cpp:165] Memory required for data: 4931680000
I0605 23:00:04.305251 54715 layer_factory.hpp:77] Creating layer bn_conv5_1b
I0605 23:00:04.305260 54715 net.cpp:106] Creating Layer bn_conv5_1b
I0605 23:00:04.305268 54715 net.cpp:454] bn_conv5_1b <- conv5_1b
I0605 23:00:04.305275 54715 net.cpp:397] bn_conv5_1b -> conv5_1b (in-place)
I0605 23:00:04.305480 54715 net.cpp:150] Setting up bn_conv5_1b
I0605 23:00:04.305487 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305491 54715 net.cpp:165] Memory required for data: 4948064000
I0605 23:00:04.305500 54715 layer_factory.hpp:77] Creating layer scale_conv5_1b
I0605 23:00:04.305510 54715 net.cpp:106] Creating Layer scale_conv5_1b
I0605 23:00:04.305513 54715 net.cpp:454] scale_conv5_1b <- conv5_1b
I0605 23:00:04.305519 54715 net.cpp:397] scale_conv5_1b -> conv5_1b (in-place)
I0605 23:00:04.305567 54715 layer_factory.hpp:77] Creating layer scale_conv5_1b
I0605 23:00:04.305692 54715 net.cpp:150] Setting up scale_conv5_1b
I0605 23:00:04.305701 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305706 54715 net.cpp:165] Memory required for data: 4964448000
I0605 23:00:04.305713 54715 layer_factory.hpp:77] Creating layer relu5_1b
I0605 23:00:04.305722 54715 net.cpp:106] Creating Layer relu5_1b
I0605 23:00:04.305727 54715 net.cpp:454] relu5_1b <- conv5_1b
I0605 23:00:04.305742 54715 net.cpp:397] relu5_1b -> conv5_1b (in-place)
I0605 23:00:04.305757 54715 net.cpp:150] Setting up relu5_1b
I0605 23:00:04.305764 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305768 54715 net.cpp:165] Memory required for data: 4980832000
I0605 23:00:04.305773 54715 layer_factory.hpp:77] Creating layer conv5_1b_relu5_1b_0_split
I0605 23:00:04.305779 54715 net.cpp:106] Creating Layer conv5_1b_relu5_1b_0_split
I0605 23:00:04.305784 54715 net.cpp:454] conv5_1b_relu5_1b_0_split <- conv5_1b
I0605 23:00:04.305791 54715 net.cpp:411] conv5_1b_relu5_1b_0_split -> conv5_1b_relu5_1b_0_split_0
I0605 23:00:04.305799 54715 net.cpp:411] conv5_1b_relu5_1b_0_split -> conv5_1b_relu5_1b_0_split_1
I0605 23:00:04.305807 54715 net.cpp:411] conv5_1b_relu5_1b_0_split -> conv5_1b_relu5_1b_0_split_2
I0605 23:00:04.305863 54715 net.cpp:150] Setting up conv5_1b_relu5_1b_0_split
I0605 23:00:04.305871 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305876 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305879 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.305884 54715 net.cpp:165] Memory required for data: 5029984000
I0605 23:00:04.305888 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.305897 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.305902 54715 net.cpp:454] ira_Inception_C_block_1/a_conv1x1_1 <- conv5_1b_relu5_1b_0_split_0
I0605 23:00:04.305912 54715 net.cpp:411] ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309698 54715 net.cpp:150] Setting up ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309716 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.309721 54715 net.cpp:165] Memory required for data: 5031520000
I0605 23:00:04.309731 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309741 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309746 54715 net.cpp:454] bn_ira_Inception_C_block_1/a_conv1x1_1 <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309754 54715 net.cpp:397] bn_ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1 (in-place)
I0605 23:00:04.309960 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309968 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.309973 54715 net.cpp:165] Memory required for data: 5033056000
I0605 23:00:04.309983 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309991 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.309996 54715 net.cpp:454] scale_ira_Inception_C_block_1/a_conv1x1_1 <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310003 54715 net.cpp:397] scale_ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1 (in-place)
I0605 23:00:04.310050 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310174 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310184 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.310187 54715 net.cpp:165] Memory required for data: 5034592000
I0605 23:00:04.310194 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310204 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310209 54715 net.cpp:454] relu_ira_Inception_C_block_1/a_conv1x1_1 <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310215 54715 net.cpp:397] relu_ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1 (in-place)
I0605 23:00:04.310222 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.310230 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.310233 54715 net.cpp:165] Memory required for data: 5036128000
I0605 23:00:04.310237 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.310261 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.310267 54715 net.cpp:454] ira_Inception_C_block_1/b_conv1x1_1 <- conv5_1b_relu5_1b_0_split_1
I0605 23:00:04.310276 54715 net.cpp:411] ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314000 54715 net.cpp:150] Setting up ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314018 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.314023 54715 net.cpp:165] Memory required for data: 5037664000
I0605 23:00:04.314031 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314041 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314047 54715 net.cpp:454] bn_ira_Inception_C_block_1/b_conv1x1_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314055 54715 net.cpp:397] bn_ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.314258 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314266 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.314270 54715 net.cpp:165] Memory required for data: 5039200000
I0605 23:00:04.314313 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314322 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314327 54715 net.cpp:454] scale_ira_Inception_C_block_1/b_conv1x1_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314333 54715 net.cpp:397] scale_ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.314384 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314509 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314517 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.314522 54715 net.cpp:165] Memory required for data: 5040736000
I0605 23:00:04.314529 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314538 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314543 54715 net.cpp:454] relu_ira_Inception_C_block_1/b_conv1x1_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314549 54715 net.cpp:397] relu_ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1 (in-place)
I0605 23:00:04.314558 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314563 54715 net.cpp:157] Top shape: 5 192 20 20 (384000)
I0605 23:00:04.314568 54715 net.cpp:165] Memory required for data: 5042272000
I0605 23:00:04.314571 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.314581 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.314585 54715 net.cpp:454] ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:04.314594 54715 net.cpp:411] ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.315798 54715 net.cpp:150] Setting up ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.315810 54715 net.cpp:157] Top shape: 5 224 20 20 (448000)
I0605 23:00:04.315814 54715 net.cpp:165] Memory required for data: 5044064000
I0605 23:00:04.315821 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.315829 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.315835 54715 net.cpp:454] bn_ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.315842 54715 net.cpp:397] bn_ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1 (in-place)
I0605 23:00:04.316040 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316048 54715 net.cpp:157] Top shape: 5 224 20 20 (448000)
I0605 23:00:04.316059 54715 net.cpp:165] Memory required for data: 5045856000
I0605 23:00:04.316076 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316084 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316088 54715 net.cpp:454] scale_ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316095 54715 net.cpp:397] scale_ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1 (in-place)
I0605 23:00:04.316165 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316293 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316301 54715 net.cpp:157] Top shape: 5 224 20 20 (448000)
I0605 23:00:04.316306 54715 net.cpp:165] Memory required for data: 5047648000
I0605 23:00:04.316313 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316320 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316325 54715 net.cpp:454] relu_ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316334 54715 net.cpp:397] relu_ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1 (in-place)
I0605 23:00:04.316339 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316345 54715 net.cpp:157] Top shape: 5 224 20 20 (448000)
I0605 23:00:04.316349 54715 net.cpp:165] Memory required for data: 5049440000
I0605 23:00:04.316354 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.316361 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.316366 54715 net.cpp:454] ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:04.316375 54715 net.cpp:411] ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317628 54715 net.cpp:150] Setting up ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317637 54715 net.cpp:157] Top shape: 5 256 20 20 (512000)
I0605 23:00:04.317641 54715 net.cpp:165] Memory required for data: 5051488000
I0605 23:00:04.317647 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317656 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317661 54715 net.cpp:454] bn_ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317667 54715 net.cpp:397] bn_ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1 (in-place)
I0605 23:00:04.317859 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317867 54715 net.cpp:157] Top shape: 5 256 20 20 (512000)
I0605 23:00:04.317872 54715 net.cpp:165] Memory required for data: 5053536000
I0605 23:00:04.317879 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317886 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317891 54715 net.cpp:454] scale_ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.317898 54715 net.cpp:397] scale_ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1 (in-place)
I0605 23:00:04.317939 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318053 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318061 54715 net.cpp:157] Top shape: 5 256 20 20 (512000)
I0605 23:00:04.318065 54715 net.cpp:165] Memory required for data: 5055584000
I0605 23:00:04.318071 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318079 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318084 54715 net.cpp:454] relu_ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318096 54715 net.cpp:397] relu_ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1 (in-place)
I0605 23:00:04.318109 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318115 54715 net.cpp:157] Top shape: 5 256 20 20 (512000)
I0605 23:00:04.318120 54715 net.cpp:165] Memory required for data: 5057632000
I0605 23:00:04.318123 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/concat
I0605 23:00:04.318130 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/concat
I0605 23:00:04.318135 54715 net.cpp:454] ira_Inception_C_block_1/concat <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:04.318140 54715 net.cpp:454] ira_Inception_C_block_1/concat <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:04.318148 54715 net.cpp:411] ira_Inception_C_block_1/concat -> ira_Inception_C_block_1/concat
I0605 23:00:04.318179 54715 net.cpp:150] Setting up ira_Inception_C_block_1/concat
I0605 23:00:04.318186 54715 net.cpp:157] Top shape: 5 448 20 20 (896000)
I0605 23:00:04.318192 54715 net.cpp:165] Memory required for data: 5061216000
I0605 23:00:04.318195 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.318205 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.318210 54715 net.cpp:454] ira_Inception_C_block_1/top_conv_1x1 <- ira_Inception_C_block_1/concat
I0605 23:00:04.318218 54715 net.cpp:411] ira_Inception_C_block_1/top_conv_1x1 -> ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325569 54715 net.cpp:150] Setting up ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325608 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.325613 54715 net.cpp:165] Memory required for data: 5077600000
I0605 23:00:04.325624 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325636 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325644 54715 net.cpp:454] bn_ira_Inception_C_block_1/top_conv_1x1 <- ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325654 54715 net.cpp:397] bn_ira_Inception_C_block_1/top_conv_1x1 -> ira_Inception_C_block_1/top_conv_1x1 (in-place)
I0605 23:00:04.325858 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325866 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.325871 54715 net.cpp:165] Memory required for data: 5093984000
I0605 23:00:04.325879 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325889 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325894 54715 net.cpp:454] scale_ira_Inception_C_block_1/top_conv_1x1 <- ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.325901 54715 net.cpp:397] scale_ira_Inception_C_block_1/top_conv_1x1 -> ira_Inception_C_block_1/top_conv_1x1 (in-place)
I0605 23:00:04.325949 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.326074 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.326082 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.326087 54715 net.cpp:165] Memory required for data: 5110368000
I0605 23:00:04.326093 54715 layer_factory.hpp:77] Creating layer conv5_sum
I0605 23:00:04.326104 54715 net.cpp:106] Creating Layer conv5_sum
I0605 23:00:04.326110 54715 net.cpp:454] conv5_sum <- conv5_1b_relu5_1b_0_split_2
I0605 23:00:04.326117 54715 net.cpp:454] conv5_sum <- ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:04.326123 54715 net.cpp:411] conv5_sum -> conv5_sum
I0605 23:00:04.326154 54715 net.cpp:150] Setting up conv5_sum
I0605 23:00:04.326162 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.326166 54715 net.cpp:165] Memory required for data: 5126752000
I0605 23:00:04.326170 54715 layer_factory.hpp:77] Creating layer relu_conv5_sum
I0605 23:00:04.326179 54715 net.cpp:106] Creating Layer relu_conv5_sum
I0605 23:00:04.326184 54715 net.cpp:454] relu_conv5_sum <- conv5_sum
I0605 23:00:04.326201 54715 net.cpp:397] relu_conv5_sum -> conv5_sum (in-place)
I0605 23:00:04.326216 54715 net.cpp:150] Setting up relu_conv5_sum
I0605 23:00:04.326223 54715 net.cpp:157] Top shape: 5 2048 20 20 (4096000)
I0605 23:00:04.326227 54715 net.cpp:165] Memory required for data: 5143136000
I0605 23:00:04.326231 54715 layer_factory.hpp:77] Creating layer deconv5_16x
I0605 23:00:04.326241 54715 net.cpp:106] Creating Layer deconv5_16x
I0605 23:00:04.326246 54715 net.cpp:454] deconv5_16x <- conv5_sum
I0605 23:00:04.326253 54715 net.cpp:411] deconv5_16x -> deconv5_16x
I0605 23:00:04.544704 54715 net.cpp:150] Setting up deconv5_16x
I0605 23:00:04.544752 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.544759 54715 net.cpp:165] Memory required for data: 5147232000
I0605 23:00:04.544770 54715 layer_factory.hpp:77] Creating layer deconv2_2x_d1
I0605 23:00:04.544785 54715 net.cpp:106] Creating Layer deconv2_2x_d1
I0605 23:00:04.544791 54715 net.cpp:454] deconv2_2x_d1 <- concat_stem_1_concat_stem_1_0_split_2
I0605 23:00:04.544805 54715 net.cpp:411] deconv2_2x_d1 -> deconv2_2x_d1
I0605 23:00:04.545464 54715 net.cpp:150] Setting up deconv2_2x_d1
I0605 23:00:04.545475 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.545478 54715 net.cpp:165] Memory required for data: 5151328000
I0605 23:00:04.545485 54715 layer_factory.hpp:77] Creating layer fc1_2x_c0
I0605 23:00:04.545495 54715 net.cpp:106] Creating Layer fc1_2x_c0
I0605 23:00:04.545500 54715 net.cpp:454] fc1_2x_c0 <- concat_stem_1_concat_stem_1_0_split_3
I0605 23:00:04.545508 54715 net.cpp:411] fc1_2x_c0 -> deconv2_2x_c0
I0605 23:00:04.545933 54715 net.cpp:150] Setting up fc1_2x_c0
I0605 23:00:04.545943 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.545946 54715 net.cpp:165] Memory required for data: 5155424000
I0605 23:00:04.545953 54715 layer_factory.hpp:77] Creating layer fc1_2x_c1
I0605 23:00:04.545963 54715 net.cpp:106] Creating Layer fc1_2x_c1
I0605 23:00:04.545967 54715 net.cpp:454] fc1_2x_c1 <- concat_stem_1_concat_stem_1_0_split_4
I0605 23:00:04.545976 54715 net.cpp:411] fc1_2x_c1 -> deconv2_2x_c1
I0605 23:00:04.546396 54715 net.cpp:150] Setting up fc1_2x_c1
I0605 23:00:04.546406 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.546411 54715 net.cpp:165] Memory required for data: 5159520000
I0605 23:00:04.546416 54715 layer_factory.hpp:77] Creating layer fc1_2x_c2
I0605 23:00:04.546424 54715 net.cpp:106] Creating Layer fc1_2x_c2
I0605 23:00:04.546430 54715 net.cpp:454] fc1_2x_c2 <- concat_stem_1_concat_stem_1_0_split_5
I0605 23:00:04.546439 54715 net.cpp:411] fc1_2x_c2 -> deconv2_2x_c2
I0605 23:00:04.548348 54715 net.cpp:150] Setting up fc1_2x_c2
I0605 23:00:04.548368 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.548374 54715 net.cpp:165] Memory required for data: 5163616000
I0605 23:00:04.548382 54715 layer_factory.hpp:77] Creating layer fc1_2x_c3
I0605 23:00:04.548393 54715 net.cpp:106] Creating Layer fc1_2x_c3
I0605 23:00:04.548398 54715 net.cpp:454] fc1_2x_c3 <- concat_stem_1_concat_stem_1_0_split_6
I0605 23:00:04.548408 54715 net.cpp:411] fc1_2x_c3 -> deconv2_2x_c3
I0605 23:00:04.548796 54715 net.cpp:150] Setting up fc1_2x_c3
I0605 23:00:04.548805 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.548810 54715 net.cpp:165] Memory required for data: 5167712000
I0605 23:00:04.548817 54715 layer_factory.hpp:77] Creating layer fc1_2x
I0605 23:00:04.548825 54715 net.cpp:106] Creating Layer fc1_2x
I0605 23:00:04.548830 54715 net.cpp:454] fc1_2x <- deconv2_2x_d1
I0605 23:00:04.548836 54715 net.cpp:454] fc1_2x <- deconv2_2x_c0
I0605 23:00:04.548842 54715 net.cpp:454] fc1_2x <- deconv2_2x_c1
I0605 23:00:04.548847 54715 net.cpp:454] fc1_2x <- deconv2_2x_c2
I0605 23:00:04.548852 54715 net.cpp:454] fc1_2x <- deconv2_2x_c3
I0605 23:00:04.548858 54715 net.cpp:411] fc1_2x -> deconv2_2x
I0605 23:00:04.548892 54715 net.cpp:150] Setting up fc1_2x
I0605 23:00:04.548899 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.548903 54715 net.cpp:165] Memory required for data: 5171808000
I0605 23:00:04.548926 54715 layer_factory.hpp:77] Creating layer fc1_4x_c0
I0605 23:00:04.548936 54715 net.cpp:106] Creating Layer fc1_4x_c0
I0605 23:00:04.548941 54715 net.cpp:454] fc1_4x_c0 <- conv3_sum_relu3_sum_0_split_3
I0605 23:00:04.548949 54715 net.cpp:411] fc1_4x_c0 -> deconv3_4x_c0
I0605 23:00:04.551182 54715 net.cpp:150] Setting up fc1_4x_c0
I0605 23:00:04.551203 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.551208 54715 net.cpp:165] Memory required for data: 5175904000
I0605 23:00:04.551214 54715 layer_factory.hpp:77] Creating layer deconv3_4x_d1
I0605 23:00:04.551226 54715 net.cpp:106] Creating Layer deconv3_4x_d1
I0605 23:00:04.551232 54715 net.cpp:454] deconv3_4x_d1 <- conv3_sum_relu3_sum_0_split_4
I0605 23:00:04.551241 54715 net.cpp:411] deconv3_4x_d1 -> deconv3_4x_d1
I0605 23:00:04.553947 54715 net.cpp:150] Setting up deconv3_4x_d1
I0605 23:00:04.553962 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.553967 54715 net.cpp:165] Memory required for data: 5180000000
I0605 23:00:04.553975 54715 layer_factory.hpp:77] Creating layer fc1_4x_c1
I0605 23:00:04.553985 54715 net.cpp:106] Creating Layer fc1_4x_c1
I0605 23:00:04.553990 54715 net.cpp:454] fc1_4x_c1 <- conv3_sum_relu3_sum_0_split_5
I0605 23:00:04.554000 54715 net.cpp:411] fc1_4x_c1 -> deconv3_4x_c1
I0605 23:00:04.554868 54715 net.cpp:150] Setting up fc1_4x_c1
I0605 23:00:04.554877 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.554883 54715 net.cpp:165] Memory required for data: 5184096000
I0605 23:00:04.554890 54715 layer_factory.hpp:77] Creating layer fc1_4x_c2
I0605 23:00:04.554899 54715 net.cpp:106] Creating Layer fc1_4x_c2
I0605 23:00:04.554904 54715 net.cpp:454] fc1_4x_c2 <- conv3_sum_relu3_sum_0_split_6
I0605 23:00:04.554913 54715 net.cpp:411] fc1_4x_c2 -> deconv3_4x_c2
I0605 23:00:04.557245 54715 net.cpp:150] Setting up fc1_4x_c2
I0605 23:00:04.557265 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.557271 54715 net.cpp:165] Memory required for data: 5188192000
I0605 23:00:04.557279 54715 layer_factory.hpp:77] Creating layer fc1_4x_c3
I0605 23:00:04.557291 54715 net.cpp:106] Creating Layer fc1_4x_c3
I0605 23:00:04.557296 54715 net.cpp:454] fc1_4x_c3 <- conv3_sum_relu3_sum_0_split_7
I0605 23:00:04.557305 54715 net.cpp:411] fc1_4x_c3 -> deconv3_4x_c3
I0605 23:00:04.558140 54715 net.cpp:150] Setting up fc1_4x_c3
I0605 23:00:04.558151 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.558154 54715 net.cpp:165] Memory required for data: 5192288000
I0605 23:00:04.558161 54715 layer_factory.hpp:77] Creating layer fc1_4x
I0605 23:00:04.558171 54715 net.cpp:106] Creating Layer fc1_4x
I0605 23:00:04.558176 54715 net.cpp:454] fc1_4x <- deconv3_4x_d1
I0605 23:00:04.558182 54715 net.cpp:454] fc1_4x <- deconv3_4x_c0
I0605 23:00:04.558187 54715 net.cpp:454] fc1_4x <- deconv3_4x_c1
I0605 23:00:04.558192 54715 net.cpp:454] fc1_4x <- deconv3_4x_c2
I0605 23:00:04.558198 54715 net.cpp:454] fc1_4x <- deconv3_4x_c3
I0605 23:00:04.558204 54715 net.cpp:411] fc1_4x -> deconv3_4x
I0605 23:00:04.558236 54715 net.cpp:150] Setting up fc1_4x
I0605 23:00:04.558244 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.558248 54715 net.cpp:165] Memory required for data: 5196384000
I0605 23:00:04.558253 54715 layer_factory.hpp:77] Creating layer deconv4_8x_d1
I0605 23:00:04.558261 54715 net.cpp:106] Creating Layer deconv4_8x_d1
I0605 23:00:04.558266 54715 net.cpp:454] deconv4_8x_d1 <- conv4_sum_relu_conv4_sum_0_split_4
I0605 23:00:04.558275 54715 net.cpp:411] deconv4_8x_d1 -> deconv4_8x_d1
I0605 23:00:04.588469 54715 net.cpp:150] Setting up deconv4_8x_d1
I0605 23:00:04.588510 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.588515 54715 net.cpp:165] Memory required for data: 5200480000
I0605 23:00:04.588527 54715 layer_factory.hpp:77] Creating layer fc1_8x_c0
I0605 23:00:04.588543 54715 net.cpp:106] Creating Layer fc1_8x_c0
I0605 23:00:04.588549 54715 net.cpp:454] fc1_8x_c0 <- conv4_sum_relu_conv4_sum_0_split_5
I0605 23:00:04.588574 54715 net.cpp:411] fc1_8x_c0 -> deconv4_8x_c0
I0605 23:00:04.596417 54715 net.cpp:150] Setting up fc1_8x_c0
I0605 23:00:04.596458 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.596463 54715 net.cpp:165] Memory required for data: 5204576000
I0605 23:00:04.596477 54715 layer_factory.hpp:77] Creating layer fc1_8x_c1
I0605 23:00:04.596491 54715 net.cpp:106] Creating Layer fc1_8x_c1
I0605 23:00:04.596498 54715 net.cpp:454] fc1_8x_c1 <- conv4_sum_relu_conv4_sum_0_split_6
I0605 23:00:04.596508 54715 net.cpp:411] fc1_8x_c1 -> deconv4_8x_c1
I0605 23:00:04.604346 54715 net.cpp:150] Setting up fc1_8x_c1
I0605 23:00:04.604387 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.604391 54715 net.cpp:165] Memory required for data: 5208672000
I0605 23:00:04.604404 54715 layer_factory.hpp:77] Creating layer fc1_8x_c2
I0605 23:00:04.604419 54715 net.cpp:106] Creating Layer fc1_8x_c2
I0605 23:00:04.604427 54715 net.cpp:454] fc1_8x_c2 <- conv4_sum_relu_conv4_sum_0_split_7
I0605 23:00:04.604439 54715 net.cpp:411] fc1_8x_c2 -> deconv4_8x_c2
I0605 23:00:04.613736 54715 net.cpp:150] Setting up fc1_8x_c2
I0605 23:00:04.613775 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.613780 54715 net.cpp:165] Memory required for data: 5212768000
I0605 23:00:04.613792 54715 layer_factory.hpp:77] Creating layer fc1_8x_c3
I0605 23:00:04.613807 54715 net.cpp:106] Creating Layer fc1_8x_c3
I0605 23:00:04.613813 54715 net.cpp:454] fc1_8x_c3 <- conv4_sum_relu_conv4_sum_0_split_8
I0605 23:00:04.613826 54715 net.cpp:411] fc1_8x_c3 -> deconv4_8x_c3
I0605 23:00:04.621595 54715 net.cpp:150] Setting up fc1_8x_c3
I0605 23:00:04.621637 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.621642 54715 net.cpp:165] Memory required for data: 5216864000
I0605 23:00:04.621655 54715 layer_factory.hpp:77] Creating layer fc1_8x
I0605 23:00:04.621668 54715 net.cpp:106] Creating Layer fc1_8x
I0605 23:00:04.621675 54715 net.cpp:454] fc1_8x <- deconv4_8x_d1
I0605 23:00:04.621682 54715 net.cpp:454] fc1_8x <- deconv4_8x_c0
I0605 23:00:04.621688 54715 net.cpp:454] fc1_8x <- deconv4_8x_c1
I0605 23:00:04.621693 54715 net.cpp:454] fc1_8x <- deconv4_8x_c2
I0605 23:00:04.621698 54715 net.cpp:454] fc1_8x <- deconv4_8x_c3
I0605 23:00:04.621706 54715 net.cpp:411] fc1_8x -> deconv4_8x
I0605 23:00:04.621745 54715 net.cpp:150] Setting up fc1_8x
I0605 23:00:04.621753 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.621758 54715 net.cpp:165] Memory required for data: 5220960000
I0605 23:00:04.621762 54715 layer_factory.hpp:77] Creating layer bn_deconv5_16x
I0605 23:00:04.621770 54715 net.cpp:106] Creating Layer bn_deconv5_16x
I0605 23:00:04.621775 54715 net.cpp:454] bn_deconv5_16x <- deconv5_16x
I0605 23:00:04.621783 54715 net.cpp:397] bn_deconv5_16x -> deconv5_16x (in-place)
I0605 23:00:04.622115 54715 net.cpp:150] Setting up bn_deconv5_16x
I0605 23:00:04.622125 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.622129 54715 net.cpp:165] Memory required for data: 5225056000
I0605 23:00:04.622139 54715 layer_factory.hpp:77] Creating layer scale_deconv5_16x
I0605 23:00:04.622148 54715 net.cpp:106] Creating Layer scale_deconv5_16x
I0605 23:00:04.622153 54715 net.cpp:454] scale_deconv5_16x <- deconv5_16x
I0605 23:00:04.622160 54715 net.cpp:397] scale_deconv5_16x -> deconv5_16x (in-place)
I0605 23:00:04.622212 54715 layer_factory.hpp:77] Creating layer scale_deconv5_16x
I0605 23:00:04.622575 54715 net.cpp:150] Setting up scale_deconv5_16x
I0605 23:00:04.622586 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.622591 54715 net.cpp:165] Memory required for data: 5229152000
I0605 23:00:04.622597 54715 layer_factory.hpp:77] Creating layer relu_deconv5_16x
I0605 23:00:04.622606 54715 net.cpp:106] Creating Layer relu_deconv5_16x
I0605 23:00:04.622611 54715 net.cpp:454] relu_deconv5_16x <- deconv5_16x
I0605 23:00:04.622617 54715 net.cpp:397] relu_deconv5_16x -> deconv5_16x (in-place)
I0605 23:00:04.622624 54715 net.cpp:150] Setting up relu_deconv5_16x
I0605 23:00:04.622648 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.622660 54715 net.cpp:165] Memory required for data: 5233248000
I0605 23:00:04.622664 54715 layer_factory.hpp:77] Creating layer bn_deconv4_8x
I0605 23:00:04.622671 54715 net.cpp:106] Creating Layer bn_deconv4_8x
I0605 23:00:04.622676 54715 net.cpp:454] bn_deconv4_8x <- deconv4_8x
I0605 23:00:04.622683 54715 net.cpp:397] bn_deconv4_8x -> deconv4_8x (in-place)
I0605 23:00:04.624503 54715 net.cpp:150] Setting up bn_deconv4_8x
I0605 23:00:04.624522 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.624526 54715 net.cpp:165] Memory required for data: 5237344000
I0605 23:00:04.624537 54715 layer_factory.hpp:77] Creating layer scale_deconv4_8x
I0605 23:00:04.624547 54715 net.cpp:106] Creating Layer scale_deconv4_8x
I0605 23:00:04.624552 54715 net.cpp:454] scale_deconv4_8x <- deconv4_8x
I0605 23:00:04.624560 54715 net.cpp:397] scale_deconv4_8x -> deconv4_8x (in-place)
I0605 23:00:04.624616 54715 layer_factory.hpp:77] Creating layer scale_deconv4_8x
I0605 23:00:04.624873 54715 net.cpp:150] Setting up scale_deconv4_8x
I0605 23:00:04.624883 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.624887 54715 net.cpp:165] Memory required for data: 5241440000
I0605 23:00:04.624894 54715 layer_factory.hpp:77] Creating layer relu_deconv4_8x
I0605 23:00:04.624903 54715 net.cpp:106] Creating Layer relu_deconv4_8x
I0605 23:00:04.624907 54715 net.cpp:454] relu_deconv4_8x <- deconv4_8x
I0605 23:00:04.624914 54715 net.cpp:397] relu_deconv4_8x -> deconv4_8x (in-place)
I0605 23:00:04.624922 54715 net.cpp:150] Setting up relu_deconv4_8x
I0605 23:00:04.624927 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.624930 54715 net.cpp:165] Memory required for data: 5245536000
I0605 23:00:04.624934 54715 layer_factory.hpp:77] Creating layer bn_deconv3_4x
I0605 23:00:04.624943 54715 net.cpp:106] Creating Layer bn_deconv3_4x
I0605 23:00:04.624946 54715 net.cpp:454] bn_deconv3_4x <- deconv3_4x
I0605 23:00:04.624953 54715 net.cpp:397] bn_deconv3_4x -> deconv3_4x (in-place)
I0605 23:00:04.625231 54715 net.cpp:150] Setting up bn_deconv3_4x
I0605 23:00:04.625241 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.625244 54715 net.cpp:165] Memory required for data: 5249632000
I0605 23:00:04.625252 54715 layer_factory.hpp:77] Creating layer scale_deconv3_4x
I0605 23:00:04.625259 54715 net.cpp:106] Creating Layer scale_deconv3_4x
I0605 23:00:04.625264 54715 net.cpp:454] scale_deconv3_4x <- deconv3_4x
I0605 23:00:04.625270 54715 net.cpp:397] scale_deconv3_4x -> deconv3_4x (in-place)
I0605 23:00:04.625313 54715 layer_factory.hpp:77] Creating layer scale_deconv3_4x
I0605 23:00:04.626999 54715 net.cpp:150] Setting up scale_deconv3_4x
I0605 23:00:04.627017 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.627022 54715 net.cpp:165] Memory required for data: 5253728000
I0605 23:00:04.627029 54715 layer_factory.hpp:77] Creating layer relu_deconv3_4x
I0605 23:00:04.627038 54715 net.cpp:106] Creating Layer relu_deconv3_4x
I0605 23:00:04.627044 54715 net.cpp:454] relu_deconv3_4x <- deconv3_4x
I0605 23:00:04.627051 54715 net.cpp:397] relu_deconv3_4x -> deconv3_4x (in-place)
I0605 23:00:04.627059 54715 net.cpp:150] Setting up relu_deconv3_4x
I0605 23:00:04.627064 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.627069 54715 net.cpp:165] Memory required for data: 5257824000
I0605 23:00:04.627074 54715 layer_factory.hpp:77] Creating layer bn_deconv2_2x
I0605 23:00:04.627080 54715 net.cpp:106] Creating Layer bn_deconv2_2x
I0605 23:00:04.627085 54715 net.cpp:454] bn_deconv2_2x <- deconv2_2x
I0605 23:00:04.627092 54715 net.cpp:397] bn_deconv2_2x -> deconv2_2x (in-place)
I0605 23:00:04.627375 54715 net.cpp:150] Setting up bn_deconv2_2x
I0605 23:00:04.627383 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.627388 54715 net.cpp:165] Memory required for data: 5261920000
I0605 23:00:04.627396 54715 layer_factory.hpp:77] Creating layer scale_deconv2_2x
I0605 23:00:04.627404 54715 net.cpp:106] Creating Layer scale_deconv2_2x
I0605 23:00:04.627418 54715 net.cpp:454] scale_deconv2_2x <- deconv2_2x
I0605 23:00:04.627432 54715 net.cpp:397] scale_deconv2_2x -> deconv2_2x (in-place)
I0605 23:00:04.627481 54715 layer_factory.hpp:77] Creating layer scale_deconv2_2x
I0605 23:00:04.627737 54715 net.cpp:150] Setting up scale_deconv2_2x
I0605 23:00:04.627746 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.627750 54715 net.cpp:165] Memory required for data: 5266016000
I0605 23:00:04.627758 54715 layer_factory.hpp:77] Creating layer relu_deconv2_2x
I0605 23:00:04.627765 54715 net.cpp:106] Creating Layer relu_deconv2_2x
I0605 23:00:04.627769 54715 net.cpp:454] relu_deconv2_2x <- deconv2_2x
I0605 23:00:04.627775 54715 net.cpp:397] relu_deconv2_2x -> deconv2_2x (in-place)
I0605 23:00:04.627782 54715 net.cpp:150] Setting up relu_deconv2_2x
I0605 23:00:04.627789 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.627791 54715 net.cpp:165] Memory required for data: 5270112000
I0605 23:00:04.627795 54715 layer_factory.hpp:77] Creating layer conv_deconv5_16x
I0605 23:00:04.627806 54715 net.cpp:106] Creating Layer conv_deconv5_16x
I0605 23:00:04.627811 54715 net.cpp:454] conv_deconv5_16x <- deconv5_16x
I0605 23:00:04.627820 54715 net.cpp:411] conv_deconv5_16x -> conv_deconv5_16x
I0605 23:00:04.628188 54715 net.cpp:150] Setting up conv_deconv5_16x
I0605 23:00:04.628201 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.628206 54715 net.cpp:165] Memory required for data: 5274208000
I0605 23:00:04.628211 54715 layer_factory.hpp:77] Creating layer conv_deconv4_8x
I0605 23:00:04.628221 54715 net.cpp:106] Creating Layer conv_deconv4_8x
I0605 23:00:04.628227 54715 net.cpp:454] conv_deconv4_8x <- deconv4_8x
I0605 23:00:04.628235 54715 net.cpp:411] conv_deconv4_8x -> conv_deconv4_8x
I0605 23:00:04.629992 54715 net.cpp:150] Setting up conv_deconv4_8x
I0605 23:00:04.630008 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.630013 54715 net.cpp:165] Memory required for data: 5278304000
I0605 23:00:04.630022 54715 layer_factory.hpp:77] Creating layer conv_deconv3_4x
I0605 23:00:04.630031 54715 net.cpp:106] Creating Layer conv_deconv3_4x
I0605 23:00:04.630038 54715 net.cpp:454] conv_deconv3_4x <- deconv3_4x
I0605 23:00:04.630048 54715 net.cpp:411] conv_deconv3_4x -> conv_deconv3_4x
I0605 23:00:04.630386 54715 net.cpp:150] Setting up conv_deconv3_4x
I0605 23:00:04.630395 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.630399 54715 net.cpp:165] Memory required for data: 5282400000
I0605 23:00:04.630408 54715 layer_factory.hpp:77] Creating layer conv_deconv2_2x
I0605 23:00:04.630417 54715 net.cpp:106] Creating Layer conv_deconv2_2x
I0605 23:00:04.630421 54715 net.cpp:454] conv_deconv2_2x <- deconv2_2x
I0605 23:00:04.630429 54715 net.cpp:411] conv_deconv2_2x -> conv_deconv2_2x
I0605 23:00:04.630750 54715 net.cpp:150] Setting up conv_deconv2_2x
I0605 23:00:04.630760 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.630764 54715 net.cpp:165] Memory required for data: 5286496000
I0605 23:00:04.630770 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv5_16x
I0605 23:00:04.630779 54715 net.cpp:106] Creating Layer bn_conv_deconv5_16x
I0605 23:00:04.630784 54715 net.cpp:454] bn_conv_deconv5_16x <- conv_deconv5_16x
I0605 23:00:04.630790 54715 net.cpp:397] bn_conv_deconv5_16x -> conv_deconv5_16x (in-place)
I0605 23:00:04.631080 54715 net.cpp:150] Setting up bn_conv_deconv5_16x
I0605 23:00:04.631093 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.631096 54715 net.cpp:165] Memory required for data: 5290592000
I0605 23:00:04.631104 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv5_16x
I0605 23:00:04.631112 54715 net.cpp:106] Creating Layer scale_conv_deconv5_16x
I0605 23:00:04.631117 54715 net.cpp:454] scale_conv_deconv5_16x <- conv_deconv5_16x
I0605 23:00:04.631124 54715 net.cpp:397] scale_conv_deconv5_16x -> conv_deconv5_16x (in-place)
I0605 23:00:04.631173 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv5_16x
I0605 23:00:04.632884 54715 net.cpp:150] Setting up scale_conv_deconv5_16x
I0605 23:00:04.632913 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.632918 54715 net.cpp:165] Memory required for data: 5294688000
I0605 23:00:04.632927 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv5_16x
I0605 23:00:04.632936 54715 net.cpp:106] Creating Layer relu_conv_deconv5_16x
I0605 23:00:04.632942 54715 net.cpp:454] relu_conv_deconv5_16x <- conv_deconv5_16x
I0605 23:00:04.632949 54715 net.cpp:397] relu_conv_deconv5_16x -> conv_deconv5_16x (in-place)
I0605 23:00:04.632957 54715 net.cpp:150] Setting up relu_conv_deconv5_16x
I0605 23:00:04.632963 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.632968 54715 net.cpp:165] Memory required for data: 5298784000
I0605 23:00:04.632972 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv4_8x
I0605 23:00:04.632979 54715 net.cpp:106] Creating Layer bn_conv_deconv4_8x
I0605 23:00:04.632983 54715 net.cpp:454] bn_conv_deconv4_8x <- conv_deconv4_8x
I0605 23:00:04.632992 54715 net.cpp:397] bn_conv_deconv4_8x -> conv_deconv4_8x (in-place)
I0605 23:00:04.633280 54715 net.cpp:150] Setting up bn_conv_deconv4_8x
I0605 23:00:04.633288 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.633292 54715 net.cpp:165] Memory required for data: 5302880000
I0605 23:00:04.633301 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv4_8x
I0605 23:00:04.633309 54715 net.cpp:106] Creating Layer scale_conv_deconv4_8x
I0605 23:00:04.633314 54715 net.cpp:454] scale_conv_deconv4_8x <- conv_deconv4_8x
I0605 23:00:04.633321 54715 net.cpp:397] scale_conv_deconv4_8x -> conv_deconv4_8x (in-place)
I0605 23:00:04.633368 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv4_8x
I0605 23:00:04.633623 54715 net.cpp:150] Setting up scale_conv_deconv4_8x
I0605 23:00:04.633632 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.633636 54715 net.cpp:165] Memory required for data: 5306976000
I0605 23:00:04.633646 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv4_8x
I0605 23:00:04.633651 54715 net.cpp:106] Creating Layer relu_conv_deconv4_8x
I0605 23:00:04.633656 54715 net.cpp:454] relu_conv_deconv4_8x <- conv_deconv4_8x
I0605 23:00:04.633662 54715 net.cpp:397] relu_conv_deconv4_8x -> conv_deconv4_8x (in-place)
I0605 23:00:04.633669 54715 net.cpp:150] Setting up relu_conv_deconv4_8x
I0605 23:00:04.633675 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.633678 54715 net.cpp:165] Memory required for data: 5311072000
I0605 23:00:04.633682 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv3_4x
I0605 23:00:04.633690 54715 net.cpp:106] Creating Layer bn_conv_deconv3_4x
I0605 23:00:04.633694 54715 net.cpp:454] bn_conv_deconv3_4x <- conv_deconv3_4x
I0605 23:00:04.633700 54715 net.cpp:397] bn_conv_deconv3_4x -> conv_deconv3_4x (in-place)
I0605 23:00:04.633977 54715 net.cpp:150] Setting up bn_conv_deconv3_4x
I0605 23:00:04.633985 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.633990 54715 net.cpp:165] Memory required for data: 5315168000
I0605 23:00:04.633997 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv3_4x
I0605 23:00:04.634004 54715 net.cpp:106] Creating Layer scale_conv_deconv3_4x
I0605 23:00:04.634009 54715 net.cpp:454] scale_conv_deconv3_4x <- conv_deconv3_4x
I0605 23:00:04.634016 54715 net.cpp:397] scale_conv_deconv3_4x -> conv_deconv3_4x (in-place)
I0605 23:00:04.634058 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv3_4x
I0605 23:00:04.635741 54715 net.cpp:150] Setting up scale_conv_deconv3_4x
I0605 23:00:04.635759 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.635764 54715 net.cpp:165] Memory required for data: 5319264000
I0605 23:00:04.635772 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv3_4x
I0605 23:00:04.635782 54715 net.cpp:106] Creating Layer relu_conv_deconv3_4x
I0605 23:00:04.635787 54715 net.cpp:454] relu_conv_deconv3_4x <- conv_deconv3_4x
I0605 23:00:04.635794 54715 net.cpp:397] relu_conv_deconv3_4x -> conv_deconv3_4x (in-place)
I0605 23:00:04.635808 54715 net.cpp:150] Setting up relu_conv_deconv3_4x
I0605 23:00:04.635821 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.635826 54715 net.cpp:165] Memory required for data: 5323360000
I0605 23:00:04.635830 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv2_2x
I0605 23:00:04.635838 54715 net.cpp:106] Creating Layer bn_conv_deconv2_2x
I0605 23:00:04.635841 54715 net.cpp:454] bn_conv_deconv2_2x <- conv_deconv2_2x
I0605 23:00:04.635849 54715 net.cpp:397] bn_conv_deconv2_2x -> conv_deconv2_2x (in-place)
I0605 23:00:04.636129 54715 net.cpp:150] Setting up bn_conv_deconv2_2x
I0605 23:00:04.636137 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.636162 54715 net.cpp:165] Memory required for data: 5327456000
I0605 23:00:04.636171 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv2_2x
I0605 23:00:04.636179 54715 net.cpp:106] Creating Layer scale_conv_deconv2_2x
I0605 23:00:04.636183 54715 net.cpp:454] scale_conv_deconv2_2x <- conv_deconv2_2x
I0605 23:00:04.636190 54715 net.cpp:397] scale_conv_deconv2_2x -> conv_deconv2_2x (in-place)
I0605 23:00:04.636238 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv2_2x
I0605 23:00:04.636493 54715 net.cpp:150] Setting up scale_conv_deconv2_2x
I0605 23:00:04.636502 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.636507 54715 net.cpp:165] Memory required for data: 5331552000
I0605 23:00:04.636514 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv2_2x
I0605 23:00:04.636521 54715 net.cpp:106] Creating Layer relu_conv_deconv2_2x
I0605 23:00:04.636525 54715 net.cpp:454] relu_conv_deconv2_2x <- conv_deconv2_2x
I0605 23:00:04.636531 54715 net.cpp:397] relu_conv_deconv2_2x -> conv_deconv2_2x (in-place)
I0605 23:00:04.636538 54715 net.cpp:150] Setting up relu_conv_deconv2_2x
I0605 23:00:04.636543 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.636548 54715 net.cpp:165] Memory required for data: 5335648000
I0605 23:00:04.636551 54715 layer_factory.hpp:77] Creating layer deconv_all_sum
I0605 23:00:04.636561 54715 net.cpp:106] Creating Layer deconv_all_sum
I0605 23:00:04.636565 54715 net.cpp:454] deconv_all_sum <- conv_deconv2_2x
I0605 23:00:04.636569 54715 net.cpp:454] deconv_all_sum <- conv_deconv3_4x
I0605 23:00:04.636574 54715 net.cpp:454] deconv_all_sum <- conv_deconv4_8x
I0605 23:00:04.636580 54715 net.cpp:454] deconv_all_sum <- conv_deconv5_16x
I0605 23:00:04.636586 54715 net.cpp:411] deconv_all_sum -> deconv_all_sum
I0605 23:00:04.636620 54715 net.cpp:150] Setting up deconv_all_sum
I0605 23:00:04.636627 54715 net.cpp:157] Top shape: 5 2 320 320 (1024000)
I0605 23:00:04.636632 54715 net.cpp:165] Memory required for data: 5339744000
I0605 23:00:04.636636 54715 layer_factory.hpp:77] Creating layer loss_deconv_all
I0605 23:00:04.636644 54715 net.cpp:106] Creating Layer loss_deconv_all
I0605 23:00:04.636648 54715 net.cpp:454] loss_deconv_all <- deconv_all_sum
I0605 23:00:04.636656 54715 net.cpp:454] loss_deconv_all <- label
I0605 23:00:04.636664 54715 net.cpp:411] loss_deconv_all -> loss_deconv_all
I0605 23:00:04.636675 54715 layer_factory.hpp:77] Creating layer loss_deconv_all
I0605 23:00:04.639678 54715 sample_selector.cpp:58] read prob from file : label_class_selection.prototxt
I0605 23:00:04.639763 54715 sample_selector.cpp:78] rest_of_label_mapping_ = 0 1
I0605 23:00:04.639775 54715 sample_selector.cpp:93] label map :0--->0
I0605 23:00:04.639780 54715 sample_selector.cpp:93] label map :1--->1
I0605 23:00:04.639783 54715 sample_selector.cpp:95] label_prob_map_ size =2
I0605 23:00:04.639792 54715 sample_selector.cpp:116] scale_factor = 3.33333
I0605 23:00:04.639806 54715 sample_selector.cpp:117] bottom_prob = 0.3
I0605 23:00:04.639811 54715 sample_selector.cpp:118] label_prob_vec.size = 2
I0605 23:00:04.639816 54715 sample_selector.cpp:164] size of prob = 1
I0605 23:00:04.639822 54715 sample_selector.cpp:19] lable class [0] weight =0.25
I0605 23:00:04.639827 54715 sample_selector.cpp:19] lable class [1] weight =1
I0605 23:00:04.639863 54715 net.cpp:150] Setting up loss_deconv_all
I0605 23:00:04.639883 54715 net.cpp:157] Top shape: (1)
I0605 23:00:04.639895 54715 net.cpp:160] with loss weight 1
I0605 23:00:04.639901 54715 net.cpp:165] Memory required for data: 5339744004
I0605 23:00:04.639906 54715 net.cpp:226] loss_deconv_all needs backward computation.
I0605 23:00:04.639919 54715 net.cpp:226] deconv_all_sum needs backward computation.
I0605 23:00:04.639925 54715 net.cpp:226] relu_conv_deconv2_2x needs backward computation.
I0605 23:00:04.639930 54715 net.cpp:226] scale_conv_deconv2_2x needs backward computation.
I0605 23:00:04.639933 54715 net.cpp:226] bn_conv_deconv2_2x needs backward computation.
I0605 23:00:04.639938 54715 net.cpp:226] relu_conv_deconv3_4x needs backward computation.
I0605 23:00:04.639943 54715 net.cpp:226] scale_conv_deconv3_4x needs backward computation.
I0605 23:00:04.639947 54715 net.cpp:226] bn_conv_deconv3_4x needs backward computation.
I0605 23:00:04.639951 54715 net.cpp:226] relu_conv_deconv4_8x needs backward computation.
I0605 23:00:04.639955 54715 net.cpp:226] scale_conv_deconv4_8x needs backward computation.
I0605 23:00:04.639961 54715 net.cpp:226] bn_conv_deconv4_8x needs backward computation.
I0605 23:00:04.639966 54715 net.cpp:226] relu_conv_deconv5_16x needs backward computation.
I0605 23:00:04.639969 54715 net.cpp:226] scale_conv_deconv5_16x needs backward computation.
I0605 23:00:04.639973 54715 net.cpp:226] bn_conv_deconv5_16x needs backward computation.
I0605 23:00:04.639978 54715 net.cpp:226] conv_deconv2_2x needs backward computation.
I0605 23:00:04.639983 54715 net.cpp:226] conv_deconv3_4x needs backward computation.
I0605 23:00:04.639987 54715 net.cpp:226] conv_deconv4_8x needs backward computation.
I0605 23:00:04.639991 54715 net.cpp:226] conv_deconv5_16x needs backward computation.
I0605 23:00:04.639997 54715 net.cpp:226] relu_deconv2_2x needs backward computation.
I0605 23:00:04.640002 54715 net.cpp:226] scale_deconv2_2x needs backward computation.
I0605 23:00:04.640005 54715 net.cpp:226] bn_deconv2_2x needs backward computation.
I0605 23:00:04.640009 54715 net.cpp:226] relu_deconv3_4x needs backward computation.
I0605 23:00:04.640013 54715 net.cpp:226] scale_deconv3_4x needs backward computation.
I0605 23:00:04.640017 54715 net.cpp:226] bn_deconv3_4x needs backward computation.
I0605 23:00:04.640022 54715 net.cpp:226] relu_deconv4_8x needs backward computation.
I0605 23:00:04.640025 54715 net.cpp:226] scale_deconv4_8x needs backward computation.
I0605 23:00:04.640030 54715 net.cpp:226] bn_deconv4_8x needs backward computation.
I0605 23:00:04.640034 54715 net.cpp:226] relu_deconv5_16x needs backward computation.
I0605 23:00:04.640039 54715 net.cpp:226] scale_deconv5_16x needs backward computation.
I0605 23:00:04.640043 54715 net.cpp:226] bn_deconv5_16x needs backward computation.
I0605 23:00:04.640048 54715 net.cpp:226] fc1_8x needs backward computation.
I0605 23:00:04.640053 54715 net.cpp:226] fc1_8x_c3 needs backward computation.
I0605 23:00:04.640058 54715 net.cpp:226] fc1_8x_c2 needs backward computation.
I0605 23:00:04.640064 54715 net.cpp:226] fc1_8x_c1 needs backward computation.
I0605 23:00:04.640069 54715 net.cpp:226] fc1_8x_c0 needs backward computation.
I0605 23:00:04.640072 54715 net.cpp:226] deconv4_8x_d1 needs backward computation.
I0605 23:00:04.640077 54715 net.cpp:226] fc1_4x needs backward computation.
I0605 23:00:04.640084 54715 net.cpp:226] fc1_4x_c3 needs backward computation.
I0605 23:00:04.640089 54715 net.cpp:226] fc1_4x_c2 needs backward computation.
I0605 23:00:04.640094 54715 net.cpp:226] fc1_4x_c1 needs backward computation.
I0605 23:00:04.640100 54715 net.cpp:226] deconv3_4x_d1 needs backward computation.
I0605 23:00:04.640103 54715 net.cpp:226] fc1_4x_c0 needs backward computation.
I0605 23:00:04.640110 54715 net.cpp:226] fc1_2x needs backward computation.
I0605 23:00:04.640115 54715 net.cpp:226] fc1_2x_c3 needs backward computation.
I0605 23:00:04.640120 54715 net.cpp:226] fc1_2x_c2 needs backward computation.
I0605 23:00:04.640125 54715 net.cpp:226] fc1_2x_c1 needs backward computation.
I0605 23:00:04.640133 54715 net.cpp:226] fc1_2x_c0 needs backward computation.
I0605 23:00:04.640172 54715 net.cpp:226] deconv2_2x_d1 needs backward computation.
I0605 23:00:04.640177 54715 net.cpp:226] deconv5_16x needs backward computation.
I0605 23:00:04.640182 54715 net.cpp:226] relu_conv5_sum needs backward computation.
I0605 23:00:04.640187 54715 net.cpp:226] conv5_sum needs backward computation.
I0605 23:00:04.640192 54715 net.cpp:226] scale_ira_Inception_C_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:04.640197 54715 net.cpp:226] bn_ira_Inception_C_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:04.640202 54715 net.cpp:226] ira_Inception_C_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:04.640208 54715 net.cpp:226] ira_Inception_C_block_1/concat needs backward computation.
I0605 23:00:04.640213 54715 net.cpp:226] relu_ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640218 54715 net.cpp:226] scale_ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640221 54715 net.cpp:226] bn_ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640228 54715 net.cpp:226] ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640233 54715 net.cpp:226] relu_ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640236 54715 net.cpp:226] scale_ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640240 54715 net.cpp:226] bn_ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640245 54715 net.cpp:226] ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640250 54715 net.cpp:226] relu_ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640254 54715 net.cpp:226] scale_ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640259 54715 net.cpp:226] bn_ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640264 54715 net.cpp:226] ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640269 54715 net.cpp:226] relu_ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640274 54715 net.cpp:226] scale_ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640277 54715 net.cpp:226] bn_ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640282 54715 net.cpp:226] ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640287 54715 net.cpp:226] conv5_1b_relu5_1b_0_split needs backward computation.
I0605 23:00:04.640291 54715 net.cpp:226] relu5_1b needs backward computation.
I0605 23:00:04.640296 54715 net.cpp:226] scale_conv5_1b needs backward computation.
I0605 23:00:04.640301 54715 net.cpp:226] bn_conv5_1b needs backward computation.
I0605 23:00:04.640305 54715 net.cpp:226] conv5_1b needs backward computation.
I0605 23:00:04.640311 54715 net.cpp:226] ira_Reduction_B_block_1/concat needs backward computation.
I0605 23:00:04.640317 54715 net.cpp:226] relu_ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:04.640322 54715 net.cpp:226] scale_ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:04.640326 54715 net.cpp:226] bn_ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:04.640331 54715 net.cpp:226] ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:04.640336 54715 net.cpp:226] relu_ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:04.640341 54715 net.cpp:226] scale_ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:04.640345 54715 net.cpp:226] bn_ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:04.640349 54715 net.cpp:226] ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:04.640354 54715 net.cpp:226] relu_ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:04.640359 54715 net.cpp:226] scale_ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:04.640372 54715 net.cpp:226] bn_ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:04.640377 54715 net.cpp:226] ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:04.640381 54715 net.cpp:226] relu_ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:04.640388 54715 net.cpp:226] scale_ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:04.640391 54715 net.cpp:226] bn_ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:04.640395 54715 net.cpp:226] ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:04.640400 54715 net.cpp:226] relu_ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:04.640405 54715 net.cpp:226] scale_ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:04.640409 54715 net.cpp:226] bn_ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:04.640414 54715 net.cpp:226] ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:04.640419 54715 net.cpp:226] relu_ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:04.640424 54715 net.cpp:226] scale_ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:04.640429 54715 net.cpp:226] bn_ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:04.640434 54715 net.cpp:226] ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:04.640439 54715 net.cpp:226] relu_ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640444 54715 net.cpp:226] scale_ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640449 54715 net.cpp:226] bn_ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640452 54715 net.cpp:226] ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640457 54715 net.cpp:226] ira_Reduction_B_block_1/a_pool needs backward computation.
I0605 23:00:04.640463 54715 net.cpp:226] conv4_sum_relu_conv4_sum_0_split needs backward computation.
I0605 23:00:04.640468 54715 net.cpp:226] relu_conv4_sum needs backward computation.
I0605 23:00:04.640472 54715 net.cpp:226] conv4_sum needs backward computation.
I0605 23:00:04.640478 54715 net.cpp:226] scale_ira_Inception_B_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:04.640483 54715 net.cpp:226] bn_ira_Inception_B_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:04.640487 54715 net.cpp:226] ira_Inception_B_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:04.640492 54715 net.cpp:226] ira_Inception_B_block_1/concat needs backward computation.
I0605 23:00:04.640498 54715 net.cpp:226] relu_ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640503 54715 net.cpp:226] scale_ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640508 54715 net.cpp:226] bn_ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640512 54715 net.cpp:226] ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:04.640517 54715 net.cpp:226] relu_ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640522 54715 net.cpp:226] scale_ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640527 54715 net.cpp:226] bn_ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640532 54715 net.cpp:226] ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:04.640537 54715 net.cpp:226] relu_ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640542 54715 net.cpp:226] scale_ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640545 54715 net.cpp:226] bn_ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640550 54715 net.cpp:226] ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:04.640558 54715 net.cpp:226] relu_ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640568 54715 net.cpp:226] scale_ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640573 54715 net.cpp:226] bn_ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640578 54715 net.cpp:226] ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:04.640583 54715 net.cpp:226] conv4_1b_relu4_1b_0_split needs backward computation.
I0605 23:00:04.640588 54715 net.cpp:226] relu4_1b needs backward computation.
I0605 23:00:04.640594 54715 net.cpp:226] scale_conv4_1b needs backward computation.
I0605 23:00:04.640597 54715 net.cpp:226] bn_conv4_1b needs backward computation.
I0605 23:00:04.640602 54715 net.cpp:226] conv4_1b needs backward computation.
I0605 23:00:04.640609 54715 net.cpp:226] ira_v4_reduction_A/concat needs backward computation.
I0605 23:00:04.640614 54715 net.cpp:226] relu_ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:04.640619 54715 net.cpp:226] scale_ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:04.640622 54715 net.cpp:226] bn_ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:04.640628 54715 net.cpp:226] ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:04.640633 54715 net.cpp:226] relu_ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:04.640637 54715 net.cpp:226] scale_ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:04.640641 54715 net.cpp:226] bn_ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:04.640647 54715 net.cpp:226] ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:04.640651 54715 net.cpp:226] relu_ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:04.640656 54715 net.cpp:226] scale_ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:04.640661 54715 net.cpp:226] bn_ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:04.640666 54715 net.cpp:226] ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:04.640671 54715 net.cpp:226] relu_ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:04.640676 54715 net.cpp:226] scale_ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:04.640679 54715 net.cpp:226] bn_ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:04.640684 54715 net.cpp:226] ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:04.640689 54715 net.cpp:226] ira_v4_reduction_A/pool needs backward computation.
I0605 23:00:04.640694 54715 net.cpp:226] conv3_sum_relu3_sum_0_split needs backward computation.
I0605 23:00:04.640699 54715 net.cpp:226] relu3_sum needs backward computation.
I0605 23:00:04.640704 54715 net.cpp:226] conv3_sum needs backward computation.
I0605 23:00:04.640710 54715 net.cpp:226] scale_ra_A_concat_top_conv_1x1 needs backward computation.
I0605 23:00:04.640714 54715 net.cpp:226] bn_ra_A_concat_top_conv_1x1 needs backward computation.
I0605 23:00:04.640718 54715 net.cpp:226] ira_A_concat_top_conv_1x1 needs backward computation.
I0605 23:00:04.640724 54715 net.cpp:226] ira_A_concat needs backward computation.
I0605 23:00:04.640730 54715 net.cpp:226] relu_ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:04.640735 54715 net.cpp:226] scale_ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:04.640739 54715 net.cpp:226] bn_ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:04.640744 54715 net.cpp:226] ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:04.640749 54715 net.cpp:226] relu_ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:04.640753 54715 net.cpp:226] scale_ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:04.640758 54715 net.cpp:226] bn_ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:04.640763 54715 net.cpp:226] ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:04.640772 54715 net.cpp:226] relu_ira_A_3_conv1x1 needs backward computation.
I0605 23:00:04.640782 54715 net.cpp:226] scale_ira_A_3_conv1x1 needs backward computation.
I0605 23:00:04.640786 54715 net.cpp:226] bn_ira_A_3_conv1x1 needs backward computation.
I0605 23:00:04.640791 54715 net.cpp:226] ira_A_3_conv1x1 needs backward computation.
I0605 23:00:04.640797 54715 net.cpp:226] relu_ira_A_2_conv3x3 needs backward computation.
I0605 23:00:04.640801 54715 net.cpp:226] scale_ira_A_2_conv3x3 needs backward computation.
I0605 23:00:04.640806 54715 net.cpp:226] bn_ira_A_2_conv3x3 needs backward computation.
I0605 23:00:04.640811 54715 net.cpp:226] ira_A_2_conv3x3 needs backward computation.
I0605 23:00:04.640815 54715 net.cpp:226] relu_ira_A_2_conv1x1 needs backward computation.
I0605 23:00:04.640820 54715 net.cpp:226] scale_ira_A_2_conv1x1 needs backward computation.
I0605 23:00:04.640825 54715 net.cpp:226] bn_ira_A_2_conv1x1 needs backward computation.
I0605 23:00:04.640830 54715 net.cpp:226] ira_A_2_conv1x1 needs backward computation.
I0605 23:00:04.640835 54715 net.cpp:226] relu_ira_A_1_conv1x1 needs backward computation.
I0605 23:00:04.640838 54715 net.cpp:226] scale_ira_A_1_conv1x1 needs backward computation.
I0605 23:00:04.640843 54715 net.cpp:226] bn_ira_A_1_conv1x1 needs backward computation.
I0605 23:00:04.640848 54715 net.cpp:226] ira_A_1_conv1x1 needs backward computation.
I0605 23:00:04.640853 54715 net.cpp:226] conv3_1b_relu3_1b_0_split needs backward computation.
I0605 23:00:04.640857 54715 net.cpp:226] relu3_1b needs backward computation.
I0605 23:00:04.640862 54715 net.cpp:226] scale_conv3_1b needs backward computation.
I0605 23:00:04.640867 54715 net.cpp:226] bn_conv3_1b needs backward computation.
I0605 23:00:04.640872 54715 net.cpp:226] conv3_1b needs backward computation.
I0605 23:00:04.640877 54715 net.cpp:226] concat_stem_2 needs backward computation.
I0605 23:00:04.640882 54715 net.cpp:226] pool_stem_concat needs backward computation.
I0605 23:00:04.640887 54715 net.cpp:226] relu_stem_concat_conv_3x3 needs backward computation.
I0605 23:00:04.640892 54715 net.cpp:226] scale_stem_concat_conv_3x3 needs backward computation.
I0605 23:00:04.640895 54715 net.cpp:226] bn_stem_concat_conv_3x3 needs backward computation.
I0605 23:00:04.640900 54715 net.cpp:226] stem_concat_conv_3x3 needs backward computation.
I0605 23:00:04.640905 54715 net.cpp:226] concat_stem_1_concat_stem_1_0_split needs backward computation.
I0605 23:00:04.640910 54715 net.cpp:226] concat_stem_1 needs backward computation.
I0605 23:00:04.640915 54715 net.cpp:226] relu2_3x3 needs backward computation.
I0605 23:00:04.640919 54715 net.cpp:226] scale_conv2_3x3 needs backward computation.
I0605 23:00:04.640924 54715 net.cpp:226] bn_conv2_3x3 needs backward computation.
I0605 23:00:04.640929 54715 net.cpp:226] conv2_3x3 needs backward computation.
I0605 23:00:04.640933 54715 net.cpp:226] relu2_7x1 needs backward computation.
I0605 23:00:04.640938 54715 net.cpp:226] scale_conv2_7x1 needs backward computation.
I0605 23:00:04.640942 54715 net.cpp:226] bn_conv2_7x1 needs backward computation.
I0605 23:00:04.640946 54715 net.cpp:226] conv2_7x1 needs backward computation.
I0605 23:00:04.640951 54715 net.cpp:226] relu2_1x7 needs backward computation.
I0605 23:00:04.640955 54715 net.cpp:226] scale_conv2_1x7 needs backward computation.
I0605 23:00:04.640960 54715 net.cpp:226] bn_conv2_1x7 needs backward computation.
I0605 23:00:04.640964 54715 net.cpp:226] conv2_1x7 needs backward computation.
I0605 23:00:04.640969 54715 net.cpp:226] relu2_1x1 needs backward computation.
I0605 23:00:04.640972 54715 net.cpp:226] scale_conv2_1x1 needs backward computation.
I0605 23:00:04.640981 54715 net.cpp:226] bn_conv2_1x1 needs backward computation.
I0605 23:00:04.640985 54715 net.cpp:226] conv2_1x1 needs backward computation.
I0605 23:00:04.640990 54715 net.cpp:226] scale_conv2_1b_3x3 needs backward computation.
I0605 23:00:04.640995 54715 net.cpp:226] bn_conv2_1b_3x3 needs backward computation.
I0605 23:00:04.641000 54715 net.cpp:226] conv2_1b_3x3 needs backward computation.
I0605 23:00:04.641007 54715 net.cpp:226] relu2_1b needs backward computation.
I0605 23:00:04.641017 54715 net.cpp:226] scale_conv2_1b needs backward computation.
I0605 23:00:04.641021 54715 net.cpp:226] bn_conv2_1b needs backward computation.
I0605 23:00:04.641026 54715 net.cpp:226] conv2_1b needs backward computation.
I0605 23:00:04.641032 54715 net.cpp:228] reshape does not need backward computation.
I0605 23:00:04.641036 54715 net.cpp:226] conv1_2_reshape_0_split needs backward computation.
I0605 23:00:04.641041 54715 net.cpp:226] reshape needs backward computation.
I0605 23:00:04.641047 54715 net.cpp:226] relu1_2 needs backward computation.
I0605 23:00:04.641052 54715 net.cpp:226] scale_conv1_2 needs backward computation.
I0605 23:00:04.641055 54715 net.cpp:226] bn_conv1_2 needs backward computation.
I0605 23:00:04.641059 54715 net.cpp:226] conv1_2 needs backward computation.
I0605 23:00:04.641064 54715 net.cpp:226] relu1_1 needs backward computation.
I0605 23:00:04.641069 54715 net.cpp:226] scale_conv1_1 needs backward computation.
I0605 23:00:04.641073 54715 net.cpp:226] bn_conv1_1 needs backward computation.
I0605 23:00:04.641077 54715 net.cpp:226] conv1_1 needs backward computation.
I0605 23:00:04.641083 54715 net.cpp:228] data does not need backward computation.
I0605 23:00:04.641088 54715 net.cpp:270] This network produces output loss_deconv_all
I0605 23:00:04.641261 54715 net.cpp:283] Network initialization done.
I0605 23:00:04.643172 54715 solver.cpp:181] Creating test net (#0) specified by net file: train_val.prototxt
I0605 23:00:04.643364 54715 net.cpp:322] The NetState phase (1) differed from the phase (0) specified by a rule in layer data
I0605 23:00:04.644497 54715 net.cpp:49] Initializing net from parameters:
state {
phase: TEST
}
layer {
name: "data"
type: "PatchData"
top: "data"
top: "label"
include {
phase: TEST
}
patch_sampler_param {
batch_size: 2
data_patch_shape {
dim: 320
dim: 320
dim: 5
}
label_patch_shape {
dim: 320
dim: 320
dim: 1
}
patches_per_data_batch: 6899999
}
transform_nd_param {
mirror: false
padding: true
pad_method: ZERO
}
data_provider_param {
data_source: "/home/ubuntu/membraneTraining_SEMTEM/valid_file.txt"
hdf5_file_shuffle: true
batch_size: 1
backend: HDF5
}
label_select_param {
balance: true
num_labels: 2
num_top_label_balance: 2
reorder_label: false
class_prob_mapping_file: "label_class_selection.prototxt"
}
}
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data"
top: "conv1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
pad: 1
pad: 1
pad: 1
kernel_size: 3
kernel_size: 3
kernel_size: 3
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv1_1"
type: "BatchNorm"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "scale_conv1_1"
type: "Scale"
bottom: "conv1_1"
top: "conv1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu1_1"
type: "ReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "conv1_2"
type: "Convolution"
bottom: "conv1_1"
top: "conv1_2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 1
pad: 1
pad: 0
kernel_size: 3
kernel_size: 3
kernel_size: 3
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv1_2"
type: "BatchNorm"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "scale_conv1_2"
type: "Scale"
bottom: "conv1_2"
top: "conv1_2"
scale_param {
bias_term: true
}
}
layer {
name: "relu1_2"
type: "ReLU"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "reshape"
type: "Reshape"
bottom: "conv1_2"
top: "conv1_2"
reshape_param {
shape {
dim: 0
dim: 0
dim: 0
dim: 0
}
}
}
layer {
name: "reshape"
type: "Reshape"
bottom: "label"
top: "label"
reshape_param {
shape {
dim: 0
dim: 0
dim: 0
dim: 0
}
}
}
layer {
name: "conv2_1b"
type: "Convolution"
bottom: "conv1_2"
top: "conv2_1b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_1b"
type: "BatchNorm"
bottom: "conv2_1b"
top: "conv2_1b"
}
layer {
name: "scale_conv2_1b"
type: "Scale"
bottom: "conv2_1b"
top: "conv2_1b"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_1b"
type: "ReLU"
bottom: "conv2_1b"
top: "conv2_1b"
}
layer {
name: "conv2_1b_3x3"
type: "Convolution"
bottom: "conv2_1b"
top: "conv2_1b_3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 96
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_1b_3x3"
type: "BatchNorm"
bottom: "conv2_1b_3x3"
top: "conv2_1b_3x3"
}
layer {
name: "scale_conv2_1b_3x3"
type: "Scale"
bottom: "conv2_1b_3x3"
top: "conv2_1b_3x3"
scale_param {
bias_term: true
}
}
layer {
name: "conv2_1x1"
type: "Convolution"
bottom: "conv1_2"
top: "conv2_1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_1x1"
type: "BatchNorm"
bottom: "conv2_1x1"
top: "conv2_1x1"
}
layer {
name: "scale_conv2_1x1"
type: "Scale"
bottom: "conv2_1x1"
top: "conv2_1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_1x1"
type: "ReLU"
bottom: "conv2_1x1"
top: "conv2_1x1"
}
layer {
name: "conv2_1x7"
type: "Convolution"
bottom: "conv2_1x1"
top: "conv2_1x7"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 3
pad_w: 0
kernel_h: 7
kernel_w: 1
}
}
layer {
name: "bn_conv2_1x7"
type: "BatchNorm"
bottom: "conv2_1x7"
top: "conv2_1x7"
}
layer {
name: "scale_conv2_1x7"
type: "Scale"
bottom: "conv2_1x7"
top: "conv2_1x7"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_1x7"
type: "ReLU"
bottom: "conv2_1x7"
top: "conv2_1x7"
}
layer {
name: "conv2_7x1"
type: "Convolution"
bottom: "conv2_1x7"
top: "conv2_7x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 0
pad_w: 3
kernel_h: 1
kernel_w: 7
}
}
layer {
name: "bn_conv2_7x1"
type: "BatchNorm"
bottom: "conv2_7x1"
top: "conv2_7x1"
}
layer {
name: "scale_conv2_7x1"
type: "Scale"
bottom: "conv2_7x1"
top: "conv2_7x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_7x1"
type: "ReLU"
bottom: "conv2_7x1"
top: "conv2_7x1"
}
layer {
name: "conv2_3x3"
type: "Convolution"
bottom: "conv2_7x1"
top: "conv2_3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 96
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv2_3x3"
type: "BatchNorm"
bottom: "conv2_3x3"
top: "conv2_3x3"
}
layer {
name: "scale_conv2_3x3"
type: "Scale"
bottom: "conv2_3x3"
top: "conv2_3x3"
scale_param {
bias_term: true
}
}
layer {
name: "relu2_3x3"
type: "ReLU"
bottom: "conv2_3x3"
top: "conv2_3x3"
}
layer {
name: "concat_stem_1"
type: "Concat"
bottom: "conv2_1b_3x3"
bottom: "conv2_3x3"
top: "concat_stem_1"
}
layer {
name: "stem_concat_conv_3x3"
type: "Convolution"
bottom: "concat_stem_1"
top: "stem_concat_conv_3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 192
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_stem_concat_conv_3x3"
type: "BatchNorm"
bottom: "stem_concat_conv_3x3"
top: "stem_concat_conv_3x3"
}
layer {
name: "scale_stem_concat_conv_3x3"
type: "Scale"
bottom: "stem_concat_conv_3x3"
top: "stem_concat_conv_3x3"
scale_param {
bias_term: true
}
}
layer {
name: "relu_stem_concat_conv_3x3"
type: "ReLU"
bottom: "stem_concat_conv_3x3"
top: "stem_concat_conv_3x3"
}
layer {
name: "pool_stem_concat"
type: "Pooling"
bottom: "concat_stem_1"
top: "pool_stem_concat"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "concat_stem_2"
type: "Concat"
bottom: "pool_stem_concat"
bottom: "stem_concat_conv_3x3"
top: "concat_stem_2"
}
layer {
name: "conv3_1b"
type: "Convolution"
bottom: "concat_stem_2"
top: "conv3_1b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv3_1b"
type: "BatchNorm"
bottom: "conv3_1b"
top: "conv3_1b"
}
layer {
name: "scale_conv3_1b"
type: "Scale"
bottom: "conv3_1b"
top: "conv3_1b"
scale_param {
bias_term: true
}
}
layer {
name: "relu3_1b"
type: "ReLU"
bottom: "conv3_1b"
top: "conv3_1b"
}
layer {
name: "ira_A_1_conv1x1"
type: "Convolution"
bottom: "conv3_1b"
top: "ira_A_1_conv1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_1_conv1x1"
type: "BatchNorm"
bottom: "ira_A_1_conv1x1"
top: "ira_A_1_conv1x1"
}
layer {
name: "scale_ira_A_1_conv1x1"
type: "Scale"
bottom: "ira_A_1_conv1x1"
top: "ira_A_1_conv1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_1_conv1x1"
type: "ReLU"
bottom: "ira_A_1_conv1x1"
top: "ira_A_1_conv1x1"
}
layer {
name: "ira_A_2_conv1x1"
type: "Convolution"
bottom: "conv3_1b"
top: "ira_A_2_conv1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_2_conv1x1"
type: "BatchNorm"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv1x1"
}
layer {
name: "scale_ira_A_2_conv1x1"
type: "Scale"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_2_conv1x1"
type: "ReLU"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv1x1"
}
layer {
name: "ira_A_2_conv3x3"
type: "Convolution"
bottom: "ira_A_2_conv1x1"
top: "ira_A_2_conv3x3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_2_conv3x3"
type: "BatchNorm"
bottom: "ira_A_2_conv3x3"
top: "ira_A_2_conv3x3"
}
layer {
name: "scale_ira_A_2_conv3x3"
type: "Scale"
bottom: "ira_A_2_conv3x3"
top: "ira_A_2_conv3x3"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_2_conv3x3"
type: "ReLU"
bottom: "ira_A_2_conv3x3"
top: "ira_A_2_conv3x3"
}
layer {
name: "ira_A_3_conv1x1"
type: "Convolution"
bottom: "conv3_1b"
top: "ira_A_3_conv1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_3_conv1x1"
type: "BatchNorm"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv1x1"
}
layer {
name: "scale_ira_A_3_conv1x1"
type: "Scale"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv1x1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_3_conv1x1"
type: "ReLU"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv1x1"
}
layer {
name: "ira_A_3_conv3x3_1"
type: "Convolution"
bottom: "ira_A_3_conv1x1"
top: "ira_A_3_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 48
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_3_conv3x3_1"
type: "BatchNorm"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_1"
}
layer {
name: "scale_ira_A_3_conv3x3_1"
type: "Scale"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_3_conv3x3_1"
type: "ReLU"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_1"
}
layer {
name: "ira_A_3_conv3x3_2"
type: "Convolution"
bottom: "ira_A_3_conv3x3_1"
top: "ira_A_3_conv3x3_2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_A_3_conv3x3_2"
type: "BatchNorm"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_3_conv3x3_2"
}
layer {
name: "scale_ira_A_3_conv3x3_2"
type: "Scale"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_3_conv3x3_2"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_A_3_conv3x3_2"
type: "ReLU"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_3_conv3x3_2"
}
layer {
name: "ira_A_concat"
type: "Concat"
bottom: "ira_A_1_conv1x1"
bottom: "ira_A_2_conv3x3"
bottom: "ira_A_3_conv3x3_2"
top: "ira_A_concat"
}
layer {
name: "ira_A_concat_top_conv_1x1"
type: "Convolution"
bottom: "ira_A_concat"
top: "ira_A_concat_top_conv_1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ra_A_concat_top_conv_1x1"
type: "BatchNorm"
bottom: "ira_A_concat_top_conv_1x1"
top: "ira_A_concat_top_conv_1x1"
}
layer {
name: "scale_ra_A_concat_top_conv_1x1"
type: "Scale"
bottom: "ira_A_concat_top_conv_1x1"
top: "ira_A_concat_top_conv_1x1"
scale_param {
bias_term: true
}
}
layer {
name: "conv3_sum"
type: "Eltwise"
bottom: "conv3_1b"
bottom: "ira_A_concat_top_conv_1x1"
top: "conv3_sum"
eltwise_param {
operation: SUM
coeff: 1
coeff: 0.1
}
}
layer {
name: "relu3_sum"
type: "ReLU"
bottom: "conv3_sum"
top: "conv3_sum"
}
layer {
name: "ira_v4_reduction_A/pool"
type: "Pooling"
bottom: "conv3_sum"
top: "ira_v4_reduction_A/pool"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "ira_v4_reduction_A/conv3x3_reduction_b"
type: "Convolution"
bottom: "conv3_sum"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv3x3_reduction_b"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
}
layer {
name: "scale_ira_v4_reduction_A/conv3x3_reduction_b"
type: "Scale"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv3x3_reduction_b"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
top: "ira_v4_reduction_A/conv3x3_reduction_b"
}
layer {
name: "ira_v4_reduction_A/conv1x1_c"
type: "Convolution"
bottom: "conv3_sum"
top: "ira_v4_reduction_A/conv1x1_c"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv1x1_c"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv1x1_c"
}
layer {
name: "scale_ira_v4_reduction_A/conv1x1_c"
type: "Scale"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv1x1_c"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv1x1_c"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv1x1_c"
}
layer {
name: "ira_v4_reduction_A/conv3x3_c"
type: "Convolution"
bottom: "ira_v4_reduction_A/conv1x1_c"
top: "ira_v4_reduction_A/conv3x3_c"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv3x3_c"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_c"
}
layer {
name: "scale_ira_v4_reduction_A/conv3x3_c"
type: "Scale"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_c"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv3x3_c"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_c"
}
layer {
name: "ira_v4_reduction_A/conv3x3_reduction_c"
type: "Convolution"
bottom: "ira_v4_reduction_A/conv3x3_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_v4_reduction_A/conv3x3_reduction_c"
type: "BatchNorm"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
}
layer {
name: "scale_ira_v4_reduction_A/conv3x3_reduction_c"
type: "Scale"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_v4_reduction_A/conv3x3_reduction_c"
type: "ReLU"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/conv3x3_reduction_c"
}
layer {
name: "ira_v4_reduction_A/concat"
type: "Concat"
bottom: "ira_v4_reduction_A/pool"
bottom: "ira_v4_reduction_A/conv3x3_reduction_b"
bottom: "ira_v4_reduction_A/conv3x3_reduction_c"
top: "ira_v4_reduction_A/concat"
}
layer {
name: "conv4_1b"
type: "Convolution"
bottom: "ira_v4_reduction_A/concat"
top: "conv4_1b"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 1154
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_conv4_1b"
type: "BatchNorm"
bottom: "conv4_1b"
top: "conv4_1b"
}
layer {
name: "scale_conv4_1b"
type: "Scale"
bottom: "conv4_1b"
top: "conv4_1b"
scale_param {
bias_term: true
}
}
layer {
name: "relu4_1b"
type: "ReLU"
bottom: "conv4_1b"
top: "conv4_1b"
}
layer {
name: "ira_Inception_B_block_1/a_conv1x1_1"
type: "Convolution"
bottom: "conv4_1b"
top: "ira_Inception_B_block_1/a_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 192
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Inception_B_block_1/a_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
top: "ira_Inception_B_block_1/a_conv1x1_1"
}
layer {
name: "scale_ira_Inception_B_block_1/a_conv1x1_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
top: "ira_Inception_B_block_1/a_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/a_conv1x1_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
top: "ira_Inception_B_block_1/a_conv1x1_1"
}
layer {
name: "ira_Inception_B_block_1/b_conv1x1_1"
type: "Convolution"
bottom: "conv4_1b"
top: "ira_Inception_B_block_1/b_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 128
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Inception_B_block_1/b_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x1_1"
}
layer {
name: "scale_ira_Inception_B_block_1/b_conv1x1_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/b_conv1x1_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x1_1"
}
layer {
name: "ira_Inception_B_block_1/b_conv1x7_1"
type: "Convolution"
bottom: "ira_Inception_B_block_1/b_conv1x1_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 160
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 0
pad_w: 3
kernel_h: 1
kernel_w: 7
}
}
layer {
name: "bn_ira_Inception_B_block_1/b_conv1x7_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
}
layer {
name: "scale_ira_Inception_B_block_1/b_conv1x7_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/b_conv1x7_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv1x7_1"
}
layer {
name: "ira_Inception_B_block_1/b_conv7x1_1"
type: "Convolution"
bottom: "ira_Inception_B_block_1/b_conv1x7_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 192
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
pad_h: 3
pad_w: 0
kernel_h: 7
kernel_w: 1
}
}
layer {
name: "bn_ira_Inception_B_block_1/b_conv7x1_1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
}
layer {
name: "scale_ira_Inception_B_block_1/b_conv7x1_1"
type: "Scale"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Inception_B_block_1/b_conv7x1_1"
type: "ReLU"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/b_conv7x1_1"
}
layer {
name: "ira_Inception_B_block_1/concat"
type: "Concat"
bottom: "ira_Inception_B_block_1/a_conv1x1_1"
bottom: "ira_Inception_B_block_1/b_conv7x1_1"
top: "ira_Inception_B_block_1/concat"
}
layer {
name: "ira_Inception_B_block_1/top_conv_1x1"
type: "Convolution"
bottom: "ira_Inception_B_block_1/concat"
top: "ira_Inception_B_block_1/top_conv_1x1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 1154
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Inception_B_block_1/top_conv_1x1"
type: "BatchNorm"
bottom: "ira_Inception_B_block_1/top_conv_1x1"
top: "ira_Inception_B_block_1/top_conv_1x1"
}
layer {
name: "scale_ira_Inception_B_block_1/top_conv_1x1"
type: "Scale"
bottom: "ira_Inception_B_block_1/top_conv_1x1"
top: "ira_Inception_B_block_1/top_conv_1x1"
scale_param {
bias_term: true
}
}
layer {
name: "conv4_sum"
type: "Eltwise"
bottom: "conv4_1b"
bottom: "ira_Inception_B_block_1/top_conv_1x1"
top: "conv4_sum"
eltwise_param {
operation: SUM
coeff: 1
coeff: 0.1
}
}
layer {
name: "relu_conv4_sum"
type: "ReLU"
bottom: "conv4_sum"
top: "conv4_sum"
}
layer {
name: "ira_Reduction_B_block_1/a_pool"
type: "Pooling"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/a_pool"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "ira_Reduction_B_block_1/b_conv1x1_1"
type: "Convolution"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/b_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/b_conv1x1_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/b_conv1x1_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv1x1_1"
}
layer {
name: "ira_Reduction_B_block_1/b_conv3x3_1"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/b_conv1x1_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/b_conv3x3_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/b_conv3x3_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/b_conv3x3_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/b_conv3x3_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/b_conv3x3_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/b_conv3x3_1"
top: "ira_Reduction_B_block_1/b_conv3x3_1"
}
layer {
name: "ira_Reduction_B_block_1/c_conv1x1_1"
type: "Convolution"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/c_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/c_conv1x1_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/c_conv1x1_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv1x1_1"
}
layer {
name: "ira_Reduction_B_block_1/c_conv3x3_1"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/c_conv1x1_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 288
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/c_conv3x3_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/c_conv3x3_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/c_conv3x3_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/c_conv3x3_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/c_conv3x3_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/c_conv3x3_1"
top: "ira_Reduction_B_block_1/c_conv3x3_1"
}
layer {
name: "ira_Reduction_B_block_1/d_conv1x1_1"
type: "Convolution"
bottom: "conv4_sum"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/d_conv1x1_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/d_conv1x1_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/d_conv1x1_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv1x1_1"
}
layer {
name: "ira_Reduction_B_block_1/d_conv3x3_1"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/d_conv1x1_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param {
num_output: 288
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bn_ira_Reduction_B_block_1/d_conv3x3_1"
type: "BatchNorm"
bottom: "ira_Reduction_B_block_1/d_conv3x3_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
}
layer {
name: "scale_ira_Reduction_B_block_1/d_conv3x3_1"
type: "Scale"
bottom: "ira_Reduction_B_block_1/d_conv3x3_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
scale_param {
bias_term: true
}
}
layer {
name: "relu_ira_Reduction_B_block_1/d_conv3x3_1"
type: "ReLU"
bottom: "ira_Reduction_B_block_1/d_conv3x3_1"
top: "ira_Reduction_B_block_1/d_conv3x3_1"
}
layer {
name: "ira_Reduction_B_block_1/d_conv3x3_2"
type: "Convolution"
bottom: "ira_Reduction_B_block_1/d_con
I0605 23:00:04.645239 54715 layer_factory.hpp:77] Creating layer data
I0605 23:00:04.645270 54715 data_provider.cpp:28] Loading list of HDF5 filenames from: /home/ubuntu/membraneTraining_SEMTEM/valid_file.txt
I0605 23:00:04.645304 54715 data_provider.cpp:42] Number of HDF5 files: 16
I0605 23:00:04.645398 54715 sample_selector.cpp:58] read prob from file : label_class_selection.prototxt
I0605 23:00:04.645459 54715 sample_selector.cpp:78] rest_of_label_mapping_ = 0 1
I0605 23:00:04.645469 54715 sample_selector.cpp:93] label map :0--->0
I0605 23:00:04.645475 54715 sample_selector.cpp:93] label map :1--->1
I0605 23:00:04.645479 54715 sample_selector.cpp:95] label_prob_map_ size =2
I0605 23:00:04.645486 54715 sample_selector.cpp:116] scale_factor = 3.33333
I0605 23:00:04.645495 54715 sample_selector.cpp:117] bottom_prob = 0.3
I0605 23:00:04.645500 54715 sample_selector.cpp:118] label_prob_vec.size = 2
I0605 23:00:04.645505 54715 sample_selector.cpp:164] size of prob = 1
I0605 23:00:04.645510 54715 sample_selector.cpp:19] lable class [0] weight =0.25
I0605 23:00:04.645521 54715 sample_selector.cpp:19] lable class [1] weight =1
I0605 23:00:04.645606 54715 patch_sampler.cpp:57] runner setup done ... count =0
I0605 23:00:04.645620 54715 net.cpp:106] Creating Layer data
I0605 23:00:04.645628 54715 net.cpp:411] data -> data
I0605 23:00:04.645642 54715 net.cpp:411] data -> label
I0605 23:00:04.645663 54715 patch_sampler.cpp:121] loading batch patch_count = 0
I0605 23:00:04.813477 54773 patch_sampler.cpp:319] solver_count = 1 size of queue pairs = 1
I0605 23:00:04.813501 54773 patch_sampler.cpp:323] size of queue is now = 0
I0605 23:00:05.347086 54715 data_provider.cpp:108] d_size =3
I0605 23:00:05.347118 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:05.347123 54715 data_provider.cpp:111] loaded data shape : 1024
I0605 23:00:05.347127 54715 data_provider.cpp:111] loaded data shape : 100
I0605 23:00:05.347131 54715 data_provider.cpp:113]
I0605 23:00:05.347136 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:05.347138 54715 data_provider.cpp:115] loaded label shape : 1024
I0605 23:00:05.347142 54715 data_provider.cpp:115] loaded label shape : 100
I0605 23:00:05.347297 54715 data_provider.cpp:144] d_size =5
I0605 23:00:05.347306 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:05.347309 54715 data_provider.cpp:147] data shape after prependig : 1
I0605 23:00:05.347313 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:05.347316 54715 data_provider.cpp:147] data shape after prependig : 1024
I0605 23:00:05.347321 54715 data_provider.cpp:147] data shape after prependig : 100
I0605 23:00:05.347324 54715 data_provider.cpp:149]
I0605 23:00:05.347328 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:05.347332 54715 data_provider.cpp:151] label shape after prependig : 1
I0605 23:00:05.347337 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:05.347340 54715 data_provider.cpp:151] label shape after prependig : 1024
I0605 23:00:05.347344 54715 data_provider.cpp:151] label shape after prependig : 100
I0605 23:00:05.347348 54715 data_provider.cpp:175] loaded hdf5 file /home/ubuntu/combined_membranetraining//training_full_stacks_v16.h5
I0605 23:00:05.379120 54715 patch_data_layer.cpp:43] reshape top data = 2
I0605 23:00:05.379143 54715 patch_data_layer.cpp:43] reshape top data = 1
I0605 23:00:05.379148 54715 patch_data_layer.cpp:43] reshape top data = 320
I0605 23:00:05.379151 54715 patch_data_layer.cpp:43] reshape top data = 320
I0605 23:00:05.379155 54715 patch_data_layer.cpp:43] reshape top data = 5
I0605 23:00:05.380970 54715 patch_data_layer.cpp:48] reshape prefetch_[0].data_
I0605 23:00:05.381002 54715 patch_data_layer.cpp:48] reshape prefetch_[1].data_
I0605 23:00:05.381028 54715 patch_data_layer.cpp:48] reshape prefetch_[2].data_
I0605 23:00:05.381036 54715 patch_data_layer.cpp:57] reshape top label = 2
I0605 23:00:05.381039 54715 patch_data_layer.cpp:57] reshape top label = 1
I0605 23:00:05.381042 54715 patch_data_layer.cpp:57] reshape top label = 320
I0605 23:00:05.381047 54715 patch_data_layer.cpp:57] reshape top label = 320
I0605 23:00:05.381050 54715 patch_data_layer.cpp:57] reshape top label = 1
I0605 23:00:05.394606 54715 net.cpp:150] Setting up data
I0605 23:00:05.394630 54715 net.cpp:157] Top shape: 2 1 320 320 5 (1024000)
I0605 23:00:05.394637 54715 net.cpp:157] Top shape: 2 1 320 320 1 (204800)
I0605 23:00:05.394641 54715 net.cpp:165] Memory required for data: 4915200
I0605 23:00:05.394650 54715 layer_factory.hpp:77] Creating layer conv1_1
I0605 23:00:05.394668 54715 net.cpp:106] Creating Layer conv1_1
I0605 23:00:05.394675 54715 net.cpp:454] conv1_1 <- data
I0605 23:00:05.394685 54715 net.cpp:411] conv1_1 -> conv1_1
I0605 23:00:05.395264 54715 net.cpp:150] Setting up conv1_1
I0605 23:00:05.395277 54715 net.cpp:157] Top shape: 2 32 160 160 3 (4915200)
I0605 23:00:05.395282 54715 net.cpp:165] Memory required for data: 24576000
I0605 23:00:05.395295 54715 layer_factory.hpp:77] Creating layer bn_conv1_1
I0605 23:00:05.395313 54715 net.cpp:106] Creating Layer bn_conv1_1
I0605 23:00:05.395325 54715 net.cpp:454] bn_conv1_1 <- conv1_1
I0605 23:00:05.395334 54715 net.cpp:397] bn_conv1_1 -> conv1_1 (in-place)
I0605 23:00:05.395617 54715 net.cpp:150] Setting up bn_conv1_1
I0605 23:00:05.395627 54715 net.cpp:157] Top shape: 2 32 160 160 3 (4915200)
I0605 23:00:05.395630 54715 net.cpp:165] Memory required for data: 44236800
I0605 23:00:05.395642 54715 layer_factory.hpp:77] Creating layer scale_conv1_1
I0605 23:00:05.395653 54715 net.cpp:106] Creating Layer scale_conv1_1
I0605 23:00:05.395658 54715 net.cpp:454] scale_conv1_1 <- conv1_1
I0605 23:00:05.395663 54715 net.cpp:397] scale_conv1_1 -> conv1_1 (in-place)
I0605 23:00:05.395721 54715 layer_factory.hpp:77] Creating layer scale_conv1_1
I0605 23:00:05.395956 54715 net.cpp:150] Setting up scale_conv1_1
I0605 23:00:05.395964 54715 net.cpp:157] Top shape: 2 32 160 160 3 (4915200)
I0605 23:00:05.395968 54715 net.cpp:165] Memory required for data: 63897600
I0605 23:00:05.395975 54715 layer_factory.hpp:77] Creating layer relu1_1
I0605 23:00:05.395984 54715 net.cpp:106] Creating Layer relu1_1
I0605 23:00:05.395988 54715 net.cpp:454] relu1_1 <- conv1_1
I0605 23:00:05.395995 54715 net.cpp:397] relu1_1 -> conv1_1 (in-place)
I0605 23:00:05.396001 54715 net.cpp:150] Setting up relu1_1
I0605 23:00:05.396008 54715 net.cpp:157] Top shape: 2 32 160 160 3 (4915200)
I0605 23:00:05.396013 54715 net.cpp:165] Memory required for data: 83558400
I0605 23:00:05.396015 54715 layer_factory.hpp:77] Creating layer conv1_2
I0605 23:00:05.396025 54715 net.cpp:106] Creating Layer conv1_2
I0605 23:00:05.396030 54715 net.cpp:454] conv1_2 <- conv1_1
I0605 23:00:05.396037 54715 net.cpp:411] conv1_2 -> conv1_2
I0605 23:00:05.397150 54715 net.cpp:150] Setting up conv1_2
I0605 23:00:05.397163 54715 net.cpp:157] Top shape: 2 64 160 160 1 (3276800)
I0605 23:00:05.397168 54715 net.cpp:165] Memory required for data: 96665600
I0605 23:00:05.397178 54715 layer_factory.hpp:77] Creating layer bn_conv1_2
I0605 23:00:05.397186 54715 net.cpp:106] Creating Layer bn_conv1_2
I0605 23:00:05.397192 54715 net.cpp:454] bn_conv1_2 <- conv1_2
I0605 23:00:05.397199 54715 net.cpp:397] bn_conv1_2 -> conv1_2 (in-place)
I0605 23:00:05.398236 54715 net.cpp:150] Setting up bn_conv1_2
I0605 23:00:05.398247 54715 net.cpp:157] Top shape: 2 64 160 160 1 (3276800)
I0605 23:00:05.398250 54715 net.cpp:165] Memory required for data: 109772800
I0605 23:00:05.398260 54715 layer_factory.hpp:77] Creating layer scale_conv1_2
I0605 23:00:05.398267 54715 net.cpp:106] Creating Layer scale_conv1_2
I0605 23:00:05.398272 54715 net.cpp:454] scale_conv1_2 <- conv1_2
I0605 23:00:05.398277 54715 net.cpp:397] scale_conv1_2 -> conv1_2 (in-place)
I0605 23:00:05.398329 54715 layer_factory.hpp:77] Creating layer scale_conv1_2
I0605 23:00:05.398519 54715 net.cpp:150] Setting up scale_conv1_2
I0605 23:00:05.398527 54715 net.cpp:157] Top shape: 2 64 160 160 1 (3276800)
I0605 23:00:05.398531 54715 net.cpp:165] Memory required for data: 122880000
I0605 23:00:05.398540 54715 layer_factory.hpp:77] Creating layer relu1_2
I0605 23:00:05.398547 54715 net.cpp:106] Creating Layer relu1_2
I0605 23:00:05.398552 54715 net.cpp:454] relu1_2 <- conv1_2
I0605 23:00:05.398558 54715 net.cpp:397] relu1_2 -> conv1_2 (in-place)
I0605 23:00:05.398566 54715 net.cpp:150] Setting up relu1_2
I0605 23:00:05.398571 54715 net.cpp:157] Top shape: 2 64 160 160 1 (3276800)
I0605 23:00:05.398574 54715 net.cpp:165] Memory required for data: 135987200
I0605 23:00:05.398578 54715 layer_factory.hpp:77] Creating layer reshape
I0605 23:00:05.398587 54715 net.cpp:106] Creating Layer reshape
I0605 23:00:05.398591 54715 net.cpp:454] reshape <- conv1_2
I0605 23:00:05.398597 54715 net.cpp:397] reshape -> conv1_2 (in-place)
I0605 23:00:05.398604 54715 net.cpp:150] Setting up reshape
I0605 23:00:05.398610 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.398614 54715 net.cpp:165] Memory required for data: 149094400
I0605 23:00:05.398618 54715 layer_factory.hpp:77] Creating layer conv1_2_reshape_0_split
I0605 23:00:05.398632 54715 net.cpp:106] Creating Layer conv1_2_reshape_0_split
I0605 23:00:05.398643 54715 net.cpp:454] conv1_2_reshape_0_split <- conv1_2
I0605 23:00:05.398649 54715 net.cpp:411] conv1_2_reshape_0_split -> conv1_2_reshape_0_split_0
I0605 23:00:05.398658 54715 net.cpp:411] conv1_2_reshape_0_split -> conv1_2_reshape_0_split_1
I0605 23:00:05.398706 54715 net.cpp:150] Setting up conv1_2_reshape_0_split
I0605 23:00:05.398715 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.398720 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.398725 54715 net.cpp:165] Memory required for data: 175308800
I0605 23:00:05.398728 54715 layer_factory.hpp:77] Creating layer reshape
I0605 23:00:05.398736 54715 net.cpp:106] Creating Layer reshape
I0605 23:00:05.398739 54715 net.cpp:454] reshape <- label
I0605 23:00:05.398747 54715 net.cpp:397] reshape -> label (in-place)
I0605 23:00:05.398754 54715 net.cpp:150] Setting up reshape
I0605 23:00:05.398761 54715 net.cpp:157] Top shape: 2 1 320 320 (204800)
I0605 23:00:05.398763 54715 net.cpp:165] Memory required for data: 176128000
I0605 23:00:05.398767 54715 layer_factory.hpp:77] Creating layer label_reshape_0_split
I0605 23:00:05.398774 54715 net.cpp:106] Creating Layer label_reshape_0_split
I0605 23:00:05.398778 54715 net.cpp:454] label_reshape_0_split <- label
I0605 23:00:05.398784 54715 net.cpp:411] label_reshape_0_split -> label_reshape_0_split_0
I0605 23:00:05.398792 54715 net.cpp:411] label_reshape_0_split -> label_reshape_0_split_1
I0605 23:00:05.398833 54715 net.cpp:150] Setting up label_reshape_0_split
I0605 23:00:05.398841 54715 net.cpp:157] Top shape: 2 1 320 320 (204800)
I0605 23:00:05.398845 54715 net.cpp:157] Top shape: 2 1 320 320 (204800)
I0605 23:00:05.398849 54715 net.cpp:165] Memory required for data: 177766400
I0605 23:00:05.398854 54715 layer_factory.hpp:77] Creating layer conv2_1b
I0605 23:00:05.398864 54715 net.cpp:106] Creating Layer conv2_1b
I0605 23:00:05.398867 54715 net.cpp:454] conv2_1b <- conv1_2_reshape_0_split_0
I0605 23:00:05.398875 54715 net.cpp:411] conv2_1b -> conv2_1b
I0605 23:00:05.399204 54715 net.cpp:150] Setting up conv2_1b
I0605 23:00:05.399214 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.399219 54715 net.cpp:165] Memory required for data: 190873600
I0605 23:00:05.399225 54715 layer_factory.hpp:77] Creating layer bn_conv2_1b
I0605 23:00:05.399233 54715 net.cpp:106] Creating Layer bn_conv2_1b
I0605 23:00:05.399238 54715 net.cpp:454] bn_conv2_1b <- conv2_1b
I0605 23:00:05.399245 54715 net.cpp:397] bn_conv2_1b -> conv2_1b (in-place)
I0605 23:00:05.399504 54715 net.cpp:150] Setting up bn_conv2_1b
I0605 23:00:05.399513 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.399518 54715 net.cpp:165] Memory required for data: 203980800
I0605 23:00:05.399529 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b
I0605 23:00:05.399538 54715 net.cpp:106] Creating Layer scale_conv2_1b
I0605 23:00:05.399543 54715 net.cpp:454] scale_conv2_1b <- conv2_1b
I0605 23:00:05.399549 54715 net.cpp:397] scale_conv2_1b -> conv2_1b (in-place)
I0605 23:00:05.399598 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b
I0605 23:00:05.399786 54715 net.cpp:150] Setting up scale_conv2_1b
I0605 23:00:05.399796 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.399801 54715 net.cpp:165] Memory required for data: 217088000
I0605 23:00:05.399807 54715 layer_factory.hpp:77] Creating layer relu2_1b
I0605 23:00:05.399816 54715 net.cpp:106] Creating Layer relu2_1b
I0605 23:00:05.399821 54715 net.cpp:454] relu2_1b <- conv2_1b
I0605 23:00:05.399827 54715 net.cpp:397] relu2_1b -> conv2_1b (in-place)
I0605 23:00:05.399833 54715 net.cpp:150] Setting up relu2_1b
I0605 23:00:05.399838 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.399842 54715 net.cpp:165] Memory required for data: 230195200
I0605 23:00:05.399847 54715 layer_factory.hpp:77] Creating layer conv2_1b_3x3
I0605 23:00:05.399857 54715 net.cpp:106] Creating Layer conv2_1b_3x3
I0605 23:00:05.399860 54715 net.cpp:454] conv2_1b_3x3 <- conv2_1b
I0605 23:00:05.399873 54715 net.cpp:411] conv2_1b_3x3 -> conv2_1b_3x3
I0605 23:00:05.401931 54715 net.cpp:150] Setting up conv2_1b_3x3
I0605 23:00:05.401947 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.401952 54715 net.cpp:165] Memory required for data: 249856000
I0605 23:00:05.401960 54715 layer_factory.hpp:77] Creating layer bn_conv2_1b_3x3
I0605 23:00:05.401969 54715 net.cpp:106] Creating Layer bn_conv2_1b_3x3
I0605 23:00:05.401974 54715 net.cpp:454] bn_conv2_1b_3x3 <- conv2_1b_3x3
I0605 23:00:05.401981 54715 net.cpp:397] bn_conv2_1b_3x3 -> conv2_1b_3x3 (in-place)
I0605 23:00:05.402225 54715 net.cpp:150] Setting up bn_conv2_1b_3x3
I0605 23:00:05.402235 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.402238 54715 net.cpp:165] Memory required for data: 269516800
I0605 23:00:05.402246 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b_3x3
I0605 23:00:05.402254 54715 net.cpp:106] Creating Layer scale_conv2_1b_3x3
I0605 23:00:05.402259 54715 net.cpp:454] scale_conv2_1b_3x3 <- conv2_1b_3x3
I0605 23:00:05.402266 54715 net.cpp:397] scale_conv2_1b_3x3 -> conv2_1b_3x3 (in-place)
I0605 23:00:05.402315 54715 layer_factory.hpp:77] Creating layer scale_conv2_1b_3x3
I0605 23:00:05.402477 54715 net.cpp:150] Setting up scale_conv2_1b_3x3
I0605 23:00:05.402487 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.402490 54715 net.cpp:165] Memory required for data: 289177600
I0605 23:00:05.402498 54715 layer_factory.hpp:77] Creating layer conv2_1x1
I0605 23:00:05.402506 54715 net.cpp:106] Creating Layer conv2_1x1
I0605 23:00:05.402513 54715 net.cpp:454] conv2_1x1 <- conv1_2_reshape_0_split_1
I0605 23:00:05.402520 54715 net.cpp:411] conv2_1x1 -> conv2_1x1
I0605 23:00:05.404240 54715 net.cpp:150] Setting up conv2_1x1
I0605 23:00:05.404253 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.404258 54715 net.cpp:165] Memory required for data: 302284800
I0605 23:00:05.404265 54715 layer_factory.hpp:77] Creating layer bn_conv2_1x1
I0605 23:00:05.404273 54715 net.cpp:106] Creating Layer bn_conv2_1x1
I0605 23:00:05.404278 54715 net.cpp:454] bn_conv2_1x1 <- conv2_1x1
I0605 23:00:05.404285 54715 net.cpp:397] bn_conv2_1x1 -> conv2_1x1 (in-place)
I0605 23:00:05.404527 54715 net.cpp:150] Setting up bn_conv2_1x1
I0605 23:00:05.404536 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.404539 54715 net.cpp:165] Memory required for data: 315392000
I0605 23:00:05.404552 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x1
I0605 23:00:05.404561 54715 net.cpp:106] Creating Layer scale_conv2_1x1
I0605 23:00:05.404564 54715 net.cpp:454] scale_conv2_1x1 <- conv2_1x1
I0605 23:00:05.404572 54715 net.cpp:397] scale_conv2_1x1 -> conv2_1x1 (in-place)
I0605 23:00:05.404623 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x1
I0605 23:00:05.404783 54715 net.cpp:150] Setting up scale_conv2_1x1
I0605 23:00:05.404793 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.404796 54715 net.cpp:165] Memory required for data: 328499200
I0605 23:00:05.404803 54715 layer_factory.hpp:77] Creating layer relu2_1x1
I0605 23:00:05.404810 54715 net.cpp:106] Creating Layer relu2_1x1
I0605 23:00:05.404814 54715 net.cpp:454] relu2_1x1 <- conv2_1x1
I0605 23:00:05.404820 54715 net.cpp:397] relu2_1x1 -> conv2_1x1 (in-place)
I0605 23:00:05.404827 54715 net.cpp:150] Setting up relu2_1x1
I0605 23:00:05.404832 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.404836 54715 net.cpp:165] Memory required for data: 341606400
I0605 23:00:05.404840 54715 layer_factory.hpp:77] Creating layer conv2_1x7
I0605 23:00:05.404850 54715 net.cpp:106] Creating Layer conv2_1x7
I0605 23:00:05.404853 54715 net.cpp:454] conv2_1x7 <- conv2_1x1
I0605 23:00:05.404861 54715 net.cpp:411] conv2_1x7 -> conv2_1x7
I0605 23:00:05.405305 54715 net.cpp:150] Setting up conv2_1x7
I0605 23:00:05.405314 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.405318 54715 net.cpp:165] Memory required for data: 354713600
I0605 23:00:05.405325 54715 layer_factory.hpp:77] Creating layer bn_conv2_1x7
I0605 23:00:05.405344 54715 net.cpp:106] Creating Layer bn_conv2_1x7
I0605 23:00:05.405350 54715 net.cpp:454] bn_conv2_1x7 <- conv2_1x7
I0605 23:00:05.405356 54715 net.cpp:397] bn_conv2_1x7 -> conv2_1x7 (in-place)
I0605 23:00:05.405599 54715 net.cpp:150] Setting up bn_conv2_1x7
I0605 23:00:05.405607 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.405612 54715 net.cpp:165] Memory required for data: 367820800
I0605 23:00:05.405620 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x7
I0605 23:00:05.405628 54715 net.cpp:106] Creating Layer scale_conv2_1x7
I0605 23:00:05.405632 54715 net.cpp:454] scale_conv2_1x7 <- conv2_1x7
I0605 23:00:05.405639 54715 net.cpp:397] scale_conv2_1x7 -> conv2_1x7 (in-place)
I0605 23:00:05.405689 54715 layer_factory.hpp:77] Creating layer scale_conv2_1x7
I0605 23:00:05.405854 54715 net.cpp:150] Setting up scale_conv2_1x7
I0605 23:00:05.405864 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.405869 54715 net.cpp:165] Memory required for data: 380928000
I0605 23:00:05.405875 54715 layer_factory.hpp:77] Creating layer relu2_1x7
I0605 23:00:05.405882 54715 net.cpp:106] Creating Layer relu2_1x7
I0605 23:00:05.405886 54715 net.cpp:454] relu2_1x7 <- conv2_1x7
I0605 23:00:05.405894 54715 net.cpp:397] relu2_1x7 -> conv2_1x7 (in-place)
I0605 23:00:05.405900 54715 net.cpp:150] Setting up relu2_1x7
I0605 23:00:05.405905 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.405910 54715 net.cpp:165] Memory required for data: 394035200
I0605 23:00:05.405913 54715 layer_factory.hpp:77] Creating layer conv2_7x1
I0605 23:00:05.405921 54715 net.cpp:106] Creating Layer conv2_7x1
I0605 23:00:05.405925 54715 net.cpp:454] conv2_7x1 <- conv2_1x7
I0605 23:00:05.405933 54715 net.cpp:411] conv2_7x1 -> conv2_7x1
I0605 23:00:05.406380 54715 net.cpp:150] Setting up conv2_7x1
I0605 23:00:05.406389 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.406394 54715 net.cpp:165] Memory required for data: 407142400
I0605 23:00:05.406399 54715 layer_factory.hpp:77] Creating layer bn_conv2_7x1
I0605 23:00:05.406407 54715 net.cpp:106] Creating Layer bn_conv2_7x1
I0605 23:00:05.406412 54715 net.cpp:454] bn_conv2_7x1 <- conv2_7x1
I0605 23:00:05.406419 54715 net.cpp:397] bn_conv2_7x1 -> conv2_7x1 (in-place)
I0605 23:00:05.406661 54715 net.cpp:150] Setting up bn_conv2_7x1
I0605 23:00:05.406668 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.406672 54715 net.cpp:165] Memory required for data: 420249600
I0605 23:00:05.406680 54715 layer_factory.hpp:77] Creating layer scale_conv2_7x1
I0605 23:00:05.406687 54715 net.cpp:106] Creating Layer scale_conv2_7x1
I0605 23:00:05.406692 54715 net.cpp:454] scale_conv2_7x1 <- conv2_7x1
I0605 23:00:05.406698 54715 net.cpp:397] scale_conv2_7x1 -> conv2_7x1 (in-place)
I0605 23:00:05.406745 54715 layer_factory.hpp:77] Creating layer scale_conv2_7x1
I0605 23:00:05.406905 54715 net.cpp:150] Setting up scale_conv2_7x1
I0605 23:00:05.406915 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.406919 54715 net.cpp:165] Memory required for data: 433356800
I0605 23:00:05.406925 54715 layer_factory.hpp:77] Creating layer relu2_7x1
I0605 23:00:05.406932 54715 net.cpp:106] Creating Layer relu2_7x1
I0605 23:00:05.406937 54715 net.cpp:454] relu2_7x1 <- conv2_7x1
I0605 23:00:05.406944 54715 net.cpp:397] relu2_7x1 -> conv2_7x1 (in-place)
I0605 23:00:05.406950 54715 net.cpp:150] Setting up relu2_7x1
I0605 23:00:05.406955 54715 net.cpp:157] Top shape: 2 64 160 160 (3276800)
I0605 23:00:05.406960 54715 net.cpp:165] Memory required for data: 446464000
I0605 23:00:05.406965 54715 layer_factory.hpp:77] Creating layer conv2_3x3
I0605 23:00:05.406975 54715 net.cpp:106] Creating Layer conv2_3x3
I0605 23:00:05.406980 54715 net.cpp:454] conv2_3x3 <- conv2_7x1
I0605 23:00:05.406987 54715 net.cpp:411] conv2_3x3 -> conv2_3x3
I0605 23:00:05.409085 54715 net.cpp:150] Setting up conv2_3x3
I0605 23:00:05.409103 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.409113 54715 net.cpp:165] Memory required for data: 466124800
I0605 23:00:05.409128 54715 layer_factory.hpp:77] Creating layer bn_conv2_3x3
I0605 23:00:05.409137 54715 net.cpp:106] Creating Layer bn_conv2_3x3
I0605 23:00:05.409142 54715 net.cpp:454] bn_conv2_3x3 <- conv2_3x3
I0605 23:00:05.409149 54715 net.cpp:397] bn_conv2_3x3 -> conv2_3x3 (in-place)
I0605 23:00:05.409405 54715 net.cpp:150] Setting up bn_conv2_3x3
I0605 23:00:05.409415 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.409418 54715 net.cpp:165] Memory required for data: 485785600
I0605 23:00:05.409425 54715 layer_factory.hpp:77] Creating layer scale_conv2_3x3
I0605 23:00:05.409433 54715 net.cpp:106] Creating Layer scale_conv2_3x3
I0605 23:00:05.409437 54715 net.cpp:454] scale_conv2_3x3 <- conv2_3x3
I0605 23:00:05.409443 54715 net.cpp:397] scale_conv2_3x3 -> conv2_3x3 (in-place)
I0605 23:00:05.409495 54715 layer_factory.hpp:77] Creating layer scale_conv2_3x3
I0605 23:00:05.409663 54715 net.cpp:150] Setting up scale_conv2_3x3
I0605 23:00:05.409672 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.409677 54715 net.cpp:165] Memory required for data: 505446400
I0605 23:00:05.409682 54715 layer_factory.hpp:77] Creating layer relu2_3x3
I0605 23:00:05.409690 54715 net.cpp:106] Creating Layer relu2_3x3
I0605 23:00:05.409694 54715 net.cpp:454] relu2_3x3 <- conv2_3x3
I0605 23:00:05.409701 54715 net.cpp:397] relu2_3x3 -> conv2_3x3 (in-place)
I0605 23:00:05.409708 54715 net.cpp:150] Setting up relu2_3x3
I0605 23:00:05.409713 54715 net.cpp:157] Top shape: 2 96 160 160 (4915200)
I0605 23:00:05.409716 54715 net.cpp:165] Memory required for data: 525107200
I0605 23:00:05.409720 54715 layer_factory.hpp:77] Creating layer concat_stem_1
I0605 23:00:05.409726 54715 net.cpp:106] Creating Layer concat_stem_1
I0605 23:00:05.409731 54715 net.cpp:454] concat_stem_1 <- conv2_1b_3x3
I0605 23:00:05.409736 54715 net.cpp:454] concat_stem_1 <- conv2_3x3
I0605 23:00:05.409741 54715 net.cpp:411] concat_stem_1 -> concat_stem_1
I0605 23:00:05.409773 54715 net.cpp:150] Setting up concat_stem_1
I0605 23:00:05.409781 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.409785 54715 net.cpp:165] Memory required for data: 564428800
I0605 23:00:05.409790 54715 layer_factory.hpp:77] Creating layer concat_stem_1_concat_stem_1_0_split
I0605 23:00:05.409797 54715 net.cpp:106] Creating Layer concat_stem_1_concat_stem_1_0_split
I0605 23:00:05.409802 54715 net.cpp:454] concat_stem_1_concat_stem_1_0_split <- concat_stem_1
I0605 23:00:05.409809 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_0
I0605 23:00:05.409817 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_1
I0605 23:00:05.409828 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_2
I0605 23:00:05.409837 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_3
I0605 23:00:05.409844 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_4
I0605 23:00:05.409852 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_5
I0605 23:00:05.409858 54715 net.cpp:411] concat_stem_1_concat_stem_1_0_split -> concat_stem_1_concat_stem_1_0_split_6
I0605 23:00:05.409973 54715 net.cpp:150] Setting up concat_stem_1_concat_stem_1_0_split
I0605 23:00:05.409981 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.409986 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.409991 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.409996 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.410001 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.410006 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.410009 54715 net.cpp:157] Top shape: 2 192 160 160 (9830400)
I0605 23:00:05.410014 54715 net.cpp:165] Memory required for data: 839680000
I0605 23:00:05.410018 54715 layer_factory.hpp:77] Creating layer stem_concat_conv_3x3
I0605 23:00:05.410037 54715 net.cpp:106] Creating Layer stem_concat_conv_3x3
I0605 23:00:05.410043 54715 net.cpp:454] stem_concat_conv_3x3 <- concat_stem_1_concat_stem_1_0_split_0
I0605 23:00:05.410053 54715 net.cpp:411] stem_concat_conv_3x3 -> stem_concat_conv_3x3
I0605 23:00:05.412173 54715 net.cpp:150] Setting up stem_concat_conv_3x3
I0605 23:00:05.412184 54715 net.cpp:157] Top shape: 2 192 80 80 (2457600)
I0605 23:00:05.412189 54715 net.cpp:165] Memory required for data: 849510400
I0605 23:00:05.412197 54715 layer_factory.hpp:77] Creating layer bn_stem_concat_conv_3x3
I0605 23:00:05.412205 54715 net.cpp:106] Creating Layer bn_stem_concat_conv_3x3
I0605 23:00:05.412209 54715 net.cpp:454] bn_stem_concat_conv_3x3 <- stem_concat_conv_3x3
I0605 23:00:05.412216 54715 net.cpp:397] bn_stem_concat_conv_3x3 -> stem_concat_conv_3x3 (in-place)
I0605 23:00:05.412453 54715 net.cpp:150] Setting up bn_stem_concat_conv_3x3
I0605 23:00:05.412461 54715 net.cpp:157] Top shape: 2 192 80 80 (2457600)
I0605 23:00:05.412466 54715 net.cpp:165] Memory required for data: 859340800
I0605 23:00:05.412473 54715 layer_factory.hpp:77] Creating layer scale_stem_concat_conv_3x3
I0605 23:00:05.412482 54715 net.cpp:106] Creating Layer scale_stem_concat_conv_3x3
I0605 23:00:05.412487 54715 net.cpp:454] scale_stem_concat_conv_3x3 <- stem_concat_conv_3x3
I0605 23:00:05.412492 54715 net.cpp:397] scale_stem_concat_conv_3x3 -> stem_concat_conv_3x3 (in-place)
I0605 23:00:05.412540 54715 layer_factory.hpp:77] Creating layer scale_stem_concat_conv_3x3
I0605 23:00:05.412686 54715 net.cpp:150] Setting up scale_stem_concat_conv_3x3
I0605 23:00:05.412695 54715 net.cpp:157] Top shape: 2 192 80 80 (2457600)
I0605 23:00:05.412699 54715 net.cpp:165] Memory required for data: 869171200
I0605 23:00:05.412705 54715 layer_factory.hpp:77] Creating layer relu_stem_concat_conv_3x3
I0605 23:00:05.412714 54715 net.cpp:106] Creating Layer relu_stem_concat_conv_3x3
I0605 23:00:05.412719 54715 net.cpp:454] relu_stem_concat_conv_3x3 <- stem_concat_conv_3x3
I0605 23:00:05.412725 54715 net.cpp:397] relu_stem_concat_conv_3x3 -> stem_concat_conv_3x3 (in-place)
I0605 23:00:05.412731 54715 net.cpp:150] Setting up relu_stem_concat_conv_3x3
I0605 23:00:05.412737 54715 net.cpp:157] Top shape: 2 192 80 80 (2457600)
I0605 23:00:05.412741 54715 net.cpp:165] Memory required for data: 879001600
I0605 23:00:05.412745 54715 layer_factory.hpp:77] Creating layer pool_stem_concat
I0605 23:00:05.412753 54715 net.cpp:106] Creating Layer pool_stem_concat
I0605 23:00:05.412758 54715 net.cpp:454] pool_stem_concat <- concat_stem_1_concat_stem_1_0_split_1
I0605 23:00:05.412765 54715 net.cpp:411] pool_stem_concat -> pool_stem_concat
I0605 23:00:05.412816 54715 net.cpp:150] Setting up pool_stem_concat
I0605 23:00:05.412823 54715 net.cpp:157] Top shape: 2 192 80 80 (2457600)
I0605 23:00:05.412828 54715 net.cpp:165] Memory required for data: 888832000
I0605 23:00:05.412832 54715 layer_factory.hpp:77] Creating layer concat_stem_2
I0605 23:00:05.412838 54715 net.cpp:106] Creating Layer concat_stem_2
I0605 23:00:05.412843 54715 net.cpp:454] concat_stem_2 <- pool_stem_concat
I0605 23:00:05.412849 54715 net.cpp:454] concat_stem_2 <- stem_concat_conv_3x3
I0605 23:00:05.412855 54715 net.cpp:411] concat_stem_2 -> concat_stem_2
I0605 23:00:05.412884 54715 net.cpp:150] Setting up concat_stem_2
I0605 23:00:05.412891 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.412896 54715 net.cpp:165] Memory required for data: 908492800
I0605 23:00:05.412900 54715 layer_factory.hpp:77] Creating layer conv3_1b
I0605 23:00:05.412909 54715 net.cpp:106] Creating Layer conv3_1b
I0605 23:00:05.412914 54715 net.cpp:454] conv3_1b <- concat_stem_2
I0605 23:00:05.412921 54715 net.cpp:411] conv3_1b -> conv3_1b
I0605 23:00:05.415586 54715 net.cpp:150] Setting up conv3_1b
I0605 23:00:05.415603 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.415607 54715 net.cpp:165] Memory required for data: 928153600
I0605 23:00:05.415623 54715 layer_factory.hpp:77] Creating layer bn_conv3_1b
I0605 23:00:05.415638 54715 net.cpp:106] Creating Layer bn_conv3_1b
I0605 23:00:05.415650 54715 net.cpp:454] bn_conv3_1b <- conv3_1b
I0605 23:00:05.415657 54715 net.cpp:397] bn_conv3_1b -> conv3_1b (in-place)
I0605 23:00:05.415890 54715 net.cpp:150] Setting up bn_conv3_1b
I0605 23:00:05.415899 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.415902 54715 net.cpp:165] Memory required for data: 947814400
I0605 23:00:05.415910 54715 layer_factory.hpp:77] Creating layer scale_conv3_1b
I0605 23:00:05.415920 54715 net.cpp:106] Creating Layer scale_conv3_1b
I0605 23:00:05.415923 54715 net.cpp:454] scale_conv3_1b <- conv3_1b
I0605 23:00:05.415930 54715 net.cpp:397] scale_conv3_1b -> conv3_1b (in-place)
I0605 23:00:05.415974 54715 layer_factory.hpp:77] Creating layer scale_conv3_1b
I0605 23:00:05.416116 54715 net.cpp:150] Setting up scale_conv3_1b
I0605 23:00:05.416126 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.416129 54715 net.cpp:165] Memory required for data: 967475200
I0605 23:00:05.416136 54715 layer_factory.hpp:77] Creating layer relu3_1b
I0605 23:00:05.416162 54715 net.cpp:106] Creating Layer relu3_1b
I0605 23:00:05.416167 54715 net.cpp:454] relu3_1b <- conv3_1b
I0605 23:00:05.416175 54715 net.cpp:397] relu3_1b -> conv3_1b (in-place)
I0605 23:00:05.416182 54715 net.cpp:150] Setting up relu3_1b
I0605 23:00:05.416188 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.416193 54715 net.cpp:165] Memory required for data: 987136000
I0605 23:00:05.416196 54715 layer_factory.hpp:77] Creating layer conv3_1b_relu3_1b_0_split
I0605 23:00:05.416203 54715 net.cpp:106] Creating Layer conv3_1b_relu3_1b_0_split
I0605 23:00:05.416208 54715 net.cpp:454] conv3_1b_relu3_1b_0_split <- conv3_1b
I0605 23:00:05.416215 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_0
I0605 23:00:05.416224 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_1
I0605 23:00:05.416231 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_2
I0605 23:00:05.416239 54715 net.cpp:411] conv3_1b_relu3_1b_0_split -> conv3_1b_relu3_1b_0_split_3
I0605 23:00:05.416316 54715 net.cpp:150] Setting up conv3_1b_relu3_1b_0_split
I0605 23:00:05.416323 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.416328 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.416334 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.416338 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.416342 54715 net.cpp:165] Memory required for data: 1065779200
I0605 23:00:05.416347 54715 layer_factory.hpp:77] Creating layer ira_A_1_conv1x1
I0605 23:00:05.416355 54715 net.cpp:106] Creating Layer ira_A_1_conv1x1
I0605 23:00:05.416360 54715 net.cpp:454] ira_A_1_conv1x1 <- conv3_1b_relu3_1b_0_split_0
I0605 23:00:05.416368 54715 net.cpp:411] ira_A_1_conv1x1 -> ira_A_1_conv1x1
I0605 23:00:05.416730 54715 net.cpp:150] Setting up ira_A_1_conv1x1
I0605 23:00:05.416740 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.416744 54715 net.cpp:165] Memory required for data: 1067417600
I0605 23:00:05.416752 54715 layer_factory.hpp:77] Creating layer bn_ira_A_1_conv1x1
I0605 23:00:05.416760 54715 net.cpp:106] Creating Layer bn_ira_A_1_conv1x1
I0605 23:00:05.416765 54715 net.cpp:454] bn_ira_A_1_conv1x1 <- ira_A_1_conv1x1
I0605 23:00:05.416772 54715 net.cpp:397] bn_ira_A_1_conv1x1 -> ira_A_1_conv1x1 (in-place)
I0605 23:00:05.417003 54715 net.cpp:150] Setting up bn_ira_A_1_conv1x1
I0605 23:00:05.417011 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.417016 54715 net.cpp:165] Memory required for data: 1069056000
I0605 23:00:05.417023 54715 layer_factory.hpp:77] Creating layer scale_ira_A_1_conv1x1
I0605 23:00:05.417032 54715 net.cpp:106] Creating Layer scale_ira_A_1_conv1x1
I0605 23:00:05.417035 54715 net.cpp:454] scale_ira_A_1_conv1x1 <- ira_A_1_conv1x1
I0605 23:00:05.417042 54715 net.cpp:397] scale_ira_A_1_conv1x1 -> ira_A_1_conv1x1 (in-place)
I0605 23:00:05.417090 54715 layer_factory.hpp:77] Creating layer scale_ira_A_1_conv1x1
I0605 23:00:05.417243 54715 net.cpp:150] Setting up scale_ira_A_1_conv1x1
I0605 23:00:05.417258 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.417263 54715 net.cpp:165] Memory required for data: 1070694400
I0605 23:00:05.417270 54715 layer_factory.hpp:77] Creating layer relu_ira_A_1_conv1x1
I0605 23:00:05.417277 54715 net.cpp:106] Creating Layer relu_ira_A_1_conv1x1
I0605 23:00:05.417281 54715 net.cpp:454] relu_ira_A_1_conv1x1 <- ira_A_1_conv1x1
I0605 23:00:05.417289 54715 net.cpp:397] relu_ira_A_1_conv1x1 -> ira_A_1_conv1x1 (in-place)
I0605 23:00:05.417295 54715 net.cpp:150] Setting up relu_ira_A_1_conv1x1
I0605 23:00:05.417300 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.417304 54715 net.cpp:165] Memory required for data: 1072332800
I0605 23:00:05.417309 54715 layer_factory.hpp:77] Creating layer ira_A_2_conv1x1
I0605 23:00:05.417317 54715 net.cpp:106] Creating Layer ira_A_2_conv1x1
I0605 23:00:05.417321 54715 net.cpp:454] ira_A_2_conv1x1 <- conv3_1b_relu3_1b_0_split_1
I0605 23:00:05.417330 54715 net.cpp:411] ira_A_2_conv1x1 -> ira_A_2_conv1x1
I0605 23:00:05.417688 54715 net.cpp:150] Setting up ira_A_2_conv1x1
I0605 23:00:05.417696 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.417701 54715 net.cpp:165] Memory required for data: 1073971200
I0605 23:00:05.417706 54715 layer_factory.hpp:77] Creating layer bn_ira_A_2_conv1x1
I0605 23:00:05.417714 54715 net.cpp:106] Creating Layer bn_ira_A_2_conv1x1
I0605 23:00:05.417718 54715 net.cpp:454] bn_ira_A_2_conv1x1 <- ira_A_2_conv1x1
I0605 23:00:05.417726 54715 net.cpp:397] bn_ira_A_2_conv1x1 -> ira_A_2_conv1x1 (in-place)
I0605 23:00:05.417954 54715 net.cpp:150] Setting up bn_ira_A_2_conv1x1
I0605 23:00:05.417963 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.417966 54715 net.cpp:165] Memory required for data: 1075609600
I0605 23:00:05.417974 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv1x1
I0605 23:00:05.417980 54715 net.cpp:106] Creating Layer scale_ira_A_2_conv1x1
I0605 23:00:05.417986 54715 net.cpp:454] scale_ira_A_2_conv1x1 <- ira_A_2_conv1x1
I0605 23:00:05.417992 54715 net.cpp:397] scale_ira_A_2_conv1x1 -> ira_A_2_conv1x1 (in-place)
I0605 23:00:05.418038 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv1x1
I0605 23:00:05.418184 54715 net.cpp:150] Setting up scale_ira_A_2_conv1x1
I0605 23:00:05.418192 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.418196 54715 net.cpp:165] Memory required for data: 1077248000
I0605 23:00:05.418202 54715 layer_factory.hpp:77] Creating layer relu_ira_A_2_conv1x1
I0605 23:00:05.418210 54715 net.cpp:106] Creating Layer relu_ira_A_2_conv1x1
I0605 23:00:05.418215 54715 net.cpp:454] relu_ira_A_2_conv1x1 <- ira_A_2_conv1x1
I0605 23:00:05.418220 54715 net.cpp:397] relu_ira_A_2_conv1x1 -> ira_A_2_conv1x1 (in-place)
I0605 23:00:05.418226 54715 net.cpp:150] Setting up relu_ira_A_2_conv1x1
I0605 23:00:05.418232 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.418236 54715 net.cpp:165] Memory required for data: 1078886400
I0605 23:00:05.418241 54715 layer_factory.hpp:77] Creating layer ira_A_2_conv3x3
I0605 23:00:05.418248 54715 net.cpp:106] Creating Layer ira_A_2_conv3x3
I0605 23:00:05.418253 54715 net.cpp:454] ira_A_2_conv3x3 <- ira_A_2_conv1x1
I0605 23:00:05.418260 54715 net.cpp:411] ira_A_2_conv3x3 -> ira_A_2_conv3x3
I0605 23:00:05.418601 54715 net.cpp:150] Setting up ira_A_2_conv3x3
I0605 23:00:05.418611 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.418614 54715 net.cpp:165] Memory required for data: 1080524800
I0605 23:00:05.418622 54715 layer_factory.hpp:77] Creating layer bn_ira_A_2_conv3x3
I0605 23:00:05.418628 54715 net.cpp:106] Creating Layer bn_ira_A_2_conv3x3
I0605 23:00:05.418633 54715 net.cpp:454] bn_ira_A_2_conv3x3 <- ira_A_2_conv3x3
I0605 23:00:05.418640 54715 net.cpp:397] bn_ira_A_2_conv3x3 -> ira_A_2_conv3x3 (in-place)
I0605 23:00:05.418874 54715 net.cpp:150] Setting up bn_ira_A_2_conv3x3
I0605 23:00:05.418881 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.418889 54715 net.cpp:165] Memory required for data: 1082163200
I0605 23:00:05.418903 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv3x3
I0605 23:00:05.418911 54715 net.cpp:106] Creating Layer scale_ira_A_2_conv3x3
I0605 23:00:05.418916 54715 net.cpp:454] scale_ira_A_2_conv3x3 <- ira_A_2_conv3x3
I0605 23:00:05.418922 54715 net.cpp:397] scale_ira_A_2_conv3x3 -> ira_A_2_conv3x3 (in-place)
I0605 23:00:05.418970 54715 layer_factory.hpp:77] Creating layer scale_ira_A_2_conv3x3
I0605 23:00:05.420641 54715 net.cpp:150] Setting up scale_ira_A_2_conv3x3
I0605 23:00:05.420660 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.420663 54715 net.cpp:165] Memory required for data: 1083801600
I0605 23:00:05.420671 54715 layer_factory.hpp:77] Creating layer relu_ira_A_2_conv3x3
I0605 23:00:05.420680 54715 net.cpp:106] Creating Layer relu_ira_A_2_conv3x3
I0605 23:00:05.420686 54715 net.cpp:454] relu_ira_A_2_conv3x3 <- ira_A_2_conv3x3
I0605 23:00:05.420692 54715 net.cpp:397] relu_ira_A_2_conv3x3 -> ira_A_2_conv3x3 (in-place)
I0605 23:00:05.420699 54715 net.cpp:150] Setting up relu_ira_A_2_conv3x3
I0605 23:00:05.420706 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.420709 54715 net.cpp:165] Memory required for data: 1085440000
I0605 23:00:05.420713 54715 layer_factory.hpp:77] Creating layer ira_A_3_conv1x1
I0605 23:00:05.420722 54715 net.cpp:106] Creating Layer ira_A_3_conv1x1
I0605 23:00:05.420728 54715 net.cpp:454] ira_A_3_conv1x1 <- conv3_1b_relu3_1b_0_split_2
I0605 23:00:05.420737 54715 net.cpp:411] ira_A_3_conv1x1 -> ira_A_3_conv1x1
I0605 23:00:05.421092 54715 net.cpp:150] Setting up ira_A_3_conv1x1
I0605 23:00:05.421100 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.421105 54715 net.cpp:165] Memory required for data: 1087078400
I0605 23:00:05.421113 54715 layer_factory.hpp:77] Creating layer bn_ira_A_3_conv1x1
I0605 23:00:05.421120 54715 net.cpp:106] Creating Layer bn_ira_A_3_conv1x1
I0605 23:00:05.421124 54715 net.cpp:454] bn_ira_A_3_conv1x1 <- ira_A_3_conv1x1
I0605 23:00:05.421133 54715 net.cpp:397] bn_ira_A_3_conv1x1 -> ira_A_3_conv1x1 (in-place)
I0605 23:00:05.421358 54715 net.cpp:150] Setting up bn_ira_A_3_conv1x1
I0605 23:00:05.421366 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.421370 54715 net.cpp:165] Memory required for data: 1088716800
I0605 23:00:05.421378 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv1x1
I0605 23:00:05.421386 54715 net.cpp:106] Creating Layer scale_ira_A_3_conv1x1
I0605 23:00:05.421391 54715 net.cpp:454] scale_ira_A_3_conv1x1 <- ira_A_3_conv1x1
I0605 23:00:05.421396 54715 net.cpp:397] scale_ira_A_3_conv1x1 -> ira_A_3_conv1x1 (in-place)
I0605 23:00:05.421447 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv1x1
I0605 23:00:05.421582 54715 net.cpp:150] Setting up scale_ira_A_3_conv1x1
I0605 23:00:05.421591 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.421594 54715 net.cpp:165] Memory required for data: 1090355200
I0605 23:00:05.421602 54715 layer_factory.hpp:77] Creating layer relu_ira_A_3_conv1x1
I0605 23:00:05.421617 54715 net.cpp:106] Creating Layer relu_ira_A_3_conv1x1
I0605 23:00:05.421622 54715 net.cpp:454] relu_ira_A_3_conv1x1 <- ira_A_3_conv1x1
I0605 23:00:05.421628 54715 net.cpp:397] relu_ira_A_3_conv1x1 -> ira_A_3_conv1x1 (in-place)
I0605 23:00:05.421635 54715 net.cpp:150] Setting up relu_ira_A_3_conv1x1
I0605 23:00:05.421640 54715 net.cpp:157] Top shape: 2 32 80 80 (409600)
I0605 23:00:05.421643 54715 net.cpp:165] Memory required for data: 1091993600
I0605 23:00:05.421648 54715 layer_factory.hpp:77] Creating layer ira_A_3_conv3x3_1
I0605 23:00:05.421656 54715 net.cpp:106] Creating Layer ira_A_3_conv3x3_1
I0605 23:00:05.421660 54715 net.cpp:454] ira_A_3_conv3x3_1 <- ira_A_3_conv1x1
I0605 23:00:05.421669 54715 net.cpp:411] ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1
I0605 23:00:05.422026 54715 net.cpp:150] Setting up ira_A_3_conv3x3_1
I0605 23:00:05.422035 54715 net.cpp:157] Top shape: 2 48 80 80 (614400)
I0605 23:00:05.422039 54715 net.cpp:165] Memory required for data: 1094451200
I0605 23:00:05.422052 54715 layer_factory.hpp:77] Creating layer bn_ira_A_3_conv3x3_1
I0605 23:00:05.422066 54715 net.cpp:106] Creating Layer bn_ira_A_3_conv3x3_1
I0605 23:00:05.422072 54715 net.cpp:454] bn_ira_A_3_conv3x3_1 <- ira_A_3_conv3x3_1
I0605 23:00:05.422080 54715 net.cpp:397] bn_ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1 (in-place)
I0605 23:00:05.422304 54715 net.cpp:150] Setting up bn_ira_A_3_conv3x3_1
I0605 23:00:05.422312 54715 net.cpp:157] Top shape: 2 48 80 80 (614400)
I0605 23:00:05.422317 54715 net.cpp:165] Memory required for data: 1096908800
I0605 23:00:05.422324 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_1
I0605 23:00:05.422333 54715 net.cpp:106] Creating Layer scale_ira_A_3_conv3x3_1
I0605 23:00:05.422336 54715 net.cpp:454] scale_ira_A_3_conv3x3_1 <- ira_A_3_conv3x3_1
I0605 23:00:05.422344 54715 net.cpp:397] scale_ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1 (in-place)
I0605 23:00:05.422391 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_1
I0605 23:00:05.422525 54715 net.cpp:150] Setting up scale_ira_A_3_conv3x3_1
I0605 23:00:05.422534 54715 net.cpp:157] Top shape: 2 48 80 80 (614400)
I0605 23:00:05.422538 54715 net.cpp:165] Memory required for data: 1099366400
I0605 23:00:05.422545 54715 layer_factory.hpp:77] Creating layer relu_ira_A_3_conv3x3_1
I0605 23:00:05.422552 54715 net.cpp:106] Creating Layer relu_ira_A_3_conv3x3_1
I0605 23:00:05.422557 54715 net.cpp:454] relu_ira_A_3_conv3x3_1 <- ira_A_3_conv3x3_1
I0605 23:00:05.422564 54715 net.cpp:397] relu_ira_A_3_conv3x3_1 -> ira_A_3_conv3x3_1 (in-place)
I0605 23:00:05.422570 54715 net.cpp:150] Setting up relu_ira_A_3_conv3x3_1
I0605 23:00:05.422576 54715 net.cpp:157] Top shape: 2 48 80 80 (614400)
I0605 23:00:05.422580 54715 net.cpp:165] Memory required for data: 1101824000
I0605 23:00:05.422585 54715 layer_factory.hpp:77] Creating layer ira_A_3_conv3x3_2
I0605 23:00:05.422593 54715 net.cpp:106] Creating Layer ira_A_3_conv3x3_2
I0605 23:00:05.422597 54715 net.cpp:454] ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_1
I0605 23:00:05.422605 54715 net.cpp:411] ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2
I0605 23:00:05.423043 54715 net.cpp:150] Setting up ira_A_3_conv3x3_2
I0605 23:00:05.423053 54715 net.cpp:157] Top shape: 2 64 80 80 (819200)
I0605 23:00:05.423056 54715 net.cpp:165] Memory required for data: 1105100800
I0605 23:00:05.423063 54715 layer_factory.hpp:77] Creating layer bn_ira_A_3_conv3x3_2
I0605 23:00:05.423070 54715 net.cpp:106] Creating Layer bn_ira_A_3_conv3x3_2
I0605 23:00:05.423075 54715 net.cpp:454] bn_ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_2
I0605 23:00:05.423081 54715 net.cpp:397] bn_ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2 (in-place)
I0605 23:00:05.423308 54715 net.cpp:150] Setting up bn_ira_A_3_conv3x3_2
I0605 23:00:05.423316 54715 net.cpp:157] Top shape: 2 64 80 80 (819200)
I0605 23:00:05.423321 54715 net.cpp:165] Memory required for data: 1108377600
I0605 23:00:05.423327 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_2
I0605 23:00:05.423336 54715 net.cpp:106] Creating Layer scale_ira_A_3_conv3x3_2
I0605 23:00:05.423341 54715 net.cpp:454] scale_ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_2
I0605 23:00:05.423346 54715 net.cpp:397] scale_ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2 (in-place)
I0605 23:00:05.423396 54715 layer_factory.hpp:77] Creating layer scale_ira_A_3_conv3x3_2
I0605 23:00:05.423527 54715 net.cpp:150] Setting up scale_ira_A_3_conv3x3_2
I0605 23:00:05.423537 54715 net.cpp:157] Top shape: 2 64 80 80 (819200)
I0605 23:00:05.423542 54715 net.cpp:165] Memory required for data: 1111654400
I0605 23:00:05.423547 54715 layer_factory.hpp:77] Creating layer relu_ira_A_3_conv3x3_2
I0605 23:00:05.423554 54715 net.cpp:106] Creating Layer relu_ira_A_3_conv3x3_2
I0605 23:00:05.423559 54715 net.cpp:454] relu_ira_A_3_conv3x3_2 <- ira_A_3_conv3x3_2
I0605 23:00:05.423565 54715 net.cpp:397] relu_ira_A_3_conv3x3_2 -> ira_A_3_conv3x3_2 (in-place)
I0605 23:00:05.423571 54715 net.cpp:150] Setting up relu_ira_A_3_conv3x3_2
I0605 23:00:05.423576 54715 net.cpp:157] Top shape: 2 64 80 80 (819200)
I0605 23:00:05.423586 54715 net.cpp:165] Memory required for data: 1114931200
I0605 23:00:05.423595 54715 layer_factory.hpp:77] Creating layer ira_A_concat
I0605 23:00:05.423602 54715 net.cpp:106] Creating Layer ira_A_concat
I0605 23:00:05.423607 54715 net.cpp:454] ira_A_concat <- ira_A_1_conv1x1
I0605 23:00:05.423614 54715 net.cpp:454] ira_A_concat <- ira_A_2_conv3x3
I0605 23:00:05.423619 54715 net.cpp:454] ira_A_concat <- ira_A_3_conv3x3_2
I0605 23:00:05.423624 54715 net.cpp:411] ira_A_concat -> ira_A_concat
I0605 23:00:05.423655 54715 net.cpp:150] Setting up ira_A_concat
I0605 23:00:05.423663 54715 net.cpp:157] Top shape: 2 128 80 80 (1638400)
I0605 23:00:05.423666 54715 net.cpp:165] Memory required for data: 1121484800
I0605 23:00:05.423671 54715 layer_factory.hpp:77] Creating layer ira_A_concat_top_conv_1x1
I0605 23:00:05.423681 54715 net.cpp:106] Creating Layer ira_A_concat_top_conv_1x1
I0605 23:00:05.423686 54715 net.cpp:454] ira_A_concat_top_conv_1x1 <- ira_A_concat
I0605 23:00:05.423693 54715 net.cpp:411] ira_A_concat_top_conv_1x1 -> ira_A_concat_top_conv_1x1
I0605 23:00:05.424270 54715 net.cpp:150] Setting up ira_A_concat_top_conv_1x1
I0605 23:00:05.424281 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.424286 54715 net.cpp:165] Memory required for data: 1141145600
I0605 23:00:05.424293 54715 layer_factory.hpp:77] Creating layer bn_ra_A_concat_top_conv_1x1
I0605 23:00:05.424301 54715 net.cpp:106] Creating Layer bn_ra_A_concat_top_conv_1x1
I0605 23:00:05.424306 54715 net.cpp:454] bn_ra_A_concat_top_conv_1x1 <- ira_A_concat_top_conv_1x1
I0605 23:00:05.424314 54715 net.cpp:397] bn_ra_A_concat_top_conv_1x1 -> ira_A_concat_top_conv_1x1 (in-place)
I0605 23:00:05.424535 54715 net.cpp:150] Setting up bn_ra_A_concat_top_conv_1x1
I0605 23:00:05.424542 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.424546 54715 net.cpp:165] Memory required for data: 1160806400
I0605 23:00:05.424554 54715 layer_factory.hpp:77] Creating layer scale_ra_A_concat_top_conv_1x1
I0605 23:00:05.424562 54715 net.cpp:106] Creating Layer scale_ra_A_concat_top_conv_1x1
I0605 23:00:05.424566 54715 net.cpp:454] scale_ra_A_concat_top_conv_1x1 <- ira_A_concat_top_conv_1x1
I0605 23:00:05.424573 54715 net.cpp:397] scale_ra_A_concat_top_conv_1x1 -> ira_A_concat_top_conv_1x1 (in-place)
I0605 23:00:05.424616 54715 layer_factory.hpp:77] Creating layer scale_ra_A_concat_top_conv_1x1
I0605 23:00:05.424746 54715 net.cpp:150] Setting up scale_ra_A_concat_top_conv_1x1
I0605 23:00:05.424754 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.424758 54715 net.cpp:165] Memory required for data: 1180467200
I0605 23:00:05.424767 54715 layer_factory.hpp:77] Creating layer conv3_sum
I0605 23:00:05.424774 54715 net.cpp:106] Creating Layer conv3_sum
I0605 23:00:05.424779 54715 net.cpp:454] conv3_sum <- conv3_1b_relu3_1b_0_split_3
I0605 23:00:05.424784 54715 net.cpp:454] conv3_sum <- ira_A_concat_top_conv_1x1
I0605 23:00:05.424793 54715 net.cpp:411] conv3_sum -> conv3_sum
I0605 23:00:05.424824 54715 net.cpp:150] Setting up conv3_sum
I0605 23:00:05.424831 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.424835 54715 net.cpp:165] Memory required for data: 1200128000
I0605 23:00:05.424840 54715 layer_factory.hpp:77] Creating layer relu3_sum
I0605 23:00:05.424847 54715 net.cpp:106] Creating Layer relu3_sum
I0605 23:00:05.424851 54715 net.cpp:454] relu3_sum <- conv3_sum
I0605 23:00:05.424859 54715 net.cpp:397] relu3_sum -> conv3_sum (in-place)
I0605 23:00:05.424865 54715 net.cpp:150] Setting up relu3_sum
I0605 23:00:05.424870 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.424875 54715 net.cpp:165] Memory required for data: 1219788800
I0605 23:00:05.424878 54715 layer_factory.hpp:77] Creating layer conv3_sum_relu3_sum_0_split
I0605 23:00:05.424886 54715 net.cpp:106] Creating Layer conv3_sum_relu3_sum_0_split
I0605 23:00:05.424890 54715 net.cpp:454] conv3_sum_relu3_sum_0_split <- conv3_sum
I0605 23:00:05.424896 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_0
I0605 23:00:05.424911 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_1
I0605 23:00:05.424927 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_2
I0605 23:00:05.424935 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_3
I0605 23:00:05.424942 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_4
I0605 23:00:05.424950 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_5
I0605 23:00:05.424958 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_6
I0605 23:00:05.424964 54715 net.cpp:411] conv3_sum_relu3_sum_0_split -> conv3_sum_relu3_sum_0_split_7
I0605 23:00:05.425091 54715 net.cpp:150] Setting up conv3_sum_relu3_sum_0_split
I0605 23:00:05.425099 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425104 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425109 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425113 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425118 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425123 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425127 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425132 54715 net.cpp:157] Top shape: 2 384 80 80 (4915200)
I0605 23:00:05.425135 54715 net.cpp:165] Memory required for data: 1377075200
I0605 23:00:05.425140 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/pool
I0605 23:00:05.425148 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/pool
I0605 23:00:05.425153 54715 net.cpp:454] ira_v4_reduction_A/pool <- conv3_sum_relu3_sum_0_split_0
I0605 23:00:05.425160 54715 net.cpp:411] ira_v4_reduction_A/pool -> ira_v4_reduction_A/pool
I0605 23:00:05.425206 54715 net.cpp:150] Setting up ira_v4_reduction_A/pool
I0605 23:00:05.425213 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.425217 54715 net.cpp:165] Memory required for data: 1381990400
I0605 23:00:05.425221 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.425231 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.425235 54715 net.cpp:454] ira_v4_reduction_A/conv3x3_reduction_b <- conv3_sum_relu3_sum_0_split_1
I0605 23:00:05.425243 54715 net.cpp:411] ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435197 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435216 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.435220 54715 net.cpp:165] Memory required for data: 1386905600
I0605 23:00:05.435230 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435238 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435245 54715 net.cpp:454] bn_ira_v4_reduction_A/conv3x3_reduction_b <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435253 54715 net.cpp:397] bn_ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b (in-place)
I0605 23:00:05.435487 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435495 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.435500 54715 net.cpp:165] Memory required for data: 1391820800
I0605 23:00:05.435508 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435518 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435521 54715 net.cpp:454] scale_ira_v4_reduction_A/conv3x3_reduction_b <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435529 54715 net.cpp:397] scale_ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b (in-place)
I0605 23:00:05.435575 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435717 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435732 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.435744 54715 net.cpp:165] Memory required for data: 1396736000
I0605 23:00:05.435750 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435758 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435762 54715 net.cpp:454] relu_ira_v4_reduction_A/conv3x3_reduction_b <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435770 54715 net.cpp:397] relu_ira_v4_reduction_A/conv3x3_reduction_b -> ira_v4_reduction_A/conv3x3_reduction_b (in-place)
I0605 23:00:05.435777 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.435783 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.435786 54715 net.cpp:165] Memory required for data: 1401651200
I0605 23:00:05.435791 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.435801 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.435806 54715 net.cpp:454] ira_v4_reduction_A/conv1x1_c <- conv3_sum_relu3_sum_0_split_2
I0605 23:00:05.435813 54715 net.cpp:411] ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436681 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436692 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.436697 54715 net.cpp:165] Memory required for data: 1414758400
I0605 23:00:05.436703 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436712 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436717 54715 net.cpp:454] bn_ira_v4_reduction_A/conv1x1_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436724 54715 net.cpp:397] bn_ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c (in-place)
I0605 23:00:05.436944 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436952 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.436956 54715 net.cpp:165] Memory required for data: 1427865600
I0605 23:00:05.436977 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436987 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.436993 54715 net.cpp:454] scale_ira_v4_reduction_A/conv1x1_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437001 54715 net.cpp:397] scale_ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c (in-place)
I0605 23:00:05.437052 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437182 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437192 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.437196 54715 net.cpp:165] Memory required for data: 1440972800
I0605 23:00:05.437204 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437211 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437217 54715 net.cpp:454] relu_ira_v4_reduction_A/conv1x1_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437223 54715 net.cpp:397] relu_ira_v4_reduction_A/conv1x1_c -> ira_v4_reduction_A/conv1x1_c (in-place)
I0605 23:00:05.437229 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437235 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.437239 54715 net.cpp:165] Memory required for data: 1454080000
I0605 23:00:05.437243 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.437252 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.437258 54715 net.cpp:454] ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv1x1_c
I0605 23:00:05.437266 54715 net.cpp:411] ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442258 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442276 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.442286 54715 net.cpp:165] Memory required for data: 1467187200
I0605 23:00:05.442301 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442311 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442315 54715 net.cpp:454] bn_ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442322 54715 net.cpp:397] bn_ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c (in-place)
I0605 23:00:05.442553 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442561 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.442564 54715 net.cpp:165] Memory required for data: 1480294400
I0605 23:00:05.442572 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442581 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442586 54715 net.cpp:454] scale_ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442593 54715 net.cpp:397] scale_ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c (in-place)
I0605 23:00:05.442642 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442775 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442783 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.442787 54715 net.cpp:165] Memory required for data: 1493401600
I0605 23:00:05.442793 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442801 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442806 54715 net.cpp:454] relu_ira_v4_reduction_A/conv3x3_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442813 54715 net.cpp:397] relu_ira_v4_reduction_A/conv3x3_c -> ira_v4_reduction_A/conv3x3_c (in-place)
I0605 23:00:05.442819 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442826 54715 net.cpp:157] Top shape: 2 256 80 80 (3276800)
I0605 23:00:05.442829 54715 net.cpp:165] Memory required for data: 1506508800
I0605 23:00:05.442833 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.442842 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.442847 54715 net.cpp:454] ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_c
I0605 23:00:05.442854 54715 net.cpp:411] ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.449767 54715 net.cpp:150] Setting up ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.449784 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.449790 54715 net.cpp:165] Memory required for data: 1511424000
I0605 23:00:05.449798 54715 layer_factory.hpp:77] Creating layer bn_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.449807 54715 net.cpp:106] Creating Layer bn_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.449812 54715 net.cpp:454] bn_ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.449822 54715 net.cpp:397] bn_ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c (in-place)
I0605 23:00:05.450057 54715 net.cpp:150] Setting up bn_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450064 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.450068 54715 net.cpp:165] Memory required for data: 1516339200
I0605 23:00:05.450078 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450085 54715 net.cpp:106] Creating Layer scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450090 54715 net.cpp:454] scale_ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450098 54715 net.cpp:397] scale_ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c (in-place)
I0605 23:00:05.450143 54715 layer_factory.hpp:77] Creating layer scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450296 54715 net.cpp:150] Setting up scale_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450312 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.450317 54715 net.cpp:165] Memory required for data: 1521254400
I0605 23:00:05.450325 54715 layer_factory.hpp:77] Creating layer relu_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450332 54715 net.cpp:106] Creating Layer relu_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450337 54715 net.cpp:454] relu_ira_v4_reduction_A/conv3x3_reduction_c <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450345 54715 net.cpp:397] relu_ira_v4_reduction_A/conv3x3_reduction_c -> ira_v4_reduction_A/conv3x3_reduction_c (in-place)
I0605 23:00:05.450352 54715 net.cpp:150] Setting up relu_ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450358 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.450362 54715 net.cpp:165] Memory required for data: 1526169600
I0605 23:00:05.450366 54715 layer_factory.hpp:77] Creating layer ira_v4_reduction_A/concat
I0605 23:00:05.450373 54715 net.cpp:106] Creating Layer ira_v4_reduction_A/concat
I0605 23:00:05.450378 54715 net.cpp:454] ira_v4_reduction_A/concat <- ira_v4_reduction_A/pool
I0605 23:00:05.450383 54715 net.cpp:454] ira_v4_reduction_A/concat <- ira_v4_reduction_A/conv3x3_reduction_b
I0605 23:00:05.450388 54715 net.cpp:454] ira_v4_reduction_A/concat <- ira_v4_reduction_A/conv3x3_reduction_c
I0605 23:00:05.450397 54715 net.cpp:411] ira_v4_reduction_A/concat -> ira_v4_reduction_A/concat
I0605 23:00:05.450429 54715 net.cpp:150] Setting up ira_v4_reduction_A/concat
I0605 23:00:05.450436 54715 net.cpp:157] Top shape: 2 1152 40 40 (3686400)
I0605 23:00:05.450439 54715 net.cpp:165] Memory required for data: 1540915200
I0605 23:00:05.450444 54715 layer_factory.hpp:77] Creating layer conv4_1b
I0605 23:00:05.450454 54715 net.cpp:106] Creating Layer conv4_1b
I0605 23:00:05.450459 54715 net.cpp:454] conv4_1b <- ira_v4_reduction_A/concat
I0605 23:00:05.450467 54715 net.cpp:411] conv4_1b -> conv4_1b
I0605 23:00:05.460479 54715 net.cpp:150] Setting up conv4_1b
I0605 23:00:05.460497 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.460502 54715 net.cpp:165] Memory required for data: 1555686400
I0605 23:00:05.460510 54715 layer_factory.hpp:77] Creating layer bn_conv4_1b
I0605 23:00:05.460520 54715 net.cpp:106] Creating Layer bn_conv4_1b
I0605 23:00:05.460525 54715 net.cpp:454] bn_conv4_1b <- conv4_1b
I0605 23:00:05.460532 54715 net.cpp:397] bn_conv4_1b -> conv4_1b (in-place)
I0605 23:00:05.460775 54715 net.cpp:150] Setting up bn_conv4_1b
I0605 23:00:05.460784 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.460788 54715 net.cpp:165] Memory required for data: 1570457600
I0605 23:00:05.460796 54715 layer_factory.hpp:77] Creating layer scale_conv4_1b
I0605 23:00:05.460804 54715 net.cpp:106] Creating Layer scale_conv4_1b
I0605 23:00:05.460810 54715 net.cpp:454] scale_conv4_1b <- conv4_1b
I0605 23:00:05.460816 54715 net.cpp:397] scale_conv4_1b -> conv4_1b (in-place)
I0605 23:00:05.460867 54715 layer_factory.hpp:77] Creating layer scale_conv4_1b
I0605 23:00:05.461017 54715 net.cpp:150] Setting up scale_conv4_1b
I0605 23:00:05.461026 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.461030 54715 net.cpp:165] Memory required for data: 1585228800
I0605 23:00:05.461037 54715 layer_factory.hpp:77] Creating layer relu4_1b
I0605 23:00:05.461045 54715 net.cpp:106] Creating Layer relu4_1b
I0605 23:00:05.461050 54715 net.cpp:454] relu4_1b <- conv4_1b
I0605 23:00:05.461056 54715 net.cpp:397] relu4_1b -> conv4_1b (in-place)
I0605 23:00:05.461062 54715 net.cpp:150] Setting up relu4_1b
I0605 23:00:05.461068 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.461072 54715 net.cpp:165] Memory required for data: 1600000000
I0605 23:00:05.461076 54715 layer_factory.hpp:77] Creating layer conv4_1b_relu4_1b_0_split
I0605 23:00:05.461083 54715 net.cpp:106] Creating Layer conv4_1b_relu4_1b_0_split
I0605 23:00:05.461087 54715 net.cpp:454] conv4_1b_relu4_1b_0_split <- conv4_1b
I0605 23:00:05.461102 54715 net.cpp:411] conv4_1b_relu4_1b_0_split -> conv4_1b_relu4_1b_0_split_0
I0605 23:00:05.461117 54715 net.cpp:411] conv4_1b_relu4_1b_0_split -> conv4_1b_relu4_1b_0_split_1
I0605 23:00:05.461124 54715 net.cpp:411] conv4_1b_relu4_1b_0_split -> conv4_1b_relu4_1b_0_split_2
I0605 23:00:05.461189 54715 net.cpp:150] Setting up conv4_1b_relu4_1b_0_split
I0605 23:00:05.461197 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.461202 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.461206 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.461210 54715 net.cpp:165] Memory required for data: 1644313600
I0605 23:00:05.461215 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.461225 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.461230 54715 net.cpp:454] ira_Inception_B_block_1/a_conv1x1_1 <- conv4_1b_relu4_1b_0_split_0
I0605 23:00:05.461239 54715 net.cpp:411] ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.462838 54715 net.cpp:150] Setting up ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.462847 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.462852 54715 net.cpp:165] Memory required for data: 1646771200
I0605 23:00:05.462858 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.462867 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.462872 54715 net.cpp:454] bn_ira_Inception_B_block_1/a_conv1x1_1 <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.462880 54715 net.cpp:397] bn_ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1 (in-place)
I0605 23:00:05.463119 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463127 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.463131 54715 net.cpp:165] Memory required for data: 1649228800
I0605 23:00:05.463140 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463147 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463152 54715 net.cpp:454] scale_ira_Inception_B_block_1/a_conv1x1_1 <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463158 54715 net.cpp:397] scale_ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1 (in-place)
I0605 23:00:05.463207 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463356 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463366 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.463371 54715 net.cpp:165] Memory required for data: 1651686400
I0605 23:00:05.463377 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463383 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463388 54715 net.cpp:454] relu_ira_Inception_B_block_1/a_conv1x1_1 <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463394 54715 net.cpp:397] relu_ira_Inception_B_block_1/a_conv1x1_1 -> ira_Inception_B_block_1/a_conv1x1_1 (in-place)
I0605 23:00:05.463402 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.463407 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.463412 54715 net.cpp:165] Memory required for data: 1654144000
I0605 23:00:05.463415 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.463423 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.463428 54715 net.cpp:454] ira_Inception_B_block_1/b_conv1x1_1 <- conv4_1b_relu4_1b_0_split_1
I0605 23:00:05.463436 54715 net.cpp:411] ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.465894 54715 net.cpp:150] Setting up ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.465911 54715 net.cpp:157] Top shape: 2 128 40 40 (409600)
I0605 23:00:05.465926 54715 net.cpp:165] Memory required for data: 1655782400
I0605 23:00:05.465936 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.465945 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.465951 54715 net.cpp:454] bn_ira_Inception_B_block_1/b_conv1x1_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.465958 54715 net.cpp:397] bn_ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.466197 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466205 54715 net.cpp:157] Top shape: 2 128 40 40 (409600)
I0605 23:00:05.466209 54715 net.cpp:165] Memory required for data: 1657420800
I0605 23:00:05.466217 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466226 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466231 54715 net.cpp:454] scale_ira_Inception_B_block_1/b_conv1x1_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466238 54715 net.cpp:397] scale_ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.466289 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466428 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466437 54715 net.cpp:157] Top shape: 2 128 40 40 (409600)
I0605 23:00:05.466441 54715 net.cpp:165] Memory required for data: 1659059200
I0605 23:00:05.466449 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466456 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466461 54715 net.cpp:454] relu_ira_Inception_B_block_1/b_conv1x1_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466470 54715 net.cpp:397] relu_ira_Inception_B_block_1/b_conv1x1_1 -> ira_Inception_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.466475 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466482 54715 net.cpp:157] Top shape: 2 128 40 40 (409600)
I0605 23:00:05.466486 54715 net.cpp:165] Memory required for data: 1660697600
I0605 23:00:05.466490 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.466500 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.466504 54715 net.cpp:454] ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x1_1
I0605 23:00:05.466512 54715 net.cpp:411] ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467579 54715 net.cpp:150] Setting up ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467589 54715 net.cpp:157] Top shape: 2 160 40 40 (512000)
I0605 23:00:05.467594 54715 net.cpp:165] Memory required for data: 1662745600
I0605 23:00:05.467602 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467609 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467614 54715 net.cpp:454] bn_ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467622 54715 net.cpp:397] bn_ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1 (in-place)
I0605 23:00:05.467934 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467943 54715 net.cpp:157] Top shape: 2 160 40 40 (512000)
I0605 23:00:05.467947 54715 net.cpp:165] Memory required for data: 1664793600
I0605 23:00:05.467957 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467964 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467969 54715 net.cpp:454] scale_ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.467977 54715 net.cpp:397] scale_ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1 (in-place)
I0605 23:00:05.468443 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468605 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468613 54715 net.cpp:157] Top shape: 2 160 40 40 (512000)
I0605 23:00:05.468617 54715 net.cpp:165] Memory required for data: 1666841600
I0605 23:00:05.468626 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468633 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468638 54715 net.cpp:454] relu_ira_Inception_B_block_1/b_conv1x7_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468646 54715 net.cpp:397] relu_ira_Inception_B_block_1/b_conv1x7_1 -> ira_Inception_B_block_1/b_conv1x7_1 (in-place)
I0605 23:00:05.468653 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468658 54715 net.cpp:157] Top shape: 2 160 40 40 (512000)
I0605 23:00:05.468662 54715 net.cpp:165] Memory required for data: 1668889600
I0605 23:00:05.468667 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.468677 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.468680 54715 net.cpp:454] ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv1x7_1
I0605 23:00:05.468688 54715 net.cpp:411] ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470136 54715 net.cpp:150] Setting up ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470147 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.470151 54715 net.cpp:165] Memory required for data: 1671347200
I0605 23:00:05.470157 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470165 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470171 54715 net.cpp:454] bn_ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470178 54715 net.cpp:397] bn_ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1 (in-place)
I0605 23:00:05.470413 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470422 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.470427 54715 net.cpp:165] Memory required for data: 1673804800
I0605 23:00:05.470434 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470441 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470446 54715 net.cpp:454] scale_ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470454 54715 net.cpp:397] scale_ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1 (in-place)
I0605 23:00:05.470502 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470649 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470656 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.470660 54715 net.cpp:165] Memory required for data: 1676262400
I0605 23:00:05.470667 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470674 54715 net.cpp:106] Creating Layer relu_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470679 54715 net.cpp:454] relu_ira_Inception_B_block_1/b_conv7x1_1 <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470687 54715 net.cpp:397] relu_ira_Inception_B_block_1/b_conv7x1_1 -> ira_Inception_B_block_1/b_conv7x1_1 (in-place)
I0605 23:00:05.470693 54715 net.cpp:150] Setting up relu_ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470698 54715 net.cpp:157] Top shape: 2 192 40 40 (614400)
I0605 23:00:05.470702 54715 net.cpp:165] Memory required for data: 1678720000
I0605 23:00:05.470706 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/concat
I0605 23:00:05.470713 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/concat
I0605 23:00:05.470728 54715 net.cpp:454] ira_Inception_B_block_1/concat <- ira_Inception_B_block_1/a_conv1x1_1
I0605 23:00:05.470733 54715 net.cpp:454] ira_Inception_B_block_1/concat <- ira_Inception_B_block_1/b_conv7x1_1
I0605 23:00:05.470741 54715 net.cpp:411] ira_Inception_B_block_1/concat -> ira_Inception_B_block_1/concat
I0605 23:00:05.470773 54715 net.cpp:150] Setting up ira_Inception_B_block_1/concat
I0605 23:00:05.470780 54715 net.cpp:157] Top shape: 2 384 40 40 (1228800)
I0605 23:00:05.470784 54715 net.cpp:165] Memory required for data: 1683635200
I0605 23:00:05.470789 54715 layer_factory.hpp:77] Creating layer ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.470798 54715 net.cpp:106] Creating Layer ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.470803 54715 net.cpp:454] ira_Inception_B_block_1/top_conv_1x1 <- ira_Inception_B_block_1/concat
I0605 23:00:05.470810 54715 net.cpp:411] ira_Inception_B_block_1/top_conv_1x1 -> ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475208 54715 net.cpp:150] Setting up ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475225 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.475229 54715 net.cpp:165] Memory required for data: 1698406400
I0605 23:00:05.475237 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475247 54715 net.cpp:106] Creating Layer bn_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475252 54715 net.cpp:454] bn_ira_Inception_B_block_1/top_conv_1x1 <- ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475260 54715 net.cpp:397] bn_ira_Inception_B_block_1/top_conv_1x1 -> ira_Inception_B_block_1/top_conv_1x1 (in-place)
I0605 23:00:05.475505 54715 net.cpp:150] Setting up bn_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475514 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.475518 54715 net.cpp:165] Memory required for data: 1713177600
I0605 23:00:05.475527 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475534 54715 net.cpp:106] Creating Layer scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475540 54715 net.cpp:454] scale_ira_Inception_B_block_1/top_conv_1x1 <- ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475546 54715 net.cpp:397] scale_ira_Inception_B_block_1/top_conv_1x1 -> ira_Inception_B_block_1/top_conv_1x1 (in-place)
I0605 23:00:05.475598 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475750 54715 net.cpp:150] Setting up scale_ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475760 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.475764 54715 net.cpp:165] Memory required for data: 1727948800
I0605 23:00:05.475770 54715 layer_factory.hpp:77] Creating layer conv4_sum
I0605 23:00:05.475780 54715 net.cpp:106] Creating Layer conv4_sum
I0605 23:00:05.475785 54715 net.cpp:454] conv4_sum <- conv4_1b_relu4_1b_0_split_2
I0605 23:00:05.475791 54715 net.cpp:454] conv4_sum <- ira_Inception_B_block_1/top_conv_1x1
I0605 23:00:05.475798 54715 net.cpp:411] conv4_sum -> conv4_sum
I0605 23:00:05.475831 54715 net.cpp:150] Setting up conv4_sum
I0605 23:00:05.475839 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.475843 54715 net.cpp:165] Memory required for data: 1742720000
I0605 23:00:05.475847 54715 layer_factory.hpp:77] Creating layer relu_conv4_sum
I0605 23:00:05.475853 54715 net.cpp:106] Creating Layer relu_conv4_sum
I0605 23:00:05.475859 54715 net.cpp:454] relu_conv4_sum <- conv4_sum
I0605 23:00:05.475867 54715 net.cpp:397] relu_conv4_sum -> conv4_sum (in-place)
I0605 23:00:05.475872 54715 net.cpp:150] Setting up relu_conv4_sum
I0605 23:00:05.475878 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.475883 54715 net.cpp:165] Memory required for data: 1757491200
I0605 23:00:05.475886 54715 layer_factory.hpp:77] Creating layer conv4_sum_relu_conv4_sum_0_split
I0605 23:00:05.475894 54715 net.cpp:106] Creating Layer conv4_sum_relu_conv4_sum_0_split
I0605 23:00:05.475904 54715 net.cpp:454] conv4_sum_relu_conv4_sum_0_split <- conv4_sum
I0605 23:00:05.475919 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_0
I0605 23:00:05.475944 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_1
I0605 23:00:05.475951 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_2
I0605 23:00:05.475960 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_3
I0605 23:00:05.475967 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_4
I0605 23:00:05.475975 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_5
I0605 23:00:05.475981 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_6
I0605 23:00:05.475988 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_7
I0605 23:00:05.475996 54715 net.cpp:411] conv4_sum_relu_conv4_sum_0_split -> conv4_sum_relu_conv4_sum_0_split_8
I0605 23:00:05.476171 54715 net.cpp:150] Setting up conv4_sum_relu_conv4_sum_0_split
I0605 23:00:05.476181 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476186 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476192 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476197 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476200 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476205 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476210 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476215 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476219 54715 net.cpp:157] Top shape: 2 1154 40 40 (3692800)
I0605 23:00:05.476223 54715 net.cpp:165] Memory required for data: 1890432000
I0605 23:00:05.476228 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/a_pool
I0605 23:00:05.476236 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/a_pool
I0605 23:00:05.476241 54715 net.cpp:454] ira_Reduction_B_block_1/a_pool <- conv4_sum_relu_conv4_sum_0_split_0
I0605 23:00:05.476248 54715 net.cpp:411] ira_Reduction_B_block_1/a_pool -> ira_Reduction_B_block_1/a_pool
I0605 23:00:05.476299 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/a_pool
I0605 23:00:05.476305 54715 net.cpp:157] Top shape: 2 1154 20 20 (923200)
I0605 23:00:05.476310 54715 net.cpp:165] Memory required for data: 1894124800
I0605 23:00:05.476313 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.476323 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.476328 54715 net.cpp:454] ira_Reduction_B_block_1/b_conv1x1_1 <- conv4_sum_relu_conv4_sum_0_split_1
I0605 23:00:05.476336 54715 net.cpp:411] ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479562 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479579 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.479584 54715 net.cpp:165] Memory required for data: 1897401600
I0605 23:00:05.479593 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479625 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479632 54715 net.cpp:454] bn_ira_Reduction_B_block_1/b_conv1x1_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479640 54715 net.cpp:397] bn_ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.479879 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479887 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.479892 54715 net.cpp:165] Memory required for data: 1900678400
I0605 23:00:05.479902 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479908 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479919 54715 net.cpp:454] scale_ira_Reduction_B_block_1/b_conv1x1_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.479933 54715 net.cpp:397] scale_ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.479988 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480131 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480155 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.480162 54715 net.cpp:165] Memory required for data: 1903955200
I0605 23:00:05.480170 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480177 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480182 54715 net.cpp:454] relu_ira_Reduction_B_block_1/b_conv1x1_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480190 54715 net.cpp:397] relu_ira_Reduction_B_block_1/b_conv1x1_1 -> ira_Reduction_B_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.480197 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480202 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.480206 54715 net.cpp:165] Memory required for data: 1907232000
I0605 23:00:05.480211 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.480221 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.480224 54715 net.cpp:454] ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv1x1_1
I0605 23:00:05.480232 54715 net.cpp:411] ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487159 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487176 54715 net.cpp:157] Top shape: 2 384 20 20 (307200)
I0605 23:00:05.487181 54715 net.cpp:165] Memory required for data: 1908460800
I0605 23:00:05.487188 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487198 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487205 54715 net.cpp:454] bn_ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487211 54715 net.cpp:397] bn_ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1 (in-place)
I0605 23:00:05.487452 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487460 54715 net.cpp:157] Top shape: 2 384 20 20 (307200)
I0605 23:00:05.487464 54715 net.cpp:165] Memory required for data: 1909689600
I0605 23:00:05.487473 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487481 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487486 54715 net.cpp:454] scale_ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487493 54715 net.cpp:397] scale_ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1 (in-place)
I0605 23:00:05.487545 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487679 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487689 54715 net.cpp:157] Top shape: 2 384 20 20 (307200)
I0605 23:00:05.487694 54715 net.cpp:165] Memory required for data: 1910918400
I0605 23:00:05.487699 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487706 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487712 54715 net.cpp:454] relu_ira_Reduction_B_block_1/b_conv3x3_1 <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487720 54715 net.cpp:397] relu_ira_Reduction_B_block_1/b_conv3x3_1 -> ira_Reduction_B_block_1/b_conv3x3_1 (in-place)
I0605 23:00:05.487726 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.487731 54715 net.cpp:157] Top shape: 2 384 20 20 (307200)
I0605 23:00:05.487741 54715 net.cpp:165] Memory required for data: 1912147200
I0605 23:00:05.487752 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.487761 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.487766 54715 net.cpp:454] ira_Reduction_B_block_1/c_conv1x1_1 <- conv4_sum_relu_conv4_sum_0_split_2
I0605 23:00:05.487776 54715 net.cpp:411] ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491171 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491189 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.491194 54715 net.cpp:165] Memory required for data: 1915424000
I0605 23:00:05.491202 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491211 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491216 54715 net.cpp:454] bn_ira_Reduction_B_block_1/c_conv1x1_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491225 54715 net.cpp:397] bn_ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1 (in-place)
I0605 23:00:05.491466 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491474 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.491477 54715 net.cpp:165] Memory required for data: 1918700800
I0605 23:00:05.491487 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491494 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491499 54715 net.cpp:454] scale_ira_Reduction_B_block_1/c_conv1x1_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491506 54715 net.cpp:397] scale_ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1 (in-place)
I0605 23:00:05.491556 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491700 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491709 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.491714 54715 net.cpp:165] Memory required for data: 1921977600
I0605 23:00:05.491720 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491729 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491732 54715 net.cpp:454] relu_ira_Reduction_B_block_1/c_conv1x1_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491739 54715 net.cpp:397] relu_ira_Reduction_B_block_1/c_conv1x1_1 -> ira_Reduction_B_block_1/c_conv1x1_1 (in-place)
I0605 23:00:05.491746 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491752 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.491756 54715 net.cpp:165] Memory required for data: 1925254400
I0605 23:00:05.491760 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.491768 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.491773 54715 net.cpp:454] ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv1x1_1
I0605 23:00:05.491781 54715 net.cpp:411] ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497205 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497222 54715 net.cpp:157] Top shape: 2 288 20 20 (230400)
I0605 23:00:05.497227 54715 net.cpp:165] Memory required for data: 1926176000
I0605 23:00:05.497236 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497244 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497249 54715 net.cpp:454] bn_ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497258 54715 net.cpp:397] bn_ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1 (in-place)
I0605 23:00:05.497515 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497531 54715 net.cpp:157] Top shape: 2 288 20 20 (230400)
I0605 23:00:05.497535 54715 net.cpp:165] Memory required for data: 1927097600
I0605 23:00:05.497545 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497552 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497557 54715 net.cpp:454] scale_ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497565 54715 net.cpp:397] scale_ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1 (in-place)
I0605 23:00:05.497618 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497766 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497776 54715 net.cpp:157] Top shape: 2 288 20 20 (230400)
I0605 23:00:05.497781 54715 net.cpp:165] Memory required for data: 1928019200
I0605 23:00:05.497787 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497794 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497799 54715 net.cpp:454] relu_ira_Reduction_B_block_1/c_conv3x3_1 <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497807 54715 net.cpp:397] relu_ira_Reduction_B_block_1/c_conv3x3_1 -> ira_Reduction_B_block_1/c_conv3x3_1 (in-place)
I0605 23:00:05.497813 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.497819 54715 net.cpp:157] Top shape: 2 288 20 20 (230400)
I0605 23:00:05.497822 54715 net.cpp:165] Memory required for data: 1928940800
I0605 23:00:05.497826 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.497836 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.497841 54715 net.cpp:454] ira_Reduction_B_block_1/d_conv1x1_1 <- conv4_sum_relu_conv4_sum_0_split_3
I0605 23:00:05.497850 54715 net.cpp:411] ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501194 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501214 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.501219 54715 net.cpp:165] Memory required for data: 1932217600
I0605 23:00:05.501227 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501237 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501243 54715 net.cpp:454] bn_ira_Reduction_B_block_1/d_conv1x1_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501251 54715 net.cpp:397] bn_ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1 (in-place)
I0605 23:00:05.501495 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501503 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.501508 54715 net.cpp:165] Memory required for data: 1935494400
I0605 23:00:05.501516 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501523 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501528 54715 net.cpp:454] scale_ira_Reduction_B_block_1/d_conv1x1_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501538 54715 net.cpp:397] scale_ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1 (in-place)
I0605 23:00:05.501590 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501739 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501749 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.501754 54715 net.cpp:165] Memory required for data: 1938771200
I0605 23:00:05.501760 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501766 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501777 54715 net.cpp:454] relu_ira_Reduction_B_block_1/d_conv1x1_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501791 54715 net.cpp:397] relu_ira_Reduction_B_block_1/d_conv1x1_1 -> ira_Reduction_B_block_1/d_conv1x1_1 (in-place)
I0605 23:00:05.501798 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501804 54715 net.cpp:157] Top shape: 2 256 40 40 (819200)
I0605 23:00:05.501808 54715 net.cpp:165] Memory required for data: 1942048000
I0605 23:00:05.501813 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.501822 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.501827 54715 net.cpp:454] ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv1x1_1
I0605 23:00:05.501834 54715 net.cpp:411] ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507567 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507586 54715 net.cpp:157] Top shape: 2 288 40 40 (921600)
I0605 23:00:05.507591 54715 net.cpp:165] Memory required for data: 1945734400
I0605 23:00:05.507598 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507608 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507614 54715 net.cpp:454] bn_ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507622 54715 net.cpp:397] bn_ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1 (in-place)
I0605 23:00:05.507880 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507889 54715 net.cpp:157] Top shape: 2 288 40 40 (921600)
I0605 23:00:05.507894 54715 net.cpp:165] Memory required for data: 1949420800
I0605 23:00:05.507901 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507910 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507915 54715 net.cpp:454] scale_ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.507921 54715 net.cpp:397] scale_ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1 (in-place)
I0605 23:00:05.507974 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508132 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508167 54715 net.cpp:157] Top shape: 2 288 40 40 (921600)
I0605 23:00:05.508172 54715 net.cpp:165] Memory required for data: 1953107200
I0605 23:00:05.508179 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508188 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508193 54715 net.cpp:454] relu_ira_Reduction_B_block_1/d_conv3x3_1 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508199 54715 net.cpp:397] relu_ira_Reduction_B_block_1/d_conv3x3_1 -> ira_Reduction_B_block_1/d_conv3x3_1 (in-place)
I0605 23:00:05.508206 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508211 54715 net.cpp:157] Top shape: 2 288 40 40 (921600)
I0605 23:00:05.508216 54715 net.cpp:165] Memory required for data: 1956793600
I0605 23:00:05.508220 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.508229 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.508234 54715 net.cpp:454] ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_1
I0605 23:00:05.508241 54715 net.cpp:411] ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.514799 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.514816 54715 net.cpp:157] Top shape: 2 320 20 20 (256000)
I0605 23:00:05.514822 54715 net.cpp:165] Memory required for data: 1957817600
I0605 23:00:05.514830 54715 layer_factory.hpp:77] Creating layer bn_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.514852 54715 net.cpp:106] Creating Layer bn_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.514858 54715 net.cpp:454] bn_ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.514865 54715 net.cpp:397] bn_ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2 (in-place)
I0605 23:00:05.515120 54715 net.cpp:150] Setting up bn_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515127 54715 net.cpp:157] Top shape: 2 320 20 20 (256000)
I0605 23:00:05.515131 54715 net.cpp:165] Memory required for data: 1958841600
I0605 23:00:05.515139 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515148 54715 net.cpp:106] Creating Layer scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515153 54715 net.cpp:454] scale_ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515161 54715 net.cpp:397] scale_ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2 (in-place)
I0605 23:00:05.515214 54715 layer_factory.hpp:77] Creating layer scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515364 54715 net.cpp:150] Setting up scale_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515373 54715 net.cpp:157] Top shape: 2 320 20 20 (256000)
I0605 23:00:05.515377 54715 net.cpp:165] Memory required for data: 1959865600
I0605 23:00:05.515383 54715 layer_factory.hpp:77] Creating layer relu_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515391 54715 net.cpp:106] Creating Layer relu_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515396 54715 net.cpp:454] relu_ira_Reduction_B_block_1/d_conv3x3_2 <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515403 54715 net.cpp:397] relu_ira_Reduction_B_block_1/d_conv3x3_2 -> ira_Reduction_B_block_1/d_conv3x3_2 (in-place)
I0605 23:00:05.515410 54715 net.cpp:150] Setting up relu_ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515417 54715 net.cpp:157] Top shape: 2 320 20 20 (256000)
I0605 23:00:05.515421 54715 net.cpp:165] Memory required for data: 1960889600
I0605 23:00:05.515425 54715 layer_factory.hpp:77] Creating layer ira_Reduction_B_block_1/concat
I0605 23:00:05.515431 54715 net.cpp:106] Creating Layer ira_Reduction_B_block_1/concat
I0605 23:00:05.515436 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/a_pool
I0605 23:00:05.515442 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/b_conv3x3_1
I0605 23:00:05.515447 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/c_conv3x3_1
I0605 23:00:05.515452 54715 net.cpp:454] ira_Reduction_B_block_1/concat <- ira_Reduction_B_block_1/d_conv3x3_2
I0605 23:00:05.515460 54715 net.cpp:411] ira_Reduction_B_block_1/concat -> ira_Reduction_B_block_1/concat
I0605 23:00:05.515493 54715 net.cpp:150] Setting up ira_Reduction_B_block_1/concat
I0605 23:00:05.515501 54715 net.cpp:157] Top shape: 2 2146 20 20 (1716800)
I0605 23:00:05.515504 54715 net.cpp:165] Memory required for data: 1967756800
I0605 23:00:05.515509 54715 layer_factory.hpp:77] Creating layer conv5_1b
I0605 23:00:05.515518 54715 net.cpp:106] Creating Layer conv5_1b
I0605 23:00:05.515523 54715 net.cpp:454] conv5_1b <- ira_Reduction_B_block_1/concat
I0605 23:00:05.515532 54715 net.cpp:411] conv5_1b -> conv5_1b
I0605 23:00:05.547037 54715 net.cpp:150] Setting up conv5_1b
I0605 23:00:05.547061 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547066 54715 net.cpp:165] Memory required for data: 1974310400
I0605 23:00:05.547076 54715 layer_factory.hpp:77] Creating layer bn_conv5_1b
I0605 23:00:05.547089 54715 net.cpp:106] Creating Layer bn_conv5_1b
I0605 23:00:05.547096 54715 net.cpp:454] bn_conv5_1b <- conv5_1b
I0605 23:00:05.547104 54715 net.cpp:397] bn_conv5_1b -> conv5_1b (in-place)
I0605 23:00:05.547354 54715 net.cpp:150] Setting up bn_conv5_1b
I0605 23:00:05.547363 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547368 54715 net.cpp:165] Memory required for data: 1980864000
I0605 23:00:05.547385 54715 layer_factory.hpp:77] Creating layer scale_conv5_1b
I0605 23:00:05.547403 54715 net.cpp:106] Creating Layer scale_conv5_1b
I0605 23:00:05.547408 54715 net.cpp:454] scale_conv5_1b <- conv5_1b
I0605 23:00:05.547415 54715 net.cpp:397] scale_conv5_1b -> conv5_1b (in-place)
I0605 23:00:05.547475 54715 layer_factory.hpp:77] Creating layer scale_conv5_1b
I0605 23:00:05.547627 54715 net.cpp:150] Setting up scale_conv5_1b
I0605 23:00:05.547637 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547641 54715 net.cpp:165] Memory required for data: 1987417600
I0605 23:00:05.547648 54715 layer_factory.hpp:77] Creating layer relu5_1b
I0605 23:00:05.547657 54715 net.cpp:106] Creating Layer relu5_1b
I0605 23:00:05.547662 54715 net.cpp:454] relu5_1b <- conv5_1b
I0605 23:00:05.547669 54715 net.cpp:397] relu5_1b -> conv5_1b (in-place)
I0605 23:00:05.547675 54715 net.cpp:150] Setting up relu5_1b
I0605 23:00:05.547680 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547685 54715 net.cpp:165] Memory required for data: 1993971200
I0605 23:00:05.547689 54715 layer_factory.hpp:77] Creating layer conv5_1b_relu5_1b_0_split
I0605 23:00:05.547698 54715 net.cpp:106] Creating Layer conv5_1b_relu5_1b_0_split
I0605 23:00:05.547701 54715 net.cpp:454] conv5_1b_relu5_1b_0_split <- conv5_1b
I0605 23:00:05.547708 54715 net.cpp:411] conv5_1b_relu5_1b_0_split -> conv5_1b_relu5_1b_0_split_0
I0605 23:00:05.547718 54715 net.cpp:411] conv5_1b_relu5_1b_0_split -> conv5_1b_relu5_1b_0_split_1
I0605 23:00:05.547725 54715 net.cpp:411] conv5_1b_relu5_1b_0_split -> conv5_1b_relu5_1b_0_split_2
I0605 23:00:05.547789 54715 net.cpp:150] Setting up conv5_1b_relu5_1b_0_split
I0605 23:00:05.547797 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547802 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547807 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.547811 54715 net.cpp:165] Memory required for data: 2013632000
I0605 23:00:05.547816 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.547825 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.547830 54715 net.cpp:454] ira_Inception_C_block_1/a_conv1x1_1 <- conv5_1b_relu5_1b_0_split_0
I0605 23:00:05.547839 54715 net.cpp:411] ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.551939 54715 net.cpp:150] Setting up ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.551956 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.551961 54715 net.cpp:165] Memory required for data: 2014246400
I0605 23:00:05.551968 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.551980 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.551985 54715 net.cpp:454] bn_ira_Inception_C_block_1/a_conv1x1_1 <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.551992 54715 net.cpp:397] bn_ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1 (in-place)
I0605 23:00:05.552295 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552306 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.552310 54715 net.cpp:165] Memory required for data: 2014860800
I0605 23:00:05.552320 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552328 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552335 54715 net.cpp:454] scale_ira_Inception_C_block_1/a_conv1x1_1 <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552340 54715 net.cpp:397] scale_ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1 (in-place)
I0605 23:00:05.552395 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552547 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552556 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.552567 54715 net.cpp:165] Memory required for data: 2015475200
I0605 23:00:05.552580 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552588 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552594 54715 net.cpp:454] relu_ira_Inception_C_block_1/a_conv1x1_1 <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552601 54715 net.cpp:397] relu_ira_Inception_C_block_1/a_conv1x1_1 -> ira_Inception_C_block_1/a_conv1x1_1 (in-place)
I0605 23:00:05.552608 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.552614 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.552619 54715 net.cpp:165] Memory required for data: 2016089600
I0605 23:00:05.552623 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.552633 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.552637 54715 net.cpp:454] ira_Inception_C_block_1/b_conv1x1_1 <- conv5_1b_relu5_1b_0_split_1
I0605 23:00:05.552647 54715 net.cpp:411] ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.556794 54715 net.cpp:150] Setting up ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.556812 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.556816 54715 net.cpp:165] Memory required for data: 2016704000
I0605 23:00:05.556824 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.556834 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.556840 54715 net.cpp:454] bn_ira_Inception_C_block_1/b_conv1x1_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.556849 54715 net.cpp:397] bn_ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.557098 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557106 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.557109 54715 net.cpp:165] Memory required for data: 2017318400
I0605 23:00:05.557149 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557158 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557163 54715 net.cpp:454] scale_ira_Inception_C_block_1/b_conv1x1_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557169 54715 net.cpp:397] scale_ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.557225 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557379 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557389 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.557392 54715 net.cpp:165] Memory required for data: 2017932800
I0605 23:00:05.557399 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557407 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557412 54715 net.cpp:454] relu_ira_Inception_C_block_1/b_conv1x1_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557418 54715 net.cpp:397] relu_ira_Inception_C_block_1/b_conv1x1_1 -> ira_Inception_C_block_1/b_conv1x1_1 (in-place)
I0605 23:00:05.557425 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557432 54715 net.cpp:157] Top shape: 2 192 20 20 (153600)
I0605 23:00:05.557435 54715 net.cpp:165] Memory required for data: 2018547200
I0605 23:00:05.557440 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.557448 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.557453 54715 net.cpp:454] ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x1_1
I0605 23:00:05.557461 54715 net.cpp:411] ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558471 54715 net.cpp:150] Setting up ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558488 54715 net.cpp:157] Top shape: 2 224 20 20 (179200)
I0605 23:00:05.558493 54715 net.cpp:165] Memory required for data: 2019264000
I0605 23:00:05.558501 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558508 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558513 54715 net.cpp:454] bn_ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558521 54715 net.cpp:397] bn_ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1 (in-place)
I0605 23:00:05.558768 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558776 54715 net.cpp:157] Top shape: 2 224 20 20 (179200)
I0605 23:00:05.558780 54715 net.cpp:165] Memory required for data: 2019980800
I0605 23:00:05.558789 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558796 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558801 54715 net.cpp:454] scale_ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.558807 54715 net.cpp:397] scale_ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1 (in-place)
I0605 23:00:05.558859 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559011 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559020 54715 net.cpp:157] Top shape: 2 224 20 20 (179200)
I0605 23:00:05.559025 54715 net.cpp:165] Memory required for data: 2020697600
I0605 23:00:05.559031 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559039 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559043 54715 net.cpp:454] relu_ira_Inception_C_block_1/b_conv1x7_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559051 54715 net.cpp:397] relu_ira_Inception_C_block_1/b_conv1x7_1 -> ira_Inception_C_block_1/b_conv1x7_1 (in-place)
I0605 23:00:05.559058 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559064 54715 net.cpp:157] Top shape: 2 224 20 20 (179200)
I0605 23:00:05.559068 54715 net.cpp:165] Memory required for data: 2021414400
I0605 23:00:05.559072 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.559082 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.559085 54715 net.cpp:454] ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv1x7_1
I0605 23:00:05.559093 54715 net.cpp:411] ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560431 54715 net.cpp:150] Setting up ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560444 54715 net.cpp:157] Top shape: 2 256 20 20 (204800)
I0605 23:00:05.560448 54715 net.cpp:165] Memory required for data: 2022233600
I0605 23:00:05.560456 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560463 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560469 54715 net.cpp:454] bn_ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560475 54715 net.cpp:397] bn_ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1 (in-place)
I0605 23:00:05.560712 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560720 54715 net.cpp:157] Top shape: 2 256 20 20 (204800)
I0605 23:00:05.560724 54715 net.cpp:165] Memory required for data: 2023052800
I0605 23:00:05.560732 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560739 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560745 54715 net.cpp:454] scale_ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560757 54715 net.cpp:397] scale_ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1 (in-place)
I0605 23:00:05.560817 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560958 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560967 54715 net.cpp:157] Top shape: 2 256 20 20 (204800)
I0605 23:00:05.560972 54715 net.cpp:165] Memory required for data: 2023872000
I0605 23:00:05.560979 54715 layer_factory.hpp:77] Creating layer relu_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560987 54715 net.cpp:106] Creating Layer relu_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560992 54715 net.cpp:454] relu_ira_Inception_C_block_1/b_conv7x1_1 <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.560999 54715 net.cpp:397] relu_ira_Inception_C_block_1/b_conv7x1_1 -> ira_Inception_C_block_1/b_conv7x1_1 (in-place)
I0605 23:00:05.561007 54715 net.cpp:150] Setting up relu_ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.561012 54715 net.cpp:157] Top shape: 2 256 20 20 (204800)
I0605 23:00:05.561015 54715 net.cpp:165] Memory required for data: 2024691200
I0605 23:00:05.561019 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/concat
I0605 23:00:05.561027 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/concat
I0605 23:00:05.561030 54715 net.cpp:454] ira_Inception_C_block_1/concat <- ira_Inception_C_block_1/a_conv1x1_1
I0605 23:00:05.561035 54715 net.cpp:454] ira_Inception_C_block_1/concat <- ira_Inception_C_block_1/b_conv7x1_1
I0605 23:00:05.561043 54715 net.cpp:411] ira_Inception_C_block_1/concat -> ira_Inception_C_block_1/concat
I0605 23:00:05.561075 54715 net.cpp:150] Setting up ira_Inception_C_block_1/concat
I0605 23:00:05.561082 54715 net.cpp:157] Top shape: 2 448 20 20 (358400)
I0605 23:00:05.561085 54715 net.cpp:165] Memory required for data: 2026124800
I0605 23:00:05.561090 54715 layer_factory.hpp:77] Creating layer ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.561100 54715 net.cpp:106] Creating Layer ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.561105 54715 net.cpp:454] ira_Inception_C_block_1/top_conv_1x1 <- ira_Inception_C_block_1/concat
I0605 23:00:05.561112 54715 net.cpp:411] ira_Inception_C_block_1/top_conv_1x1 -> ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568346 54715 net.cpp:150] Setting up ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568365 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.568370 54715 net.cpp:165] Memory required for data: 2032678400
I0605 23:00:05.568379 54715 layer_factory.hpp:77] Creating layer bn_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568389 54715 net.cpp:106] Creating Layer bn_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568397 54715 net.cpp:454] bn_ira_Inception_C_block_1/top_conv_1x1 <- ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568405 54715 net.cpp:397] bn_ira_Inception_C_block_1/top_conv_1x1 -> ira_Inception_C_block_1/top_conv_1x1 (in-place)
I0605 23:00:05.568645 54715 net.cpp:150] Setting up bn_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568655 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.568658 54715 net.cpp:165] Memory required for data: 2039232000
I0605 23:00:05.568667 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568676 54715 net.cpp:106] Creating Layer scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568681 54715 net.cpp:454] scale_ira_Inception_C_block_1/top_conv_1x1 <- ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568689 54715 net.cpp:397] scale_ira_Inception_C_block_1/top_conv_1x1 -> ira_Inception_C_block_1/top_conv_1x1 (in-place)
I0605 23:00:05.568740 54715 layer_factory.hpp:77] Creating layer scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568891 54715 net.cpp:150] Setting up scale_ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568899 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.568904 54715 net.cpp:165] Memory required for data: 2045785600
I0605 23:00:05.568918 54715 layer_factory.hpp:77] Creating layer conv5_sum
I0605 23:00:05.568935 54715 net.cpp:106] Creating Layer conv5_sum
I0605 23:00:05.568941 54715 net.cpp:454] conv5_sum <- conv5_1b_relu5_1b_0_split_2
I0605 23:00:05.568948 54715 net.cpp:454] conv5_sum <- ira_Inception_C_block_1/top_conv_1x1
I0605 23:00:05.568956 54715 net.cpp:411] conv5_sum -> conv5_sum
I0605 23:00:05.568991 54715 net.cpp:150] Setting up conv5_sum
I0605 23:00:05.569000 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.569003 54715 net.cpp:165] Memory required for data: 2052339200
I0605 23:00:05.569007 54715 layer_factory.hpp:77] Creating layer relu_conv5_sum
I0605 23:00:05.569015 54715 net.cpp:106] Creating Layer relu_conv5_sum
I0605 23:00:05.569020 54715 net.cpp:454] relu_conv5_sum <- conv5_sum
I0605 23:00:05.569026 54715 net.cpp:397] relu_conv5_sum -> conv5_sum (in-place)
I0605 23:00:05.569033 54715 net.cpp:150] Setting up relu_conv5_sum
I0605 23:00:05.569038 54715 net.cpp:157] Top shape: 2 2048 20 20 (1638400)
I0605 23:00:05.569043 54715 net.cpp:165] Memory required for data: 2058892800
I0605 23:00:05.569047 54715 layer_factory.hpp:77] Creating layer deconv5_16x
I0605 23:00:05.569056 54715 net.cpp:106] Creating Layer deconv5_16x
I0605 23:00:05.569061 54715 net.cpp:454] deconv5_16x <- conv5_sum
I0605 23:00:05.569069 54715 net.cpp:411] deconv5_16x -> deconv5_16x
I0605 23:00:05.776062 54715 net.cpp:150] Setting up deconv5_16x
I0605 23:00:05.776099 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.776104 54715 net.cpp:165] Memory required for data: 2060531200
I0605 23:00:05.776115 54715 layer_factory.hpp:77] Creating layer deconv2_2x_d1
I0605 23:00:05.776130 54715 net.cpp:106] Creating Layer deconv2_2x_d1
I0605 23:00:05.776161 54715 net.cpp:454] deconv2_2x_d1 <- concat_stem_1_concat_stem_1_0_split_2
I0605 23:00:05.776176 54715 net.cpp:411] deconv2_2x_d1 -> deconv2_2x_d1
I0605 23:00:05.776890 54715 net.cpp:150] Setting up deconv2_2x_d1
I0605 23:00:05.776901 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.776906 54715 net.cpp:165] Memory required for data: 2062169600
I0605 23:00:05.776912 54715 layer_factory.hpp:77] Creating layer fc1_2x_c0
I0605 23:00:05.776922 54715 net.cpp:106] Creating Layer fc1_2x_c0
I0605 23:00:05.776927 54715 net.cpp:454] fc1_2x_c0 <- concat_stem_1_concat_stem_1_0_split_3
I0605 23:00:05.776937 54715 net.cpp:411] fc1_2x_c0 -> deconv2_2x_c0
I0605 23:00:05.777410 54715 net.cpp:150] Setting up fc1_2x_c0
I0605 23:00:05.777420 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.777424 54715 net.cpp:165] Memory required for data: 2063808000
I0605 23:00:05.777431 54715 layer_factory.hpp:77] Creating layer fc1_2x_c1
I0605 23:00:05.777441 54715 net.cpp:106] Creating Layer fc1_2x_c1
I0605 23:00:05.777446 54715 net.cpp:454] fc1_2x_c1 <- concat_stem_1_concat_stem_1_0_split_4
I0605 23:00:05.777454 54715 net.cpp:411] fc1_2x_c1 -> deconv2_2x_c1
I0605 23:00:05.777922 54715 net.cpp:150] Setting up fc1_2x_c1
I0605 23:00:05.777932 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.777936 54715 net.cpp:165] Memory required for data: 2065446400
I0605 23:00:05.777943 54715 layer_factory.hpp:77] Creating layer fc1_2x_c2
I0605 23:00:05.777952 54715 net.cpp:106] Creating Layer fc1_2x_c2
I0605 23:00:05.777957 54715 net.cpp:454] fc1_2x_c2 <- concat_stem_1_concat_stem_1_0_split_5
I0605 23:00:05.777966 54715 net.cpp:411] fc1_2x_c2 -> deconv2_2x_c2
I0605 23:00:05.778431 54715 net.cpp:150] Setting up fc1_2x_c2
I0605 23:00:05.778440 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.778445 54715 net.cpp:165] Memory required for data: 2067084800
I0605 23:00:05.778450 54715 layer_factory.hpp:77] Creating layer fc1_2x_c3
I0605 23:00:05.778460 54715 net.cpp:106] Creating Layer fc1_2x_c3
I0605 23:00:05.778465 54715 net.cpp:454] fc1_2x_c3 <- concat_stem_1_concat_stem_1_0_split_6
I0605 23:00:05.778473 54715 net.cpp:411] fc1_2x_c3 -> deconv2_2x_c3
I0605 23:00:05.780375 54715 net.cpp:150] Setting up fc1_2x_c3
I0605 23:00:05.780401 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.780413 54715 net.cpp:165] Memory required for data: 2068723200
I0605 23:00:05.780421 54715 layer_factory.hpp:77] Creating layer fc1_2x
I0605 23:00:05.780431 54715 net.cpp:106] Creating Layer fc1_2x
I0605 23:00:05.780437 54715 net.cpp:454] fc1_2x <- deconv2_2x_d1
I0605 23:00:05.780443 54715 net.cpp:454] fc1_2x <- deconv2_2x_c0
I0605 23:00:05.780448 54715 net.cpp:454] fc1_2x <- deconv2_2x_c1
I0605 23:00:05.780453 54715 net.cpp:454] fc1_2x <- deconv2_2x_c2
I0605 23:00:05.780458 54715 net.cpp:454] fc1_2x <- deconv2_2x_c3
I0605 23:00:05.780464 54715 net.cpp:411] fc1_2x -> deconv2_2x
I0605 23:00:05.780506 54715 net.cpp:150] Setting up fc1_2x
I0605 23:00:05.780515 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.780519 54715 net.cpp:165] Memory required for data: 2070361600
I0605 23:00:05.780524 54715 layer_factory.hpp:77] Creating layer fc1_4x_c0
I0605 23:00:05.780532 54715 net.cpp:106] Creating Layer fc1_4x_c0
I0605 23:00:05.780539 54715 net.cpp:454] fc1_4x_c0 <- conv3_sum_relu3_sum_0_split_3
I0605 23:00:05.780547 54715 net.cpp:411] fc1_4x_c0 -> deconv3_4x_c0
I0605 23:00:05.781417 54715 net.cpp:150] Setting up fc1_4x_c0
I0605 23:00:05.781427 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.781431 54715 net.cpp:165] Memory required for data: 2072000000
I0605 23:00:05.781438 54715 layer_factory.hpp:77] Creating layer deconv3_4x_d1
I0605 23:00:05.781446 54715 net.cpp:106] Creating Layer deconv3_4x_d1
I0605 23:00:05.781450 54715 net.cpp:454] deconv3_4x_d1 <- conv3_sum_relu3_sum_0_split_4
I0605 23:00:05.781458 54715 net.cpp:411] deconv3_4x_d1 -> deconv3_4x_d1
I0605 23:00:05.784162 54715 net.cpp:150] Setting up deconv3_4x_d1
I0605 23:00:05.784173 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.784178 54715 net.cpp:165] Memory required for data: 2073638400
I0605 23:00:05.784185 54715 layer_factory.hpp:77] Creating layer fc1_4x_c1
I0605 23:00:05.784195 54715 net.cpp:106] Creating Layer fc1_4x_c1
I0605 23:00:05.784200 54715 net.cpp:454] fc1_4x_c1 <- conv3_sum_relu3_sum_0_split_5
I0605 23:00:05.784209 54715 net.cpp:411] fc1_4x_c1 -> deconv3_4x_c1
I0605 23:00:05.785066 54715 net.cpp:150] Setting up fc1_4x_c1
I0605 23:00:05.785075 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.785079 54715 net.cpp:165] Memory required for data: 2075276800
I0605 23:00:05.785085 54715 layer_factory.hpp:77] Creating layer fc1_4x_c2
I0605 23:00:05.785094 54715 net.cpp:106] Creating Layer fc1_4x_c2
I0605 23:00:05.785099 54715 net.cpp:454] fc1_4x_c2 <- conv3_sum_relu3_sum_0_split_6
I0605 23:00:05.785107 54715 net.cpp:411] fc1_4x_c2 -> deconv3_4x_c2
I0605 23:00:05.785964 54715 net.cpp:150] Setting up fc1_4x_c2
I0605 23:00:05.785974 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.785979 54715 net.cpp:165] Memory required for data: 2076915200
I0605 23:00:05.785984 54715 layer_factory.hpp:77] Creating layer fc1_4x_c3
I0605 23:00:05.785993 54715 net.cpp:106] Creating Layer fc1_4x_c3
I0605 23:00:05.785997 54715 net.cpp:454] fc1_4x_c3 <- conv3_sum_relu3_sum_0_split_7
I0605 23:00:05.786006 54715 net.cpp:411] fc1_4x_c3 -> deconv3_4x_c3
I0605 23:00:05.788261 54715 net.cpp:150] Setting up fc1_4x_c3
I0605 23:00:05.788280 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.788286 54715 net.cpp:165] Memory required for data: 2078553600
I0605 23:00:05.788295 54715 layer_factory.hpp:77] Creating layer fc1_4x
I0605 23:00:05.788305 54715 net.cpp:106] Creating Layer fc1_4x
I0605 23:00:05.788311 54715 net.cpp:454] fc1_4x <- deconv3_4x_d1
I0605 23:00:05.788317 54715 net.cpp:454] fc1_4x <- deconv3_4x_c0
I0605 23:00:05.788323 54715 net.cpp:454] fc1_4x <- deconv3_4x_c1
I0605 23:00:05.788327 54715 net.cpp:454] fc1_4x <- deconv3_4x_c2
I0605 23:00:05.788332 54715 net.cpp:454] fc1_4x <- deconv3_4x_c3
I0605 23:00:05.788339 54715 net.cpp:411] fc1_4x -> deconv3_4x
I0605 23:00:05.788380 54715 net.cpp:150] Setting up fc1_4x
I0605 23:00:05.788388 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.788393 54715 net.cpp:165] Memory required for data: 2080192000
I0605 23:00:05.788409 54715 layer_factory.hpp:77] Creating layer deconv4_8x_d1
I0605 23:00:05.788420 54715 net.cpp:106] Creating Layer deconv4_8x_d1
I0605 23:00:05.788426 54715 net.cpp:454] deconv4_8x_d1 <- conv4_sum_relu_conv4_sum_0_split_4
I0605 23:00:05.788434 54715 net.cpp:411] deconv4_8x_d1 -> deconv4_8x_d1
I0605 23:00:05.818154 54715 net.cpp:150] Setting up deconv4_8x_d1
I0605 23:00:05.818181 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.818186 54715 net.cpp:165] Memory required for data: 2081830400
I0605 23:00:05.818195 54715 layer_factory.hpp:77] Creating layer fc1_8x_c0
I0605 23:00:05.818208 54715 net.cpp:106] Creating Layer fc1_8x_c0
I0605 23:00:05.818215 54715 net.cpp:454] fc1_8x_c0 <- conv4_sum_relu_conv4_sum_0_split_5
I0605 23:00:05.818226 54715 net.cpp:411] fc1_8x_c0 -> deconv4_8x_c0
I0605 23:00:05.825901 54715 net.cpp:150] Setting up fc1_8x_c0
I0605 23:00:05.825920 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.825925 54715 net.cpp:165] Memory required for data: 2083468800
I0605 23:00:05.825934 54715 layer_factory.hpp:77] Creating layer fc1_8x_c1
I0605 23:00:05.825945 54715 net.cpp:106] Creating Layer fc1_8x_c1
I0605 23:00:05.825950 54715 net.cpp:454] fc1_8x_c1 <- conv4_sum_relu_conv4_sum_0_split_6
I0605 23:00:05.825960 54715 net.cpp:411] fc1_8x_c1 -> deconv4_8x_c1
I0605 23:00:05.833597 54715 net.cpp:150] Setting up fc1_8x_c1
I0605 23:00:05.833616 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.833621 54715 net.cpp:165] Memory required for data: 2085107200
I0605 23:00:05.833631 54715 layer_factory.hpp:77] Creating layer fc1_8x_c2
I0605 23:00:05.833642 54715 net.cpp:106] Creating Layer fc1_8x_c2
I0605 23:00:05.833647 54715 net.cpp:454] fc1_8x_c2 <- conv4_sum_relu_conv4_sum_0_split_7
I0605 23:00:05.833657 54715 net.cpp:411] fc1_8x_c2 -> deconv4_8x_c2
I0605 23:00:05.841287 54715 net.cpp:150] Setting up fc1_8x_c2
I0605 23:00:05.841305 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.841310 54715 net.cpp:165] Memory required for data: 2086745600
I0605 23:00:05.841317 54715 layer_factory.hpp:77] Creating layer fc1_8x_c3
I0605 23:00:05.841329 54715 net.cpp:106] Creating Layer fc1_8x_c3
I0605 23:00:05.841334 54715 net.cpp:454] fc1_8x_c3 <- conv4_sum_relu_conv4_sum_0_split_8
I0605 23:00:05.841344 54715 net.cpp:411] fc1_8x_c3 -> deconv4_8x_c3
I0605 23:00:05.850260 54715 net.cpp:150] Setting up fc1_8x_c3
I0605 23:00:05.850278 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.850283 54715 net.cpp:165] Memory required for data: 2088384000
I0605 23:00:05.850291 54715 layer_factory.hpp:77] Creating layer fc1_8x
I0605 23:00:05.850301 54715 net.cpp:106] Creating Layer fc1_8x
I0605 23:00:05.850307 54715 net.cpp:454] fc1_8x <- deconv4_8x_d1
I0605 23:00:05.850313 54715 net.cpp:454] fc1_8x <- deconv4_8x_c0
I0605 23:00:05.850318 54715 net.cpp:454] fc1_8x <- deconv4_8x_c1
I0605 23:00:05.850324 54715 net.cpp:454] fc1_8x <- deconv4_8x_c2
I0605 23:00:05.850329 54715 net.cpp:454] fc1_8x <- deconv4_8x_c3
I0605 23:00:05.850337 54715 net.cpp:411] fc1_8x -> deconv4_8x
I0605 23:00:05.850379 54715 net.cpp:150] Setting up fc1_8x
I0605 23:00:05.850387 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.850392 54715 net.cpp:165] Memory required for data: 2090022400
I0605 23:00:05.850396 54715 layer_factory.hpp:77] Creating layer bn_deconv5_16x
I0605 23:00:05.850404 54715 net.cpp:106] Creating Layer bn_deconv5_16x
I0605 23:00:05.850409 54715 net.cpp:454] bn_deconv5_16x <- deconv5_16x
I0605 23:00:05.850417 54715 net.cpp:397] bn_deconv5_16x -> deconv5_16x (in-place)
I0605 23:00:05.850754 54715 net.cpp:150] Setting up bn_deconv5_16x
I0605 23:00:05.850762 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.850766 54715 net.cpp:165] Memory required for data: 2091660800
I0605 23:00:05.850776 54715 layer_factory.hpp:77] Creating layer scale_deconv5_16x
I0605 23:00:05.850785 54715 net.cpp:106] Creating Layer scale_deconv5_16x
I0605 23:00:05.850790 54715 net.cpp:454] scale_deconv5_16x <- deconv5_16x
I0605 23:00:05.850805 54715 net.cpp:397] scale_deconv5_16x -> deconv5_16x (in-place)
I0605 23:00:05.850872 54715 layer_factory.hpp:77] Creating layer scale_deconv5_16x
I0605 23:00:05.851145 54715 net.cpp:150] Setting up scale_deconv5_16x
I0605 23:00:05.851153 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.851158 54715 net.cpp:165] Memory required for data: 2093299200
I0605 23:00:05.851166 54715 layer_factory.hpp:77] Creating layer relu_deconv5_16x
I0605 23:00:05.851173 54715 net.cpp:106] Creating Layer relu_deconv5_16x
I0605 23:00:05.851178 54715 net.cpp:454] relu_deconv5_16x <- deconv5_16x
I0605 23:00:05.851186 54715 net.cpp:397] relu_deconv5_16x -> deconv5_16x (in-place)
I0605 23:00:05.851192 54715 net.cpp:150] Setting up relu_deconv5_16x
I0605 23:00:05.851197 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.851202 54715 net.cpp:165] Memory required for data: 2094937600
I0605 23:00:05.851205 54715 layer_factory.hpp:77] Creating layer bn_deconv4_8x
I0605 23:00:05.851212 54715 net.cpp:106] Creating Layer bn_deconv4_8x
I0605 23:00:05.851217 54715 net.cpp:454] bn_deconv4_8x <- deconv4_8x
I0605 23:00:05.851222 54715 net.cpp:397] bn_deconv4_8x -> deconv4_8x (in-place)
I0605 23:00:05.851532 54715 net.cpp:150] Setting up bn_deconv4_8x
I0605 23:00:05.851541 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.851544 54715 net.cpp:165] Memory required for data: 2096576000
I0605 23:00:05.851553 54715 layer_factory.hpp:77] Creating layer scale_deconv4_8x
I0605 23:00:05.851562 54715 net.cpp:106] Creating Layer scale_deconv4_8x
I0605 23:00:05.851565 54715 net.cpp:454] scale_deconv4_8x <- deconv4_8x
I0605 23:00:05.851572 54715 net.cpp:397] scale_deconv4_8x -> deconv4_8x (in-place)
I0605 23:00:05.851622 54715 layer_factory.hpp:77] Creating layer scale_deconv4_8x
I0605 23:00:05.853276 54715 net.cpp:150] Setting up scale_deconv4_8x
I0605 23:00:05.853293 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.853297 54715 net.cpp:165] Memory required for data: 2098214400
I0605 23:00:05.853305 54715 layer_factory.hpp:77] Creating layer relu_deconv4_8x
I0605 23:00:05.853313 54715 net.cpp:106] Creating Layer relu_deconv4_8x
I0605 23:00:05.853319 54715 net.cpp:454] relu_deconv4_8x <- deconv4_8x
I0605 23:00:05.853327 54715 net.cpp:397] relu_deconv4_8x -> deconv4_8x (in-place)
I0605 23:00:05.853333 54715 net.cpp:150] Setting up relu_deconv4_8x
I0605 23:00:05.853339 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.853343 54715 net.cpp:165] Memory required for data: 2099852800
I0605 23:00:05.853348 54715 layer_factory.hpp:77] Creating layer bn_deconv3_4x
I0605 23:00:05.853353 54715 net.cpp:106] Creating Layer bn_deconv3_4x
I0605 23:00:05.853358 54715 net.cpp:454] bn_deconv3_4x <- deconv3_4x
I0605 23:00:05.853365 54715 net.cpp:397] bn_deconv3_4x -> deconv3_4x (in-place)
I0605 23:00:05.853682 54715 net.cpp:150] Setting up bn_deconv3_4x
I0605 23:00:05.853690 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.853694 54715 net.cpp:165] Memory required for data: 2101491200
I0605 23:00:05.853703 54715 layer_factory.hpp:77] Creating layer scale_deconv3_4x
I0605 23:00:05.853710 54715 net.cpp:106] Creating Layer scale_deconv3_4x
I0605 23:00:05.853714 54715 net.cpp:454] scale_deconv3_4x <- deconv3_4x
I0605 23:00:05.853721 54715 net.cpp:397] scale_deconv3_4x -> deconv3_4x (in-place)
I0605 23:00:05.853773 54715 layer_factory.hpp:77] Creating layer scale_deconv3_4x
I0605 23:00:05.854046 54715 net.cpp:150] Setting up scale_deconv3_4x
I0605 23:00:05.854055 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.854059 54715 net.cpp:165] Memory required for data: 2103129600
I0605 23:00:05.854068 54715 layer_factory.hpp:77] Creating layer relu_deconv3_4x
I0605 23:00:05.854074 54715 net.cpp:106] Creating Layer relu_deconv3_4x
I0605 23:00:05.854079 54715 net.cpp:454] relu_deconv3_4x <- deconv3_4x
I0605 23:00:05.854085 54715 net.cpp:397] relu_deconv3_4x -> deconv3_4x (in-place)
I0605 23:00:05.854091 54715 net.cpp:150] Setting up relu_deconv3_4x
I0605 23:00:05.854102 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.854112 54715 net.cpp:165] Memory required for data: 2104768000
I0605 23:00:05.854117 54715 layer_factory.hpp:77] Creating layer bn_deconv2_2x
I0605 23:00:05.854125 54715 net.cpp:106] Creating Layer bn_deconv2_2x
I0605 23:00:05.854130 54715 net.cpp:454] bn_deconv2_2x <- deconv2_2x
I0605 23:00:05.854136 54715 net.cpp:397] bn_deconv2_2x -> deconv2_2x (in-place)
I0605 23:00:05.855818 54715 net.cpp:150] Setting up bn_deconv2_2x
I0605 23:00:05.855835 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.855839 54715 net.cpp:165] Memory required for data: 2106406400
I0605 23:00:05.855849 54715 layer_factory.hpp:77] Creating layer scale_deconv2_2x
I0605 23:00:05.855857 54715 net.cpp:106] Creating Layer scale_deconv2_2x
I0605 23:00:05.855864 54715 net.cpp:454] scale_deconv2_2x <- deconv2_2x
I0605 23:00:05.855870 54715 net.cpp:397] scale_deconv2_2x -> deconv2_2x (in-place)
I0605 23:00:05.855928 54715 layer_factory.hpp:77] Creating layer scale_deconv2_2x
I0605 23:00:05.856233 54715 net.cpp:150] Setting up scale_deconv2_2x
I0605 23:00:05.856246 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.856251 54715 net.cpp:165] Memory required for data: 2108044800
I0605 23:00:05.856257 54715 layer_factory.hpp:77] Creating layer relu_deconv2_2x
I0605 23:00:05.856266 54715 net.cpp:106] Creating Layer relu_deconv2_2x
I0605 23:00:05.856271 54715 net.cpp:454] relu_deconv2_2x <- deconv2_2x
I0605 23:00:05.856276 54715 net.cpp:397] relu_deconv2_2x -> deconv2_2x (in-place)
I0605 23:00:05.856283 54715 net.cpp:150] Setting up relu_deconv2_2x
I0605 23:00:05.856289 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.856293 54715 net.cpp:165] Memory required for data: 2109683200
I0605 23:00:05.856297 54715 layer_factory.hpp:77] Creating layer conv_deconv5_16x
I0605 23:00:05.856307 54715 net.cpp:106] Creating Layer conv_deconv5_16x
I0605 23:00:05.856312 54715 net.cpp:454] conv_deconv5_16x <- deconv5_16x
I0605 23:00:05.856321 54715 net.cpp:411] conv_deconv5_16x -> conv_deconv5_16x
I0605 23:00:05.858067 54715 net.cpp:150] Setting up conv_deconv5_16x
I0605 23:00:05.858083 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.858088 54715 net.cpp:165] Memory required for data: 2111321600
I0605 23:00:05.858096 54715 layer_factory.hpp:77] Creating layer conv_deconv4_8x
I0605 23:00:05.858106 54715 net.cpp:106] Creating Layer conv_deconv4_8x
I0605 23:00:05.858112 54715 net.cpp:454] conv_deconv4_8x <- deconv4_8x
I0605 23:00:05.858121 54715 net.cpp:411] conv_deconv4_8x -> conv_deconv4_8x
I0605 23:00:05.858397 54715 net.cpp:150] Setting up conv_deconv4_8x
I0605 23:00:05.858407 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.858410 54715 net.cpp:165] Memory required for data: 2112960000
I0605 23:00:05.858418 54715 layer_factory.hpp:77] Creating layer conv_deconv3_4x
I0605 23:00:05.858428 54715 net.cpp:106] Creating Layer conv_deconv3_4x
I0605 23:00:05.858433 54715 net.cpp:454] conv_deconv3_4x <- deconv3_4x
I0605 23:00:05.858440 54715 net.cpp:411] conv_deconv3_4x -> conv_deconv3_4x
I0605 23:00:05.860052 54715 net.cpp:150] Setting up conv_deconv3_4x
I0605 23:00:05.860069 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.860074 54715 net.cpp:165] Memory required for data: 2114598400
I0605 23:00:05.860081 54715 layer_factory.hpp:77] Creating layer conv_deconv2_2x
I0605 23:00:05.860092 54715 net.cpp:106] Creating Layer conv_deconv2_2x
I0605 23:00:05.860098 54715 net.cpp:454] conv_deconv2_2x <- deconv2_2x
I0605 23:00:05.860106 54715 net.cpp:411] conv_deconv2_2x -> conv_deconv2_2x
I0605 23:00:05.860416 54715 net.cpp:150] Setting up conv_deconv2_2x
I0605 23:00:05.860430 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.860435 54715 net.cpp:165] Memory required for data: 2116236800
I0605 23:00:05.860440 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv5_16x
I0605 23:00:05.860448 54715 net.cpp:106] Creating Layer bn_conv_deconv5_16x
I0605 23:00:05.860455 54715 net.cpp:454] bn_conv_deconv5_16x <- conv_deconv5_16x
I0605 23:00:05.860467 54715 net.cpp:397] bn_conv_deconv5_16x -> conv_deconv5_16x (in-place)
I0605 23:00:05.860703 54715 net.cpp:150] Setting up bn_conv_deconv5_16x
I0605 23:00:05.860713 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.860716 54715 net.cpp:165] Memory required for data: 2117875200
I0605 23:00:05.860725 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv5_16x
I0605 23:00:05.860733 54715 net.cpp:106] Creating Layer scale_conv_deconv5_16x
I0605 23:00:05.860738 54715 net.cpp:454] scale_conv_deconv5_16x <- conv_deconv5_16x
I0605 23:00:05.860744 54715 net.cpp:397] scale_conv_deconv5_16x -> conv_deconv5_16x (in-place)
I0605 23:00:05.860785 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv5_16x
I0605 23:00:05.861011 54715 net.cpp:150] Setting up scale_conv_deconv5_16x
I0605 23:00:05.861021 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.861026 54715 net.cpp:165] Memory required for data: 2119513600
I0605 23:00:05.861032 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv5_16x
I0605 23:00:05.861040 54715 net.cpp:106] Creating Layer relu_conv_deconv5_16x
I0605 23:00:05.861044 54715 net.cpp:454] relu_conv_deconv5_16x <- conv_deconv5_16x
I0605 23:00:05.861052 54715 net.cpp:397] relu_conv_deconv5_16x -> conv_deconv5_16x (in-place)
I0605 23:00:05.861059 54715 net.cpp:150] Setting up relu_conv_deconv5_16x
I0605 23:00:05.861064 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.861068 54715 net.cpp:165] Memory required for data: 2121152000
I0605 23:00:05.861073 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv4_8x
I0605 23:00:05.861079 54715 net.cpp:106] Creating Layer bn_conv_deconv4_8x
I0605 23:00:05.861084 54715 net.cpp:454] bn_conv_deconv4_8x <- conv_deconv4_8x
I0605 23:00:05.861089 54715 net.cpp:397] bn_conv_deconv4_8x -> conv_deconv4_8x (in-place)
I0605 23:00:05.862686 54715 net.cpp:150] Setting up bn_conv_deconv4_8x
I0605 23:00:05.862701 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.862706 54715 net.cpp:165] Memory required for data: 2122790400
I0605 23:00:05.862715 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv4_8x
I0605 23:00:05.862725 54715 net.cpp:106] Creating Layer scale_conv_deconv4_8x
I0605 23:00:05.862730 54715 net.cpp:454] scale_conv_deconv4_8x <- conv_deconv4_8x
I0605 23:00:05.862738 54715 net.cpp:397] scale_conv_deconv4_8x -> conv_deconv4_8x (in-place)
I0605 23:00:05.862777 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv4_8x
I0605 23:00:05.863003 54715 net.cpp:150] Setting up scale_conv_deconv4_8x
I0605 23:00:05.863013 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.863018 54715 net.cpp:165] Memory required for data: 2124428800
I0605 23:00:05.863023 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv4_8x
I0605 23:00:05.863031 54715 net.cpp:106] Creating Layer relu_conv_deconv4_8x
I0605 23:00:05.863036 54715 net.cpp:454] relu_conv_deconv4_8x <- conv_deconv4_8x
I0605 23:00:05.863044 54715 net.cpp:397] relu_conv_deconv4_8x -> conv_deconv4_8x (in-place)
I0605 23:00:05.863049 54715 net.cpp:150] Setting up relu_conv_deconv4_8x
I0605 23:00:05.863055 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.863059 54715 net.cpp:165] Memory required for data: 2126067200
I0605 23:00:05.863063 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv3_4x
I0605 23:00:05.863070 54715 net.cpp:106] Creating Layer bn_conv_deconv3_4x
I0605 23:00:05.863075 54715 net.cpp:454] bn_conv_deconv3_4x <- conv_deconv3_4x
I0605 23:00:05.863082 54715 net.cpp:397] bn_conv_deconv3_4x -> conv_deconv3_4x (in-place)
I0605 23:00:05.863306 54715 net.cpp:150] Setting up bn_conv_deconv3_4x
I0605 23:00:05.863314 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.863318 54715 net.cpp:165] Memory required for data: 2127705600
I0605 23:00:05.863327 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv3_4x
I0605 23:00:05.863334 54715 net.cpp:106] Creating Layer scale_conv_deconv3_4x
I0605 23:00:05.863338 54715 net.cpp:454] scale_conv_deconv3_4x <- conv_deconv3_4x
I0605 23:00:05.863351 54715 net.cpp:397] scale_conv_deconv3_4x -> conv_deconv3_4x (in-place)
I0605 23:00:05.863395 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv3_4x
I0605 23:00:05.865006 54715 net.cpp:150] Setting up scale_conv_deconv3_4x
I0605 23:00:05.865023 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865028 54715 net.cpp:165] Memory required for data: 2129344000
I0605 23:00:05.865037 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv3_4x
I0605 23:00:05.865046 54715 net.cpp:106] Creating Layer relu_conv_deconv3_4x
I0605 23:00:05.865051 54715 net.cpp:454] relu_conv_deconv3_4x <- conv_deconv3_4x
I0605 23:00:05.865058 54715 net.cpp:397] relu_conv_deconv3_4x -> conv_deconv3_4x (in-place)
I0605 23:00:05.865067 54715 net.cpp:150] Setting up relu_conv_deconv3_4x
I0605 23:00:05.865072 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865077 54715 net.cpp:165] Memory required for data: 2130982400
I0605 23:00:05.865080 54715 layer_factory.hpp:77] Creating layer bn_conv_deconv2_2x
I0605 23:00:05.865088 54715 net.cpp:106] Creating Layer bn_conv_deconv2_2x
I0605 23:00:05.865092 54715 net.cpp:454] bn_conv_deconv2_2x <- conv_deconv2_2x
I0605 23:00:05.865098 54715 net.cpp:397] bn_conv_deconv2_2x -> conv_deconv2_2x (in-place)
I0605 23:00:05.865337 54715 net.cpp:150] Setting up bn_conv_deconv2_2x
I0605 23:00:05.865346 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865350 54715 net.cpp:165] Memory required for data: 2132620800
I0605 23:00:05.865360 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv2_2x
I0605 23:00:05.865367 54715 net.cpp:106] Creating Layer scale_conv_deconv2_2x
I0605 23:00:05.865372 54715 net.cpp:454] scale_conv_deconv2_2x <- conv_deconv2_2x
I0605 23:00:05.865378 54715 net.cpp:397] scale_conv_deconv2_2x -> conv_deconv2_2x (in-place)
I0605 23:00:05.865414 54715 layer_factory.hpp:77] Creating layer scale_conv_deconv2_2x
I0605 23:00:05.865641 54715 net.cpp:150] Setting up scale_conv_deconv2_2x
I0605 23:00:05.865651 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865655 54715 net.cpp:165] Memory required for data: 2134259200
I0605 23:00:05.865662 54715 layer_factory.hpp:77] Creating layer relu_conv_deconv2_2x
I0605 23:00:05.865669 54715 net.cpp:106] Creating Layer relu_conv_deconv2_2x
I0605 23:00:05.865674 54715 net.cpp:454] relu_conv_deconv2_2x <- conv_deconv2_2x
I0605 23:00:05.865681 54715 net.cpp:397] relu_conv_deconv2_2x -> conv_deconv2_2x (in-place)
I0605 23:00:05.865687 54715 net.cpp:150] Setting up relu_conv_deconv2_2x
I0605 23:00:05.865694 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865698 54715 net.cpp:165] Memory required for data: 2135897600
I0605 23:00:05.865702 54715 layer_factory.hpp:77] Creating layer deconv_all_sum
I0605 23:00:05.865710 54715 net.cpp:106] Creating Layer deconv_all_sum
I0605 23:00:05.865715 54715 net.cpp:454] deconv_all_sum <- conv_deconv2_2x
I0605 23:00:05.865720 54715 net.cpp:454] deconv_all_sum <- conv_deconv3_4x
I0605 23:00:05.865725 54715 net.cpp:454] deconv_all_sum <- conv_deconv4_8x
I0605 23:00:05.865731 54715 net.cpp:454] deconv_all_sum <- conv_deconv5_16x
I0605 23:00:05.865736 54715 net.cpp:411] deconv_all_sum -> deconv_all_sum
I0605 23:00:05.865764 54715 net.cpp:150] Setting up deconv_all_sum
I0605 23:00:05.865772 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865775 54715 net.cpp:165] Memory required for data: 2137536000
I0605 23:00:05.865779 54715 layer_factory.hpp:77] Creating layer deconv_all_sum_deconv_all_sum_0_split
I0605 23:00:05.865787 54715 net.cpp:106] Creating Layer deconv_all_sum_deconv_all_sum_0_split
I0605 23:00:05.865792 54715 net.cpp:454] deconv_all_sum_deconv_all_sum_0_split <- deconv_all_sum
I0605 23:00:05.865799 54715 net.cpp:411] deconv_all_sum_deconv_all_sum_0_split -> deconv_all_sum_deconv_all_sum_0_split_0
I0605 23:00:05.865808 54715 net.cpp:411] deconv_all_sum_deconv_all_sum_0_split -> deconv_all_sum_deconv_all_sum_0_split_1
I0605 23:00:05.865841 54715 net.cpp:150] Setting up deconv_all_sum_deconv_all_sum_0_split
I0605 23:00:05.865857 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865869 54715 net.cpp:157] Top shape: 2 2 320 320 (409600)
I0605 23:00:05.865875 54715 net.cpp:165] Memory required for data: 2140812800
I0605 23:00:05.865880 54715 layer_factory.hpp:77] Creating layer loss_deconv_all
I0605 23:00:05.865887 54715 net.cpp:106] Creating Layer loss_deconv_all
I0605 23:00:05.865892 54715 net.cpp:454] loss_deconv_all <- deconv_all_sum_deconv_all_sum_0_split_0
I0605 23:00:05.865898 54715 net.cpp:454] loss_deconv_all <- label_reshape_0_split_0
I0605 23:00:05.865907 54715 net.cpp:411] loss_deconv_all -> loss_deconv_all
I0605 23:00:05.865917 54715 layer_factory.hpp:77] Creating layer loss_deconv_all
I0605 23:00:05.867640 54715 sample_selector.cpp:58] read prob from file : label_class_selection.prototxt
I0605 23:00:05.867707 54715 sample_selector.cpp:78] rest_of_label_mapping_ = 0 1
I0605 23:00:05.867718 54715 sample_selector.cpp:93] label map :0--->0
I0605 23:00:05.867723 54715 sample_selector.cpp:93] label map :1--->1
I0605 23:00:05.867727 54715 sample_selector.cpp:95] label_prob_map_ size =2
I0605 23:00:05.867734 54715 sample_selector.cpp:116] scale_factor = 3.33333
I0605 23:00:05.867748 54715 sample_selector.cpp:117] bottom_prob = 0.3
I0605 23:00:05.867753 54715 sample_selector.cpp:118] label_prob_vec.size = 2
I0605 23:00:05.867756 54715 sample_selector.cpp:164] size of prob = 1
I0605 23:00:05.867763 54715 sample_selector.cpp:19] lable class [0] weight =0.25
I0605 23:00:05.867769 54715 sample_selector.cpp:19] lable class [1] weight =1
I0605 23:00:05.867794 54715 net.cpp:150] Setting up loss_deconv_all
I0605 23:00:05.867802 54715 net.cpp:157] Top shape: (1)
I0605 23:00:05.867806 54715 net.cpp:160] with loss weight 1
I0605 23:00:05.867812 54715 net.cpp:165] Memory required for data: 2140812804
I0605 23:00:05.867817 54715 layer_factory.hpp:77] Creating layer accuracy_conv
I0605 23:00:05.867827 54715 net.cpp:106] Creating Layer accuracy_conv
I0605 23:00:05.867832 54715 net.cpp:454] accuracy_conv <- deconv_all_sum_deconv_all_sum_0_split_1
I0605 23:00:05.867839 54715 net.cpp:454] accuracy_conv <- label_reshape_0_split_1
I0605 23:00:05.867847 54715 net.cpp:411] accuracy_conv -> accuracy_conv
I0605 23:00:05.867856 54715 net.cpp:411] accuracy_conv -> class_Acc
I0605 23:00:05.867893 54715 net.cpp:150] Setting up accuracy_conv
I0605 23:00:05.867899 54715 net.cpp:157] Top shape: (1)
I0605 23:00:05.867904 54715 net.cpp:157] Top shape: 2 (2)
I0605 23:00:05.867908 54715 net.cpp:165] Memory required for data: 2140812816
I0605 23:00:05.867913 54715 net.cpp:228] accuracy_conv does not need backward computation.
I0605 23:00:05.867919 54715 net.cpp:226] loss_deconv_all needs backward computation.
I0605 23:00:05.867924 54715 net.cpp:226] deconv_all_sum_deconv_all_sum_0_split needs backward computation.
I0605 23:00:05.867928 54715 net.cpp:226] deconv_all_sum needs backward computation.
I0605 23:00:05.867934 54715 net.cpp:226] relu_conv_deconv2_2x needs backward computation.
I0605 23:00:05.867939 54715 net.cpp:226] scale_conv_deconv2_2x needs backward computation.
I0605 23:00:05.867944 54715 net.cpp:226] bn_conv_deconv2_2x needs backward computation.
I0605 23:00:05.867947 54715 net.cpp:226] relu_conv_deconv3_4x needs backward computation.
I0605 23:00:05.867951 54715 net.cpp:226] scale_conv_deconv3_4x needs backward computation.
I0605 23:00:05.867955 54715 net.cpp:226] bn_conv_deconv3_4x needs backward computation.
I0605 23:00:05.867959 54715 net.cpp:226] relu_conv_deconv4_8x needs backward computation.
I0605 23:00:05.867964 54715 net.cpp:226] scale_conv_deconv4_8x needs backward computation.
I0605 23:00:05.867969 54715 net.cpp:226] bn_conv_deconv4_8x needs backward computation.
I0605 23:00:05.867972 54715 net.cpp:226] relu_conv_deconv5_16x needs backward computation.
I0605 23:00:05.867976 54715 net.cpp:226] scale_conv_deconv5_16x needs backward computation.
I0605 23:00:05.867980 54715 net.cpp:226] bn_conv_deconv5_16x needs backward computation.
I0605 23:00:05.867985 54715 net.cpp:226] conv_deconv2_2x needs backward computation.
I0605 23:00:05.868000 54715 net.cpp:226] conv_deconv3_4x needs backward computation.
I0605 23:00:05.868006 54715 net.cpp:226] conv_deconv4_8x needs backward computation.
I0605 23:00:05.868010 54715 net.cpp:226] conv_deconv5_16x needs backward computation.
I0605 23:00:05.868016 54715 net.cpp:226] relu_deconv2_2x needs backward computation.
I0605 23:00:05.868021 54715 net.cpp:226] scale_deconv2_2x needs backward computation.
I0605 23:00:05.868024 54715 net.cpp:226] bn_deconv2_2x needs backward computation.
I0605 23:00:05.868027 54715 net.cpp:226] relu_deconv3_4x needs backward computation.
I0605 23:00:05.868032 54715 net.cpp:226] scale_deconv3_4x needs backward computation.
I0605 23:00:05.868036 54715 net.cpp:226] bn_deconv3_4x needs backward computation.
I0605 23:00:05.868041 54715 net.cpp:226] relu_deconv4_8x needs backward computation.
I0605 23:00:05.868044 54715 net.cpp:226] scale_deconv4_8x needs backward computation.
I0605 23:00:05.868048 54715 net.cpp:226] bn_deconv4_8x needs backward computation.
I0605 23:00:05.868053 54715 net.cpp:226] relu_deconv5_16x needs backward computation.
I0605 23:00:05.868057 54715 net.cpp:226] scale_deconv5_16x needs backward computation.
I0605 23:00:05.868062 54715 net.cpp:226] bn_deconv5_16x needs backward computation.
I0605 23:00:05.868067 54715 net.cpp:226] fc1_8x needs backward computation.
I0605 23:00:05.868072 54715 net.cpp:226] fc1_8x_c3 needs backward computation.
I0605 23:00:05.868077 54715 net.cpp:226] fc1_8x_c2 needs backward computation.
I0605 23:00:05.868082 54715 net.cpp:226] fc1_8x_c1 needs backward computation.
I0605 23:00:05.868086 54715 net.cpp:226] fc1_8x_c0 needs backward computation.
I0605 23:00:05.868091 54715 net.cpp:226] deconv4_8x_d1 needs backward computation.
I0605 23:00:05.868096 54715 net.cpp:226] fc1_4x needs backward computation.
I0605 23:00:05.868101 54715 net.cpp:226] fc1_4x_c3 needs backward computation.
I0605 23:00:05.868106 54715 net.cpp:226] fc1_4x_c2 needs backward computation.
I0605 23:00:05.868113 54715 net.cpp:226] fc1_4x_c1 needs backward computation.
I0605 23:00:05.868116 54715 net.cpp:226] deconv3_4x_d1 needs backward computation.
I0605 23:00:05.868121 54715 net.cpp:226] fc1_4x_c0 needs backward computation.
I0605 23:00:05.868126 54715 net.cpp:226] fc1_2x needs backward computation.
I0605 23:00:05.868132 54715 net.cpp:226] fc1_2x_c3 needs backward computation.
I0605 23:00:05.868137 54715 net.cpp:226] fc1_2x_c2 needs backward computation.
I0605 23:00:05.868167 54715 net.cpp:226] fc1_2x_c1 needs backward computation.
I0605 23:00:05.868173 54715 net.cpp:226] fc1_2x_c0 needs backward computation.
I0605 23:00:05.868178 54715 net.cpp:226] deconv2_2x_d1 needs backward computation.
I0605 23:00:05.868183 54715 net.cpp:226] deconv5_16x needs backward computation.
I0605 23:00:05.868188 54715 net.cpp:226] relu_conv5_sum needs backward computation.
I0605 23:00:05.868193 54715 net.cpp:226] conv5_sum needs backward computation.
I0605 23:00:05.868199 54715 net.cpp:226] scale_ira_Inception_C_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:05.868203 54715 net.cpp:226] bn_ira_Inception_C_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:05.868208 54715 net.cpp:226] ira_Inception_C_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:05.868213 54715 net.cpp:226] ira_Inception_C_block_1/concat needs backward computation.
I0605 23:00:05.868219 54715 net.cpp:226] relu_ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868223 54715 net.cpp:226] scale_ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868228 54715 net.cpp:226] bn_ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868232 54715 net.cpp:226] ira_Inception_C_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868238 54715 net.cpp:226] relu_ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868242 54715 net.cpp:226] scale_ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868247 54715 net.cpp:226] bn_ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868260 54715 net.cpp:226] ira_Inception_C_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868266 54715 net.cpp:226] relu_ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868270 54715 net.cpp:226] scale_ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868274 54715 net.cpp:226] bn_ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868279 54715 net.cpp:226] ira_Inception_C_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868284 54715 net.cpp:226] relu_ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868289 54715 net.cpp:226] scale_ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868294 54715 net.cpp:226] bn_ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868299 54715 net.cpp:226] ira_Inception_C_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868304 54715 net.cpp:226] conv5_1b_relu5_1b_0_split needs backward computation.
I0605 23:00:05.868309 54715 net.cpp:226] relu5_1b needs backward computation.
I0605 23:00:05.868312 54715 net.cpp:226] scale_conv5_1b needs backward computation.
I0605 23:00:05.868317 54715 net.cpp:226] bn_conv5_1b needs backward computation.
I0605 23:00:05.868321 54715 net.cpp:226] conv5_1b needs backward computation.
I0605 23:00:05.868326 54715 net.cpp:226] ira_Reduction_B_block_1/concat needs backward computation.
I0605 23:00:05.868332 54715 net.cpp:226] relu_ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:05.868337 54715 net.cpp:226] scale_ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:05.868342 54715 net.cpp:226] bn_ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:05.868346 54715 net.cpp:226] ira_Reduction_B_block_1/d_conv3x3_2 needs backward computation.
I0605 23:00:05.868351 54715 net.cpp:226] relu_ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:05.868356 54715 net.cpp:226] scale_ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:05.868360 54715 net.cpp:226] bn_ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:05.868366 54715 net.cpp:226] ira_Reduction_B_block_1/d_conv3x3_1 needs backward computation.
I0605 23:00:05.868369 54715 net.cpp:226] relu_ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:05.868374 54715 net.cpp:226] scale_ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:05.868379 54715 net.cpp:226] bn_ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:05.868383 54715 net.cpp:226] ira_Reduction_B_block_1/d_conv1x1_1 needs backward computation.
I0605 23:00:05.868388 54715 net.cpp:226] relu_ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:05.868393 54715 net.cpp:226] scale_ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:05.868397 54715 net.cpp:226] bn_ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:05.868402 54715 net.cpp:226] ira_Reduction_B_block_1/c_conv3x3_1 needs backward computation.
I0605 23:00:05.868407 54715 net.cpp:226] relu_ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:05.868412 54715 net.cpp:226] scale_ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:05.868417 54715 net.cpp:226] bn_ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:05.868422 54715 net.cpp:226] ira_Reduction_B_block_1/c_conv1x1_1 needs backward computation.
I0605 23:00:05.868425 54715 net.cpp:226] relu_ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:05.868430 54715 net.cpp:226] scale_ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:05.868435 54715 net.cpp:226] bn_ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:05.868439 54715 net.cpp:226] ira_Reduction_B_block_1/b_conv3x3_1 needs backward computation.
I0605 23:00:05.868450 54715 net.cpp:226] relu_ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868456 54715 net.cpp:226] scale_ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868461 54715 net.cpp:226] bn_ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868465 54715 net.cpp:226] ira_Reduction_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868470 54715 net.cpp:226] ira_Reduction_B_block_1/a_pool needs backward computation.
I0605 23:00:05.868475 54715 net.cpp:226] conv4_sum_relu_conv4_sum_0_split needs backward computation.
I0605 23:00:05.868480 54715 net.cpp:226] relu_conv4_sum needs backward computation.
I0605 23:00:05.868485 54715 net.cpp:226] conv4_sum needs backward computation.
I0605 23:00:05.868490 54715 net.cpp:226] scale_ira_Inception_B_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:05.868495 54715 net.cpp:226] bn_ira_Inception_B_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:05.868501 54715 net.cpp:226] ira_Inception_B_block_1/top_conv_1x1 needs backward computation.
I0605 23:00:05.868505 54715 net.cpp:226] ira_Inception_B_block_1/concat needs backward computation.
I0605 23:00:05.868510 54715 net.cpp:226] relu_ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868515 54715 net.cpp:226] scale_ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868520 54715 net.cpp:226] bn_ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868525 54715 net.cpp:226] ira_Inception_B_block_1/b_conv7x1_1 needs backward computation.
I0605 23:00:05.868530 54715 net.cpp:226] relu_ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868533 54715 net.cpp:226] scale_ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868538 54715 net.cpp:226] bn_ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868542 54715 net.cpp:226] ira_Inception_B_block_1/b_conv1x7_1 needs backward computation.
I0605 23:00:05.868547 54715 net.cpp:226] relu_ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868551 54715 net.cpp:226] scale_ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868556 54715 net.cpp:226] bn_ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868561 54715 net.cpp:226] ira_Inception_B_block_1/b_conv1x1_1 needs backward computation.
I0605 23:00:05.868566 54715 net.cpp:226] relu_ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868571 54715 net.cpp:226] scale_ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868576 54715 net.cpp:226] bn_ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868580 54715 net.cpp:226] ira_Inception_B_block_1/a_conv1x1_1 needs backward computation.
I0605 23:00:05.868585 54715 net.cpp:226] conv4_1b_relu4_1b_0_split needs backward computation.
I0605 23:00:05.868592 54715 net.cpp:226] relu4_1b needs backward computation.
I0605 23:00:05.868597 54715 net.cpp:226] scale_conv4_1b needs backward computation.
I0605 23:00:05.868600 54715 net.cpp:226] bn_conv4_1b needs backward computation.
I0605 23:00:05.868604 54715 net.cpp:226] conv4_1b needs backward computation.
I0605 23:00:05.868609 54715 net.cpp:226] ira_v4_reduction_A/concat needs backward computation.
I0605 23:00:05.868616 54715 net.cpp:226] relu_ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:05.868620 54715 net.cpp:226] scale_ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:05.868624 54715 net.cpp:226] bn_ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:05.868629 54715 net.cpp:226] ira_v4_reduction_A/conv3x3_reduction_c needs backward computation.
I0605 23:00:05.868634 54715 net.cpp:226] relu_ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:05.868643 54715 net.cpp:226] scale_ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:05.868652 54715 net.cpp:226] bn_ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:05.868657 54715 net.cpp:226] ira_v4_reduction_A/conv3x3_c needs backward computation.
I0605 23:00:05.868662 54715 net.cpp:226] relu_ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:05.868667 54715 net.cpp:226] scale_ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:05.868671 54715 net.cpp:226] bn_ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:05.868676 54715 net.cpp:226] ira_v4_reduction_A/conv1x1_c needs backward computation.
I0605 23:00:05.868682 54715 net.cpp:226] relu_ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:05.868686 54715 net.cpp:226] scale_ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:05.868691 54715 net.cpp:226] bn_ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:05.868696 54715 net.cpp:226] ira_v4_reduction_A/conv3x3_reduction_b needs backward computation.
I0605 23:00:05.868701 54715 net.cpp:226] ira_v4_reduction_A/pool needs backward computation.
I0605 23:00:05.868706 54715 net.cpp:226] conv3_sum_relu3_sum_0_split needs backward computation.
I0605 23:00:05.868711 54715 net.cpp:226] relu3_sum needs backward computation.
I0605 23:00:05.868716 54715 net.cpp:226] conv3_sum needs backward computation.
I0605 23:00:05.868722 54715 net.cpp:226] scale_ra_A_concat_top_conv_1x1 needs backward computation.
I0605 23:00:05.868726 54715 net.cpp:226] bn_ra_A_concat_top_conv_1x1 needs backward computation.
I0605 23:00:05.868731 54715 net.cpp:226] ira_A_concat_top_conv_1x1 needs backward computation.
I0605 23:00:05.868736 54715 net.cpp:226] ira_A_concat needs backward computation.
I0605 23:00:05.868742 54715 net.cpp:226] relu_ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:05.868746 54715 net.cpp:226] scale_ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:05.868752 54715 net.cpp:226] bn_ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:05.868755 54715 net.cpp:226] ira_A_3_conv3x3_2 needs backward computation.
I0605 23:00:05.868760 54715 net.cpp:226] relu_ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:05.868764 54715 net.cpp:226] scale_ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:05.868769 54715 net.cpp:226] bn_ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:05.868774 54715 net.cpp:226] ira_A_3_conv3x3_1 needs backward computation.
I0605 23:00:05.868779 54715 net.cpp:226] relu_ira_A_3_conv1x1 needs backward computation.
I0605 23:00:05.868783 54715 net.cpp:226] scale_ira_A_3_conv1x1 needs backward computation.
I0605 23:00:05.868788 54715 net.cpp:226] bn_ira_A_3_conv1x1 needs backward computation.
I0605 23:00:05.868793 54715 net.cpp:226] ira_A_3_conv1x1 needs backward computation.
I0605 23:00:05.868798 54715 net.cpp:226] relu_ira_A_2_conv3x3 needs backward computation.
I0605 23:00:05.868803 54715 net.cpp:226] scale_ira_A_2_conv3x3 needs backward computation.
I0605 23:00:05.868808 54715 net.cpp:226] bn_ira_A_2_conv3x3 needs backward computation.
I0605 23:00:05.868813 54715 net.cpp:226] ira_A_2_conv3x3 needs backward computation.
I0605 23:00:05.868818 54715 net.cpp:226] relu_ira_A_2_conv1x1 needs backward computation.
I0605 23:00:05.868821 54715 net.cpp:226] scale_ira_A_2_conv1x1 needs backward computation.
I0605 23:00:05.868825 54715 net.cpp:226] bn_ira_A_2_conv1x1 needs backward computation.
I0605 23:00:05.868830 54715 net.cpp:226] ira_A_2_conv1x1 needs backward computation.
I0605 23:00:05.868835 54715 net.cpp:226] relu_ira_A_1_conv1x1 needs backward computation.
I0605 23:00:05.868840 54715 net.cpp:226] scale_ira_A_1_conv1x1 needs backward computation.
I0605 23:00:05.868844 54715 net.cpp:226] bn_ira_A_1_conv1x1 needs backward computation.
I0605 23:00:05.868849 54715 net.cpp:226] ira_A_1_conv1x1 needs backward computation.
I0605 23:00:05.868854 54715 net.cpp:226] conv3_1b_relu3_1b_0_split needs backward computation.
I0605 23:00:05.868862 54715 net.cpp:226] relu3_1b needs backward computation.
I0605 23:00:05.868871 54715 net.cpp:226] scale_conv3_1b needs backward computation.
I0605 23:00:05.868876 54715 net.cpp:226] bn_conv3_1b needs backward computation.
I0605 23:00:05.868881 54715 net.cpp:226] conv3_1b needs backward computation.
I0605 23:00:05.868886 54715 net.cpp:226] concat_stem_2 needs backward computation.
I0605 23:00:05.868891 54715 net.cpp:226] pool_stem_concat needs backward computation.
I0605 23:00:05.868896 54715 net.cpp:226] relu_stem_concat_conv_3x3 needs backward computation.
I0605 23:00:05.868902 54715 net.cpp:226] scale_stem_concat_conv_3x3 needs backward computation.
I0605 23:00:05.868906 54715 net.cpp:226] bn_stem_concat_conv_3x3 needs backward computation.
I0605 23:00:05.868911 54715 net.cpp:226] stem_concat_conv_3x3 needs backward computation.
I0605 23:00:05.868916 54715 net.cpp:226] concat_stem_1_concat_stem_1_0_split needs backward computation.
I0605 23:00:05.868921 54715 net.cpp:226] concat_stem_1 needs backward computation.
I0605 23:00:05.868927 54715 net.cpp:226] relu2_3x3 needs backward computation.
I0605 23:00:05.868932 54715 net.cpp:226] scale_conv2_3x3 needs backward computation.
I0605 23:00:05.868935 54715 net.cpp:226] bn_conv2_3x3 needs backward computation.
I0605 23:00:05.868940 54715 net.cpp:226] conv2_3x3 needs backward computation.
I0605 23:00:05.868944 54715 net.cpp:226] relu2_7x1 needs backward computation.
I0605 23:00:05.868949 54715 net.cpp:226] scale_conv2_7x1 needs backward computation.
I0605 23:00:05.868954 54715 net.cpp:226] bn_conv2_7x1 needs backward computation.
I0605 23:00:05.868959 54715 net.cpp:226] conv2_7x1 needs backward computation.
I0605 23:00:05.868963 54715 net.cpp:226] relu2_1x7 needs backward computation.
I0605 23:00:05.868968 54715 net.cpp:226] scale_conv2_1x7 needs backward computation.
I0605 23:00:05.868973 54715 net.cpp:226] bn_conv2_1x7 needs backward computation.
I0605 23:00:05.868976 54715 net.cpp:226] conv2_1x7 needs backward computation.
I0605 23:00:05.868980 54715 net.cpp:226] relu2_1x1 needs backward computation.
I0605 23:00:05.868985 54715 net.cpp:226] scale_conv2_1x1 needs backward computation.
I0605 23:00:05.868989 54715 net.cpp:226] bn_conv2_1x1 needs backward computation.
I0605 23:00:05.868994 54715 net.cpp:226] conv2_1x1 needs backward computation.
I0605 23:00:05.868999 54715 net.cpp:226] scale_conv2_1b_3x3 needs backward computation.
I0605 23:00:05.869004 54715 net.cpp:226] bn_conv2_1b_3x3 needs backward computation.
I0605 23:00:05.869009 54715 net.cpp:226] conv2_1b_3x3 needs backward computation.
I0605 23:00:05.869012 54715 net.cpp:226] relu2_1b needs backward computation.
I0605 23:00:05.869017 54715 net.cpp:226] scale_conv2_1b needs backward computation.
I0605 23:00:05.869021 54715 net.cpp:226] bn_conv2_1b needs backward computation.
I0605 23:00:05.869026 54715 net.cpp:226] conv2_1b needs backward computation.
I0605 23:00:05.869032 54715 net.cpp:228] label_reshape_0_split does not need backward computation.
I0605 23:00:05.869037 54715 net.cpp:228] reshape does not need backward computation.
I0605 23:00:05.869041 54715 net.cpp:226] conv1_2_reshape_0_split needs backward computation.
I0605 23:00:05.869048 54715 net.cpp:226] reshape needs backward computation.
I0605 23:00:05.869053 54715 net.cpp:226] relu1_2 needs backward computation.
I0605 23:00:05.869057 54715 net.cpp:226] scale_conv1_2 needs backward computation.
I0605 23:00:05.869061 54715 net.cpp:226] bn_conv1_2 needs backward computation.
I0605 23:00:05.869066 54715 net.cpp:226] conv1_2 needs backward computation.
I0605 23:00:05.869071 54715 net.cpp:226] relu1_1 needs backward computation.
I0605 23:00:05.869076 54715 net.cpp:226] scale_conv1_1 needs backward computation.
I0605 23:00:05.869079 54715 net.cpp:226] bn_conv1_1 needs backward computation.
I0605 23:00:05.869084 54715 net.cpp:226] conv1_1 needs backward computation.
I0605 23:00:05.869089 54715 net.cpp:228] data does not need backward computation.
I0605 23:00:05.869093 54715 net.cpp:270] This network produces output accuracy_conv
I0605 23:00:05.869102 54715 net.cpp:270] This network produces output class_Acc
I0605 23:00:05.869112 54715 net.cpp:270] This network produces output loss_deconv_all
I0605 23:00:05.869257 54715 net.cpp:283] Network initialization done.
I0605 23:00:05.869851 54715 solver.cpp:60] Solver scaffolding done.
I0605 23:00:05.880543 54715 caffe.cpp:214] Starting Optimization
I0605 23:00:05.880555 54715 solver.cpp:288] Solving
I0605 23:00:05.880560 54715 solver.cpp:289] Learning Rate Policy: poly
I0605 23:00:05.903295 54715 solver.cpp:341] Iteration 0, Testing net (#0)
I0605 23:00:07.397783 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.296045
I0605 23:00:07.397828 54715 solver.cpp:409] Test net output #1: class_Acc = 0
I0605 23:00:07.397835 54715 solver.cpp:409] Test net output #2: class_Acc = 1
I0605 23:00:07.397847 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 87.3365 (* 1 = 87.3365 loss)
I0605 23:00:10.644413 54715 solver.cpp:237] Iteration 0, loss = 0.799057
I0605 23:00:10.644466 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.77411 (* 1 = 0.77411 loss)
I0605 23:00:10.644485 54715 sgd_solver.cpp:106] Iteration 0, lr = 0.01
I0605 23:00:20.056955 54715 solver.cpp:237] Iteration 3, loss = 1.05315
I0605 23:00:20.057103 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 1.00028 (* 1 = 1.00028 loss)
I0605 23:00:20.057116 54715 sgd_solver.cpp:106] Iteration 3, lr = 0.00999952
I0605 23:00:29.428508 54715 solver.cpp:237] Iteration 6, loss = 1.02582
I0605 23:00:29.428560 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 1.12069 (* 1 = 1.12069 loss)
I0605 23:00:29.428570 54715 sgd_solver.cpp:106] Iteration 6, lr = 0.00999904
I0605 23:00:38.799330 54715 solver.cpp:237] Iteration 9, loss = 0.983895
I0605 23:00:38.799383 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.631817 (* 1 = 0.631817 loss)
I0605 23:00:38.799394 54715 sgd_solver.cpp:106] Iteration 9, lr = 0.00999856
I0605 23:00:38.908877 54715 solver.cpp:341] Iteration 10, Testing net (#0)
I0605 23:00:40.186975 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.320941
I0605 23:00:40.187019 54715 solver.cpp:409] Test net output #1: class_Acc = 0.00126623
I0605 23:00:40.187026 54715 solver.cpp:409] Test net output #2: class_Acc = 0.999484
I0605 23:00:40.187037 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 42.9352 (* 1 = 42.9352 loss)
I0605 23:00:49.446295 54715 solver.cpp:237] Iteration 12, loss = 0.951686
I0605 23:00:49.446348 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.681332 (* 1 = 0.681332 loss)
I0605 23:00:49.446359 54715 sgd_solver.cpp:106] Iteration 12, lr = 0.00999808
I0605 23:00:58.818470 54715 solver.cpp:237] Iteration 15, loss = 0.920488
I0605 23:00:58.818604 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.949086 (* 1 = 0.949086 loss)
I0605 23:00:58.818619 54715 sgd_solver.cpp:106] Iteration 15, lr = 0.0099976
I0605 23:01:08.189049 54715 solver.cpp:237] Iteration 18, loss = 0.86329
I0605 23:01:08.189100 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.763923 (* 1 = 0.763923 loss)
I0605 23:01:08.189111 54715 sgd_solver.cpp:106] Iteration 18, lr = 0.00999712
I0605 23:01:11.422953 54715 solver.cpp:341] Iteration 20, Testing net (#0)
I0605 23:01:12.701784 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.327685
I0605 23:01:12.701831 54715 solver.cpp:409] Test net output #1: class_Acc = 0.0397163
I0605 23:01:12.701839 54715 solver.cpp:409] Test net output #2: class_Acc = 0.958302
I0605 23:01:12.701850 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 11.5041 (* 1 = 11.5041 loss)
I0605 23:01:18.839491 54715 solver.cpp:237] Iteration 21, loss = 0.82233
I0605 23:01:18.839543 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.655838 (* 1 = 0.655838 loss)
I0605 23:01:18.839555 54715 sgd_solver.cpp:106] Iteration 21, lr = 0.00999664
I0605 23:01:28.208827 54715 solver.cpp:237] Iteration 24, loss = 0.790932
I0605 23:01:28.208883 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.838271 (* 1 = 0.838271 loss)
I0605 23:01:28.208894 54715 sgd_solver.cpp:106] Iteration 24, lr = 0.00999616
I0605 23:01:37.580255 54715 solver.cpp:237] Iteration 27, loss = 0.758576
I0605 23:01:37.580440 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.524668 (* 1 = 0.524668 loss)
I0605 23:01:37.580453 54715 sgd_solver.cpp:106] Iteration 27, lr = 0.00999568
I0605 23:01:43.940940 54715 solver.cpp:341] Iteration 30, Testing net (#0)
I0605 23:01:45.219796 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.353909
I0605 23:01:45.219841 54715 solver.cpp:409] Test net output #1: class_Acc = 0.0693848
I0605 23:01:45.219848 54715 solver.cpp:409] Test net output #2: class_Acc = 0.936765
I0605 23:01:45.219859 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 9.47416 (* 1 = 9.47416 loss)
I0605 23:01:45.321434 54715 softmax_loss_layer.cu:194] weight loss 0 =0.343963 weight loss 1 =1 weight loss 2 =0
I0605 23:01:48.233050 54715 solver.cpp:237] Iteration 30, loss = 0.752785
I0605 23:01:48.233104 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.829022 (* 1 = 0.829022 loss)
I0605 23:01:48.233116 54715 sgd_solver.cpp:106] Iteration 30, lr = 0.0099952
I0605 23:01:57.605793 54715 solver.cpp:237] Iteration 33, loss = 0.74432
I0605 23:01:57.605844 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.676078 (* 1 = 0.676078 loss)
I0605 23:01:57.605854 54715 sgd_solver.cpp:106] Iteration 33, lr = 0.00999472
I0605 23:02:06.978408 54715 solver.cpp:237] Iteration 36, loss = 0.731353
I0605 23:02:06.978461 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.515855 (* 1 = 0.515855 loss)
I0605 23:02:06.978471 54715 sgd_solver.cpp:106] Iteration 36, lr = 0.00999424
I0605 23:02:16.349959 54715 solver.cpp:237] Iteration 39, loss = 0.717155
I0605 23:02:16.350066 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.512185 (* 1 = 0.512185 loss)
I0605 23:02:16.350078 54715 sgd_solver.cpp:106] Iteration 39, lr = 0.00999376
I0605 23:02:16.459687 54715 solver.cpp:341] Iteration 40, Testing net (#0)
I0605 23:02:17.738041 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.498358
I0605 23:02:17.738087 54715 solver.cpp:409] Test net output #1: class_Acc = 0.482458
I0605 23:02:17.738095 54715 solver.cpp:409] Test net output #2: class_Acc = 0.513953
I0605 23:02:17.738106 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 2.11004 (* 1 = 2.11004 loss)
I0605 23:02:26.998734 54715 solver.cpp:237] Iteration 42, loss = 0.706679
I0605 23:02:26.998785 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.543704 (* 1 = 0.543704 loss)
I0605 23:02:26.998795 54715 sgd_solver.cpp:106] Iteration 42, lr = 0.00999328
I0605 23:02:36.370563 54715 solver.cpp:237] Iteration 45, loss = 0.694478
I0605 23:02:36.370615 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.495351 (* 1 = 0.495351 loss)
I0605 23:02:36.370625 54715 sgd_solver.cpp:106] Iteration 45, lr = 0.0099928
I0605 23:02:45.744519 54715 solver.cpp:237] Iteration 48, loss = 0.683082
I0605 23:02:45.744570 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.735723 (* 1 = 0.735723 loss)
I0605 23:02:45.744580 54715 sgd_solver.cpp:106] Iteration 48, lr = 0.00999232
I0605 23:02:48.978497 54715 solver.cpp:341] Iteration 50, Testing net (#0)
I0605 23:02:50.257930 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.612194
I0605 23:02:50.257978 54715 solver.cpp:409] Test net output #1: class_Acc = 0.668245
I0605 23:02:50.257985 54715 solver.cpp:409] Test net output #2: class_Acc = 0.443657
I0605 23:02:50.257995 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 1.1527 (* 1 = 1.1527 loss)
I0605 23:02:56.398057 54715 solver.cpp:237] Iteration 51, loss = 0.675345
I0605 23:02:56.398108 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.754469 (* 1 = 0.754469 loss)
I0605 23:02:56.398119 54715 sgd_solver.cpp:106] Iteration 51, lr = 0.00999184
I0605 23:03:05.772231 54715 solver.cpp:237] Iteration 54, loss = 0.676911
I0605 23:03:05.772282 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.526864 (* 1 = 0.526864 loss)
I0605 23:03:05.772294 54715 sgd_solver.cpp:106] Iteration 54, lr = 0.00999136
I0605 23:03:15.142493 54715 solver.cpp:237] Iteration 57, loss = 0.677786
I0605 23:03:15.142544 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.776321 (* 1 = 0.776321 loss)
I0605 23:03:15.142555 54715 sgd_solver.cpp:106] Iteration 57, lr = 0.00999088
I0605 23:03:21.502090 54715 solver.cpp:341] Iteration 60, Testing net (#0)
I0605 23:03:22.785058 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.703807
I0605 23:03:22.785105 54715 solver.cpp:409] Test net output #1: class_Acc = 0.774373
I0605 23:03:22.785112 54715 solver.cpp:409] Test net output #2: class_Acc = 0.500021
I0605 23:03:22.785122 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.807287 (* 1 = 0.807287 loss)
I0605 23:03:25.798929 54715 solver.cpp:237] Iteration 60, loss = 0.675462
I0605 23:03:25.798977 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.477874 (* 1 = 0.477874 loss)
I0605 23:03:25.798988 54715 sgd_solver.cpp:106] Iteration 60, lr = 0.0099904
I0605 23:03:35.174589 54715 solver.cpp:237] Iteration 63, loss = 0.667065
I0605 23:03:35.174639 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.710081 (* 1 = 0.710081 loss)
I0605 23:03:35.174650 54715 sgd_solver.cpp:106] Iteration 63, lr = 0.00998992
I0605 23:03:44.547718 54715 solver.cpp:237] Iteration 66, loss = 0.661477
I0605 23:03:44.547767 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.768507 (* 1 = 0.768507 loss)
I0605 23:03:44.547778 54715 sgd_solver.cpp:106] Iteration 66, lr = 0.00998944
I0605 23:03:53.920846 54715 solver.cpp:237] Iteration 69, loss = 0.647901
I0605 23:03:53.920958 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.543998 (* 1 = 0.543998 loss)
I0605 23:03:53.920971 54715 sgd_solver.cpp:106] Iteration 69, lr = 0.00998896
I0605 23:03:54.030367 54715 solver.cpp:341] Iteration 70, Testing net (#0)
I0605 23:03:55.311962 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.720267
I0605 23:03:55.312008 54715 solver.cpp:409] Test net output #1: class_Acc = 0.782316
I0605 23:03:55.312016 54715 solver.cpp:409] Test net output #2: class_Acc = 0.578775
I0605 23:03:55.312026 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.628091 (* 1 = 0.628091 loss)
I0605 23:04:04.574960 54715 solver.cpp:237] Iteration 72, loss = 0.636962
I0605 23:04:04.575014 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.450282 (* 1 = 0.450282 loss)
I0605 23:04:04.575026 54715 sgd_solver.cpp:106] Iteration 72, lr = 0.00998848
I0605 23:04:13.951298 54715 solver.cpp:237] Iteration 75, loss = 0.621429
I0605 23:04:13.951349 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.565005 (* 1 = 0.565005 loss)
I0605 23:04:13.951360 54715 sgd_solver.cpp:106] Iteration 75, lr = 0.009988
I0605 23:04:23.327198 54715 solver.cpp:237] Iteration 78, loss = 0.625584
I0605 23:04:23.327247 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.755388 (* 1 = 0.755388 loss)
I0605 23:04:23.327258 54715 sgd_solver.cpp:106] Iteration 78, lr = 0.00998752
I0605 23:04:26.561692 54715 solver.cpp:341] Iteration 80, Testing net (#0)
I0605 23:04:27.843294 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.714088
I0605 23:04:27.843339 54715 solver.cpp:409] Test net output #1: class_Acc = 0.772391
I0605 23:04:27.843346 54715 solver.cpp:409] Test net output #2: class_Acc = 0.559617
I0605 23:04:27.843356 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.628931 (* 1 = 0.628931 loss)
I0605 23:04:33.982578 54715 solver.cpp:237] Iteration 81, loss = 0.618367
I0605 23:04:33.982621 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.573698 (* 1 = 0.573698 loss)
I0605 23:04:33.982632 54715 sgd_solver.cpp:106] Iteration 81, lr = 0.00998704
I0605 23:04:43.355633 54715 solver.cpp:237] Iteration 84, loss = 0.624201
I0605 23:04:43.355687 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.673287 (* 1 = 0.673287 loss)
I0605 23:04:43.355698 54715 sgd_solver.cpp:106] Iteration 84, lr = 0.00998656
I0605 23:04:52.732990 54715 solver.cpp:237] Iteration 87, loss = 0.621678
I0605 23:04:52.733038 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.458524 (* 1 = 0.458524 loss)
I0605 23:04:52.733050 54715 sgd_solver.cpp:106] Iteration 87, lr = 0.00998608
I0605 23:04:59.094130 54715 solver.cpp:341] Iteration 90, Testing net (#0)
I0605 23:05:00.374717 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.724358
I0605 23:05:00.374763 54715 solver.cpp:409] Test net output #1: class_Acc = 0.833502
I0605 23:05:00.374770 54715 solver.cpp:409] Test net output #2: class_Acc = 0.454427
I0605 23:05:00.374780 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.559474 (* 1 = 0.559474 loss)
I0605 23:05:03.390516 54715 solver.cpp:237] Iteration 90, loss = 0.618488
I0605 23:05:03.390563 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.548868 (* 1 = 0.548868 loss)
I0605 23:05:03.390575 54715 sgd_solver.cpp:106] Iteration 90, lr = 0.0099856
I0605 23:05:12.763098 54715 solver.cpp:237] Iteration 93, loss = 0.613989
I0605 23:05:12.763152 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.715032 (* 1 = 0.715032 loss)
I0605 23:05:12.763164 54715 sgd_solver.cpp:106] Iteration 93, lr = 0.00998512
I0605 23:05:22.139302 54715 solver.cpp:237] Iteration 96, loss = 0.607054
I0605 23:05:22.139353 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.541614 (* 1 = 0.541614 loss)
I0605 23:05:22.139364 54715 sgd_solver.cpp:106] Iteration 96, lr = 0.00998464
I0605 23:05:31.511983 54715 solver.cpp:237] Iteration 99, loss = 0.603025
I0605 23:05:31.512096 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.639951 (* 1 = 0.639951 loss)
I0605 23:05:31.512110 54715 sgd_solver.cpp:106] Iteration 99, lr = 0.00998416
I0605 23:05:31.621485 54715 solver.cpp:341] Iteration 100, Testing net (#0)
I0605 23:05:32.903414 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.725941
I0605 23:05:32.903456 54715 solver.cpp:409] Test net output #1: class_Acc = 0.769251
I0605 23:05:32.903463 54715 solver.cpp:409] Test net output #2: class_Acc = 0.602062
I0605 23:05:32.903473 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.558138 (* 1 = 0.558138 loss)
I0605 23:05:36.909224 54715 softmax_loss_layer.cu:194] weight loss 0 =0.284399 weight loss 1 =1 weight loss 2 =0
I0605 23:05:42.167950 54715 solver.cpp:237] Iteration 102, loss = 0.589982
I0605 23:05:42.168002 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.502613 (* 1 = 0.502613 loss)
I0605 23:05:42.168014 54715 sgd_solver.cpp:106] Iteration 102, lr = 0.00998368
I0605 23:05:51.541838 54715 solver.cpp:237] Iteration 105, loss = 0.592307
I0605 23:05:51.541887 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.72405 (* 1 = 0.72405 loss)
I0605 23:05:51.541898 54715 sgd_solver.cpp:106] Iteration 105, lr = 0.0099832
I0605 23:06:00.913975 54715 solver.cpp:237] Iteration 108, loss = 0.593305
I0605 23:06:00.914017 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.531698 (* 1 = 0.531698 loss)
I0605 23:06:00.914029 54715 sgd_solver.cpp:106] Iteration 108, lr = 0.00998272
I0605 23:06:04.147513 54715 solver.cpp:341] Iteration 110, Testing net (#0)
I0605 23:06:05.430341 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.7438
I0605 23:06:05.430383 54715 solver.cpp:409] Test net output #1: class_Acc = 0.799392
I0605 23:06:05.430390 54715 solver.cpp:409] Test net output #2: class_Acc = 0.592007
I0605 23:06:05.430400 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.530425 (* 1 = 0.530425 loss)
I0605 23:06:11.568897 54715 solver.cpp:237] Iteration 111, loss = 0.596321
I0605 23:06:11.568950 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.751129 (* 1 = 0.751129 loss)
I0605 23:06:11.568972 54715 sgd_solver.cpp:106] Iteration 111, lr = 0.00998224
I0605 23:06:20.940549 54715 solver.cpp:237] Iteration 114, loss = 0.586753
I0605 23:06:20.940595 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.659482 (* 1 = 0.659482 loss)
I0605 23:06:20.940606 54715 sgd_solver.cpp:106] Iteration 114, lr = 0.00998176
I0605 23:06:30.312727 54715 solver.cpp:237] Iteration 117, loss = 0.59172
I0605 23:06:30.312780 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.592681 (* 1 = 0.592681 loss)
I0605 23:06:30.312791 54715 sgd_solver.cpp:106] Iteration 117, lr = 0.00998128
I0605 23:06:36.672823 54715 solver.cpp:341] Iteration 120, Testing net (#0)
I0605 23:06:37.955606 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.744954
I0605 23:06:37.955648 54715 solver.cpp:409] Test net output #1: class_Acc = 0.793114
I0605 23:06:37.955655 54715 solver.cpp:409] Test net output #2: class_Acc = 0.628582
I0605 23:06:37.955667 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.518914 (* 1 = 0.518914 loss)
I0605 23:06:38.835517 54715 softmax_loss_layer.cu:194] weight loss 0 =0.185023 weight loss 1 =1 weight loss 2 =0
I0605 23:06:40.969027 54715 solver.cpp:237] Iteration 120, loss = 0.594428
I0605 23:06:40.969074 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.567259 (* 1 = 0.567259 loss)
I0605 23:06:40.969085 54715 sgd_solver.cpp:106] Iteration 120, lr = 0.00998079
I0605 23:06:50.341698 54715 solver.cpp:237] Iteration 123, loss = 0.59584
I0605 23:06:50.341743 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.475956 (* 1 = 0.475956 loss)
I0605 23:06:50.341754 54715 sgd_solver.cpp:106] Iteration 123, lr = 0.00998032
I0605 23:06:59.715224 54715 solver.cpp:237] Iteration 126, loss = 0.59031
I0605 23:06:59.715276 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.555723 (* 1 = 0.555723 loss)
I0605 23:06:59.715286 54715 sgd_solver.cpp:106] Iteration 126, lr = 0.00997983
I0605 23:07:09.086585 54715 solver.cpp:237] Iteration 129, loss = 0.579977
I0605 23:07:09.086689 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.467698 (* 1 = 0.467698 loss)
I0605 23:07:09.086702 54715 sgd_solver.cpp:106] Iteration 129, lr = 0.00997935
I0605 23:07:09.196202 54715 solver.cpp:341] Iteration 130, Testing net (#0)
I0605 23:07:10.477469 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.751475
I0605 23:07:10.477517 54715 solver.cpp:409] Test net output #1: class_Acc = 0.836879
I0605 23:07:10.477524 54715 solver.cpp:409] Test net output #2: class_Acc = 0.515245
I0605 23:07:10.477535 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.522446 (* 1 = 0.522446 loss)
I0605 23:07:19.743854 54715 solver.cpp:237] Iteration 132, loss = 0.568639
I0605 23:07:19.743903 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.617828 (* 1 = 0.617828 loss)
I0605 23:07:19.743916 54715 sgd_solver.cpp:106] Iteration 132, lr = 0.00997887
I0605 23:07:29.116564 54715 solver.cpp:237] Iteration 135, loss = 0.568446
I0605 23:07:29.116612 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.529409 (* 1 = 0.529409 loss)
I0605 23:07:29.116622 54715 sgd_solver.cpp:106] Iteration 135, lr = 0.00997839
I0605 23:07:38.489997 54715 solver.cpp:237] Iteration 138, loss = 0.562843
I0605 23:07:38.490047 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.689324 (* 1 = 0.689324 loss)
I0605 23:07:38.490058 54715 sgd_solver.cpp:106] Iteration 138, lr = 0.00997791
I0605 23:07:41.723543 54715 solver.cpp:341] Iteration 140, Testing net (#0)
I0605 23:07:43.005159 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.751874
I0605 23:07:43.005205 54715 solver.cpp:409] Test net output #1: class_Acc = 0.846317
I0605 23:07:43.005213 54715 solver.cpp:409] Test net output #2: class_Acc = 0.506932
I0605 23:07:43.005223 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.527847 (* 1 = 0.527847 loss)
I0605 23:07:49.142192 54715 solver.cpp:237] Iteration 141, loss = 0.562419
I0605 23:07:49.142252 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.590614 (* 1 = 0.590614 loss)
I0605 23:07:49.142264 54715 sgd_solver.cpp:106] Iteration 141, lr = 0.00997743
I0605 23:07:58.518678 54715 solver.cpp:237] Iteration 144, loss = 0.562657
I0605 23:07:58.518730 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.530829 (* 1 = 0.530829 loss)
I0605 23:07:58.518740 54715 sgd_solver.cpp:106] Iteration 144, lr = 0.00997695
I0605 23:08:07.906023 54715 solver.cpp:237] Iteration 147, loss = 0.563565
I0605 23:08:07.906077 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.553992 (* 1 = 0.553992 loss)
I0605 23:08:07.906090 54715 sgd_solver.cpp:106] Iteration 147, lr = 0.00997647
I0605 23:08:14.284760 54715 solver.cpp:341] Iteration 150, Testing net (#0)
I0605 23:08:15.601249 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.749123
I0605 23:08:15.601299 54715 solver.cpp:409] Test net output #1: class_Acc = 0.82844
I0605 23:08:15.601305 54715 solver.cpp:409] Test net output #2: class_Acc = 0.564821
I0605 23:08:15.601316 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.513753 (* 1 = 0.513753 loss)
I0605 23:08:18.622009 54715 solver.cpp:237] Iteration 150, loss = 0.562744
I0605 23:08:18.622054 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.540395 (* 1 = 0.540395 loss)
I0605 23:08:18.622066 54715 sgd_solver.cpp:106] Iteration 150, lr = 0.00997599
I0605 23:08:28.021121 54715 solver.cpp:237] Iteration 153, loss = 0.558247
I0605 23:08:28.021173 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.60527 (* 1 = 0.60527 loss)
I0605 23:08:28.021184 54715 sgd_solver.cpp:106] Iteration 153, lr = 0.00997551
I0605 23:08:37.415637 54715 solver.cpp:237] Iteration 156, loss = 0.55213
I0605 23:08:37.415684 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.579593 (* 1 = 0.579593 loss)
I0605 23:08:37.415694 54715 sgd_solver.cpp:106] Iteration 156, lr = 0.00997503
I0605 23:08:46.787825 54715 solver.cpp:237] Iteration 159, loss = 0.546842
I0605 23:08:46.787921 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.458081 (* 1 = 0.458081 loss)
I0605 23:08:46.787935 54715 sgd_solver.cpp:106] Iteration 159, lr = 0.00997455
I0605 23:08:46.897289 54715 solver.cpp:341] Iteration 160, Testing net (#0)
I0605 23:08:48.178110 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.743229
I0605 23:08:48.178155 54715 solver.cpp:409] Test net output #1: class_Acc = 0.825148
I0605 23:08:48.178162 54715 solver.cpp:409] Test net output #2: class_Acc = 0.536439
I0605 23:08:48.178171 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.514882 (* 1 = 0.514882 loss)
I0605 23:08:57.440522 54715 solver.cpp:237] Iteration 162, loss = 0.548507
I0605 23:08:57.440572 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.496041 (* 1 = 0.496041 loss)
I0605 23:08:57.440582 54715 sgd_solver.cpp:106] Iteration 162, lr = 0.00997407
I0605 23:09:06.812045 54715 solver.cpp:237] Iteration 165, loss = 0.539519
I0605 23:09:06.812081 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.586657 (* 1 = 0.586657 loss)
I0605 23:09:06.812093 54715 sgd_solver.cpp:106] Iteration 165, lr = 0.00997359
I0605 23:09:16.190590 54715 solver.cpp:237] Iteration 168, loss = 0.533632
I0605 23:09:16.190641 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.458211 (* 1 = 0.458211 loss)
I0605 23:09:16.190654 54715 sgd_solver.cpp:106] Iteration 168, lr = 0.00997311
I0605 23:09:19.424913 54715 solver.cpp:341] Iteration 170, Testing net (#0)
I0605 23:09:20.707406 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.75004
I0605 23:09:20.707449 54715 solver.cpp:409] Test net output #1: class_Acc = 0.820304
I0605 23:09:20.707456 54715 solver.cpp:409] Test net output #2: class_Acc = 0.571319
I0605 23:09:20.707466 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.507214 (* 1 = 0.507214 loss)
I0605 23:09:26.845665 54715 solver.cpp:237] Iteration 171, loss = 0.541536
I0605 23:09:26.845723 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.665282 (* 1 = 0.665282 loss)
I0605 23:09:26.845736 54715 sgd_solver.cpp:106] Iteration 171, lr = 0.00997263
I0605 23:09:36.220290 54715 solver.cpp:237] Iteration 174, loss = 0.543623
I0605 23:09:36.220340 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.519714 (* 1 = 0.519714 loss)
I0605 23:09:36.220350 54715 sgd_solver.cpp:106] Iteration 174, lr = 0.00997215
I0605 23:09:38.377050 54715 softmax_loss_layer.cu:194] weight loss 0 =0.275377 weight loss 1 =1 weight loss 2 =0
I0605 23:09:45.592281 54715 solver.cpp:237] Iteration 177, loss = 0.53726
I0605 23:09:45.592332 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.430699 (* 1 = 0.430699 loss)
I0605 23:09:45.592344 54715 sgd_solver.cpp:106] Iteration 177, lr = 0.00997167
I0605 23:09:51.951489 54715 solver.cpp:341] Iteration 180, Testing net (#0)
I0605 23:09:53.233644 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.765924
I0605 23:09:53.233690 54715 solver.cpp:409] Test net output #1: class_Acc = 0.875987
I0605 23:09:53.233697 54715 solver.cpp:409] Test net output #2: class_Acc = 0.51231
I0605 23:09:53.233707 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.484631 (* 1 = 0.484631 loss)
I0605 23:09:56.248561 54715 solver.cpp:237] Iteration 180, loss = 0.541508
I0605 23:09:56.248610 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.47876 (* 1 = 0.47876 loss)
I0605 23:09:56.248620 54715 sgd_solver.cpp:106] Iteration 180, lr = 0.00997119
I0605 23:10:05.622745 54715 solver.cpp:237] Iteration 183, loss = 0.543821
I0605 23:10:05.622793 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.503138 (* 1 = 0.503138 loss)
I0605 23:10:05.622805 54715 sgd_solver.cpp:106] Iteration 183, lr = 0.00997071
I0605 23:10:14.995242 54715 solver.cpp:237] Iteration 186, loss = 0.537041
I0605 23:10:14.995291 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.676141 (* 1 = 0.676141 loss)
I0605 23:10:14.995303 54715 sgd_solver.cpp:106] Iteration 186, lr = 0.00997023
I0605 23:10:24.368577 54715 solver.cpp:237] Iteration 189, loss = 0.528837
I0605 23:10:24.368686 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.501475 (* 1 = 0.501475 loss)
I0605 23:10:24.368698 54715 sgd_solver.cpp:106] Iteration 189, lr = 0.00996975
I0605 23:10:24.478008 54715 solver.cpp:341] Iteration 190, Testing net (#0)
I0605 23:10:25.759212 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.745583
I0605 23:10:25.759255 54715 solver.cpp:409] Test net output #1: class_Acc = 0.864453
I0605 23:10:25.759263 54715 solver.cpp:409] Test net output #2: class_Acc = 0.466005
I0605 23:10:25.759274 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.502257 (* 1 = 0.502257 loss)
I0605 23:10:35.026625 54715 solver.cpp:237] Iteration 192, loss = 0.527561
I0605 23:10:35.026674 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.486206 (* 1 = 0.486206 loss)
I0605 23:10:35.026686 54715 sgd_solver.cpp:106] Iteration 192, lr = 0.00996927
I0605 23:10:44.401768 54715 solver.cpp:237] Iteration 195, loss = 0.526251
I0605 23:10:44.401859 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.471054 (* 1 = 0.471054 loss)
I0605 23:10:44.401868 54715 sgd_solver.cpp:106] Iteration 195, lr = 0.00996879
I0605 23:10:53.778213 54715 solver.cpp:237] Iteration 198, loss = 0.520644
I0605 23:10:53.778259 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.566922 (* 1 = 0.566922 loss)
I0605 23:10:53.778268 54715 sgd_solver.cpp:106] Iteration 198, lr = 0.00996831
I0605 23:10:57.012395 54715 solver.cpp:341] Iteration 200, Testing net (#0)
I0605 23:10:58.293583 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.758484
I0605 23:10:58.293627 54715 solver.cpp:409] Test net output #1: class_Acc = 0.83783
I0605 23:10:58.293633 54715 solver.cpp:409] Test net output #2: class_Acc = 0.571312
I0605 23:10:58.293654 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.501877 (* 1 = 0.501877 loss)
I0605 23:11:04.435093 54715 solver.cpp:237] Iteration 201, loss = 0.524495
I0605 23:11:04.435142 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.512095 (* 1 = 0.512095 loss)
I0605 23:11:04.435151 54715 sgd_solver.cpp:106] Iteration 201, lr = 0.00996783
I0605 23:11:13.808459 54715 solver.cpp:237] Iteration 204, loss = 0.522888
I0605 23:11:13.808492 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.497034 (* 1 = 0.497034 loss)
I0605 23:11:13.808502 54715 sgd_solver.cpp:106] Iteration 204, lr = 0.00996735
I0605 23:11:23.180269 54715 solver.cpp:237] Iteration 207, loss = 0.523962
I0605 23:11:23.180317 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.570239 (* 1 = 0.570239 loss)
I0605 23:11:23.180328 54715 sgd_solver.cpp:106] Iteration 207, lr = 0.00996687
I0605 23:11:23.392665 54715 softmax_loss_layer.cu:194] weight loss 0 =0.343028 weight loss 1 =1 weight loss 2 =0
I0605 23:11:29.538120 54715 solver.cpp:341] Iteration 210, Testing net (#0)
I0605 23:11:30.820076 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.76152
I0605 23:11:30.820123 54715 solver.cpp:409] Test net output #1: class_Acc = 0.856612
I0605 23:11:30.820132 54715 solver.cpp:409] Test net output #2: class_Acc = 0.524117
I0605 23:11:30.820152 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.490234 (* 1 = 0.490234 loss)
I0605 23:11:33.835280 54715 solver.cpp:237] Iteration 210, loss = 0.528121
I0605 23:11:33.835328 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.551787 (* 1 = 0.551787 loss)
I0605 23:11:33.835340 54715 sgd_solver.cpp:106] Iteration 210, lr = 0.00996639
I0605 23:11:43.207728 54715 solver.cpp:237] Iteration 213, loss = 0.525688
I0605 23:11:43.207777 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.444693 (* 1 = 0.444693 loss)
I0605 23:11:43.207787 54715 sgd_solver.cpp:106] Iteration 213, lr = 0.0099659
I0605 23:11:52.583688 54715 solver.cpp:237] Iteration 216, loss = 0.524025
I0605 23:11:52.583737 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.436858 (* 1 = 0.436858 loss)
I0605 23:11:52.583748 54715 sgd_solver.cpp:106] Iteration 216, lr = 0.00996542
I0605 23:12:01.958243 54715 solver.cpp:237] Iteration 219, loss = 0.522881
I0605 23:12:01.958317 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.647196 (* 1 = 0.647196 loss)
I0605 23:12:01.958328 54715 sgd_solver.cpp:106] Iteration 219, lr = 0.00996494
I0605 23:12:02.067656 54715 solver.cpp:341] Iteration 220, Testing net (#0)
I0605 23:12:03.351022 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.755789
I0605 23:12:03.351066 54715 solver.cpp:409] Test net output #1: class_Acc = 0.835307
I0605 23:12:03.351073 54715 solver.cpp:409] Test net output #2: class_Acc = 0.56491
I0605 23:12:03.351083 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.492313 (* 1 = 0.492313 loss)
I0605 23:12:08.132282 54715 softmax_loss_layer.cu:194] weight loss 0 =0.322666 weight loss 1 =1 weight loss 2 =0
I0605 23:12:08.911115 54715 softmax_loss_layer.cu:194] weight loss 0 =0.282485 weight loss 1 =1 weight loss 2 =0
I0605 23:12:12.612699 54715 solver.cpp:237] Iteration 222, loss = 0.513291
I0605 23:12:12.612742 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.467343 (* 1 = 0.467343 loss)
I0605 23:12:12.612754 54715 sgd_solver.cpp:106] Iteration 222, lr = 0.00996446
I0605 23:12:18.673974 54715 softmax_loss_layer.cu:194] weight loss 0 =0.341332 weight loss 1 =1 weight loss 2 =0
I0605 23:12:21.986537 54715 solver.cpp:237] Iteration 225, loss = 0.508308
I0605 23:12:21.986587 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.536449 (* 1 = 0.536449 loss)
I0605 23:12:21.986596 54715 sgd_solver.cpp:106] Iteration 225, lr = 0.00996398
I0605 23:12:30.001713 54715 softmax_loss_layer.cu:194] weight loss 0 =0.290931 weight loss 1 =1 weight loss 2 =0
I0605 23:12:31.358922 54715 solver.cpp:237] Iteration 228, loss = 0.509016
I0605 23:12:31.358979 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.53237 (* 1 = 0.53237 loss)
I0605 23:12:31.358990 54715 sgd_solver.cpp:106] Iteration 228, lr = 0.0099635
I0605 23:12:34.594945 54715 solver.cpp:341] Iteration 230, Testing net (#0)
I0605 23:12:35.876446 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.771313
I0605 23:12:35.876492 54715 solver.cpp:409] Test net output #1: class_Acc = 0.891722
I0605 23:12:35.876499 54715 solver.cpp:409] Test net output #2: class_Acc = 0.500078
I0605 23:12:35.876510 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.462048 (* 1 = 0.462048 loss)
I0605 23:12:40.658496 54715 softmax_loss_layer.cu:194] weight loss 0 =0.270572 weight loss 1 =1 weight loss 2 =0
I0605 23:12:42.014698 54715 solver.cpp:237] Iteration 231, loss = 0.503729
I0605 23:12:42.014750 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.467138 (* 1 = 0.467138 loss)
I0605 23:12:42.014762 54715 sgd_solver.cpp:106] Iteration 231, lr = 0.00996302
I0605 23:12:51.390215 54715 solver.cpp:237] Iteration 234, loss = 0.501922
I0605 23:12:51.390269 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.671139 (* 1 = 0.671139 loss)
I0605 23:12:51.390280 54715 sgd_solver.cpp:106] Iteration 234, lr = 0.00996254
I0605 23:13:00.760895 54715 solver.cpp:237] Iteration 237, loss = 0.499117
I0605 23:13:00.760946 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.423243 (* 1 = 0.423243 loss)
I0605 23:13:00.760958 54715 sgd_solver.cpp:106] Iteration 237, lr = 0.00996206
I0605 23:13:07.118041 54715 solver.cpp:341] Iteration 240, Testing net (#0)
I0605 23:13:08.399572 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.760828
I0605 23:13:08.399600 54715 solver.cpp:409] Test net output #1: class_Acc = 0.868926
I0605 23:13:08.399605 54715 solver.cpp:409] Test net output #2: class_Acc = 0.504456
I0605 23:13:08.399616 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.48268 (* 1 = 0.48268 loss)
I0605 23:13:11.414031 54715 solver.cpp:237] Iteration 240, loss = 0.505921
I0605 23:13:11.414078 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.556508 (* 1 = 0.556508 loss)
I0605 23:13:11.414088 54715 sgd_solver.cpp:106] Iteration 240, lr = 0.00996158
I0605 23:13:20.790563 54715 solver.cpp:237] Iteration 243, loss = 0.4983
I0605 23:13:20.790617 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.481324 (* 1 = 0.481324 loss)
I0605 23:13:20.790628 54715 sgd_solver.cpp:106] Iteration 243, lr = 0.0099611
I0605 23:13:30.165056 54715 solver.cpp:237] Iteration 246, loss = 0.499041
I0605 23:13:30.165105 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.46218 (* 1 = 0.46218 loss)
I0605 23:13:30.165117 54715 sgd_solver.cpp:106] Iteration 246, lr = 0.00996062
I0605 23:13:39.539939 54715 solver.cpp:237] Iteration 249, loss = 0.498039
I0605 23:13:39.540041 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.480222 (* 1 = 0.480222 loss)
I0605 23:13:39.540053 54715 sgd_solver.cpp:106] Iteration 249, lr = 0.00996014
I0605 23:13:39.649364 54715 solver.cpp:341] Iteration 250, Testing net (#0)
I0605 23:13:40.931272 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.761487
I0605 23:13:40.931318 54715 solver.cpp:409] Test net output #1: class_Acc = 0.925773
I0605 23:13:40.931324 54715 solver.cpp:409] Test net output #2: class_Acc = 0.365759
I0605 23:13:40.931337 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.477394 (* 1 = 0.477394 loss)
I0605 23:13:50.191496 54715 solver.cpp:237] Iteration 252, loss = 0.502331
I0605 23:13:50.191545 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.560851 (* 1 = 0.560851 loss)
I0605 23:13:50.191558 54715 sgd_solver.cpp:106] Iteration 252, lr = 0.00995966
I0605 23:13:59.568177 54715 solver.cpp:237] Iteration 255, loss = 0.496695
I0605 23:13:59.568220 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.524902 (* 1 = 0.524902 loss)
I0605 23:13:59.568236 54715 sgd_solver.cpp:106] Iteration 255, lr = 0.00995918
I0605 23:14:08.942782 54715 solver.cpp:237] Iteration 258, loss = 0.490953
I0605 23:14:08.942833 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.400697 (* 1 = 0.400697 loss)
I0605 23:14:08.942843 54715 sgd_solver.cpp:106] Iteration 258, lr = 0.0099587
I0605 23:14:12.178798 54715 solver.cpp:341] Iteration 260, Testing net (#0)
I0605 23:14:13.459317 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.75888
I0605 23:14:13.459363 54715 solver.cpp:409] Test net output #1: class_Acc = 0.907141
I0605 23:14:13.459370 54715 solver.cpp:409] Test net output #2: class_Acc = 0.399027
I0605 23:14:13.459380 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.486537 (* 1 = 0.486537 loss)
I0605 23:14:19.599490 54715 solver.cpp:237] Iteration 261, loss = 0.48616
I0605 23:14:19.599544 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.524459 (* 1 = 0.524459 loss)
I0605 23:14:19.599553 54715 sgd_solver.cpp:106] Iteration 261, lr = 0.00995822
I0605 23:14:28.973593 54715 solver.cpp:237] Iteration 264, loss = 0.488677
I0605 23:14:28.973636 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.539147 (* 1 = 0.539147 loss)
I0605 23:14:28.973646 54715 sgd_solver.cpp:106] Iteration 264, lr = 0.00995774
I0605 23:14:38.346606 54715 solver.cpp:237] Iteration 267, loss = 0.489403
I0605 23:14:38.346657 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.468583 (* 1 = 0.468583 loss)
I0605 23:14:38.346669 54715 sgd_solver.cpp:106] Iteration 267, lr = 0.00995726
I0605 23:14:44.704737 54715 solver.cpp:341] Iteration 270, Testing net (#0)
I0605 23:14:45.983777 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.725958
I0605 23:14:45.983822 54715 solver.cpp:409] Test net output #1: class_Acc = 0.9174
I0605 23:14:45.983829 54715 solver.cpp:409] Test net output #2: class_Acc = 0.248989
I0605 23:14:45.983840 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.552182 (* 1 = 0.552182 loss)
I0605 23:14:48.998271 54715 solver.cpp:237] Iteration 270, loss = 0.488283
I0605 23:14:48.998328 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.459439 (* 1 = 0.459439 loss)
I0605 23:14:48.999099 54715 sgd_solver.cpp:106] Iteration 270, lr = 0.00995678
I0605 23:14:58.374356 54715 solver.cpp:237] Iteration 273, loss = 0.489139
I0605 23:14:58.374387 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.424274 (* 1 = 0.424274 loss)
I0605 23:14:58.374398 54715 sgd_solver.cpp:106] Iteration 273, lr = 0.0099563
I0605 23:15:07.743669 54715 solver.cpp:237] Iteration 276, loss = 0.495673
I0605 23:15:07.743721 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.507682 (* 1 = 0.507682 loss)
I0605 23:15:07.743731 54715 sgd_solver.cpp:106] Iteration 276, lr = 0.00995582
I0605 23:15:10.680512 54715 softmax_loss_layer.cu:194] weight loss 0 =0.354784 weight loss 1 =1 weight loss 2 =0
I0605 23:15:17.118556 54715 solver.cpp:237] Iteration 279, loss = 0.493585
I0605 23:15:17.118686 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.45841 (* 1 = 0.45841 loss)
I0605 23:15:17.118698 54715 sgd_solver.cpp:106] Iteration 279, lr = 0.00995533
I0605 23:15:17.227910 54715 solver.cpp:341] Iteration 280, Testing net (#0)
I0605 23:15:18.507170 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.757397
I0605 23:15:18.507215 54715 solver.cpp:409] Test net output #1: class_Acc = 0.92542
I0605 23:15:18.507221 54715 solver.cpp:409] Test net output #2: class_Acc = 0.338605
I0605 23:15:18.507230 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.486538 (* 1 = 0.486538 loss)
I0605 23:15:27.769982 54715 solver.cpp:237] Iteration 282, loss = 0.486961
I0605 23:15:27.770035 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.43523 (* 1 = 0.43523 loss)
I0605 23:15:27.770045 54715 sgd_solver.cpp:106] Iteration 282, lr = 0.00995485
I0605 23:15:36.955458 54715 softmax_loss_layer.cu:194] weight loss 0 =0.281602 weight loss 1 =1 weight loss 2 =0
I0605 23:15:37.144999 54715 solver.cpp:237] Iteration 285, loss = 0.486428
I0605 23:15:37.145042 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.444975 (* 1 = 0.444975 loss)
I0605 23:15:37.145052 54715 sgd_solver.cpp:106] Iteration 285, lr = 0.00995437
I0605 23:15:46.525365 54715 solver.cpp:237] Iteration 288, loss = 0.488368
I0605 23:15:46.525414 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.492464 (* 1 = 0.492464 loss)
I0605 23:15:46.525425 54715 sgd_solver.cpp:106] Iteration 288, lr = 0.00995389
I0605 23:15:49.071005 54715 softmax_loss_layer.cu:194] weight loss 0 =0.237056 weight loss 1 =1 weight loss 2 =0
I0605 23:15:49.759572 54715 solver.cpp:341] Iteration 290, Testing net (#0)
I0605 23:15:51.038353 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.733865
I0605 23:15:51.038396 54715 solver.cpp:409] Test net output #1: class_Acc = 0.957118
I0605 23:15:51.038403 54715 solver.cpp:409] Test net output #2: class_Acc = 0.206461
I0605 23:15:51.038414 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.562184 (* 1 = 0.562184 loss)
I0605 23:15:57.179121 54715 solver.cpp:237] Iteration 291, loss = 0.484888
I0605 23:15:57.179170 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.407487 (* 1 = 0.407487 loss)
I0605 23:15:57.179181 54715 sgd_solver.cpp:106] Iteration 291, lr = 0.00995341
I0605 23:16:06.553318 54715 solver.cpp:237] Iteration 294, loss = 0.481924
I0605 23:16:06.553367 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.48123 (* 1 = 0.48123 loss)
I0605 23:16:06.553377 54715 sgd_solver.cpp:106] Iteration 294, lr = 0.00995293
I0605 23:16:15.929498 54715 solver.cpp:237] Iteration 297, loss = 0.48062
I0605 23:16:15.929549 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.442043 (* 1 = 0.442043 loss)
I0605 23:16:15.929559 54715 sgd_solver.cpp:106] Iteration 297, lr = 0.00995245
I0605 23:16:22.289425 54715 solver.cpp:341] Iteration 300, Testing net (#0)
I0605 23:16:23.570489 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.75165
I0605 23:16:23.570534 54715 solver.cpp:409] Test net output #1: class_Acc = 0.913953
I0605 23:16:23.570541 54715 solver.cpp:409] Test net output #2: class_Acc = 0.414423
I0605 23:16:23.570552 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.491345 (* 1 = 0.491345 loss)
I0605 23:16:26.585041 54715 solver.cpp:237] Iteration 300, loss = 0.477985
I0605 23:16:26.585096 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.424313 (* 1 = 0.424313 loss)
I0605 23:16:26.585108 54715 sgd_solver.cpp:106] Iteration 300, lr = 0.00995197
I0605 23:16:35.960165 54715 solver.cpp:237] Iteration 303, loss = 0.474034
I0605 23:16:35.960214 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.487665 (* 1 = 0.487665 loss)
I0605 23:16:35.960225 54715 sgd_solver.cpp:106] Iteration 303, lr = 0.00995149
I0605 23:16:45.334858 54715 solver.cpp:237] Iteration 306, loss = 0.468225
I0605 23:16:45.334908 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.514258 (* 1 = 0.514258 loss)
I0605 23:16:45.334919 54715 sgd_solver.cpp:106] Iteration 306, lr = 0.00995101
I0605 23:16:54.707231 54715 solver.cpp:237] Iteration 309, loss = 0.469053
I0605 23:16:54.707334 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395145 (* 1 = 0.395145 loss)
I0605 23:16:54.707347 54715 sgd_solver.cpp:106] Iteration 309, lr = 0.00995053
I0605 23:16:54.816802 54715 solver.cpp:341] Iteration 310, Testing net (#0)
I0605 23:16:56.097890 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.735689
I0605 23:16:56.097936 54715 solver.cpp:409] Test net output #1: class_Acc = 0.925443
I0605 23:16:56.097944 54715 solver.cpp:409] Test net output #2: class_Acc = 0.337835
I0605 23:16:56.097954 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.5129 (* 1 = 0.5129 loss)
I0605 23:17:05.361421 54715 solver.cpp:237] Iteration 312, loss = 0.472489
I0605 23:17:05.361472 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.486189 (* 1 = 0.486189 loss)
I0605 23:17:05.361492 54715 sgd_solver.cpp:106] Iteration 312, lr = 0.00995005
I0605 23:17:14.733014 54715 solver.cpp:237] Iteration 315, loss = 0.474369
I0605 23:17:14.733065 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.49632 (* 1 = 0.49632 loss)
I0605 23:17:14.733078 54715 sgd_solver.cpp:106] Iteration 315, lr = 0.00994957
I0605 23:17:24.105654 54715 solver.cpp:237] Iteration 318, loss = 0.477154
I0605 23:17:24.105702 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.496821 (* 1 = 0.496821 loss)
I0605 23:17:24.105713 54715 sgd_solver.cpp:106] Iteration 318, lr = 0.00994909
I0605 23:17:27.340447 54715 solver.cpp:341] Iteration 320, Testing net (#0)
I0605 23:17:28.620069 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.744989
I0605 23:17:28.620110 54715 solver.cpp:409] Test net output #1: class_Acc = 0.953524
I0605 23:17:28.620117 54715 solver.cpp:409] Test net output #2: class_Acc = 0.276529
I0605 23:17:28.620127 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.516958 (* 1 = 0.516958 loss)
I0605 23:17:34.758474 54715 solver.cpp:237] Iteration 321, loss = 0.477596
I0605 23:17:34.758518 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.406364 (* 1 = 0.406364 loss)
I0605 23:17:34.758529 54715 sgd_solver.cpp:106] Iteration 321, lr = 0.00994861
I0605 23:17:44.132643 54715 solver.cpp:237] Iteration 324, loss = 0.477097
I0605 23:17:44.132694 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.508111 (* 1 = 0.508111 loss)
I0605 23:17:44.132706 54715 sgd_solver.cpp:106] Iteration 324, lr = 0.00994813
I0605 23:17:53.503448 54715 solver.cpp:237] Iteration 327, loss = 0.473014
I0605 23:17:53.503481 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.467243 (* 1 = 0.467243 loss)
I0605 23:17:53.503491 54715 sgd_solver.cpp:106] Iteration 327, lr = 0.00994765
I0605 23:17:59.860327 54715 solver.cpp:341] Iteration 330, Testing net (#0)
I0605 23:18:01.143224 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.762744
I0605 23:18:01.143267 54715 solver.cpp:409] Test net output #1: class_Acc = 0.912125
I0605 23:18:01.143275 54715 solver.cpp:409] Test net output #2: class_Acc = 0.429844
I0605 23:18:01.143285 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.475258 (* 1 = 0.475258 loss)
I0605 23:18:04.156769 54715 solver.cpp:237] Iteration 330, loss = 0.469824
I0605 23:18:04.156819 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.467113 (* 1 = 0.467113 loss)
I0605 23:18:04.156831 54715 sgd_solver.cpp:106] Iteration 330, lr = 0.00994716
I0605 23:18:13.530409 54715 solver.cpp:237] Iteration 333, loss = 0.467528
I0605 23:18:13.530462 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.437846 (* 1 = 0.437846 loss)
I0605 23:18:13.530472 54715 sgd_solver.cpp:106] Iteration 333, lr = 0.00994668
I0605 23:18:22.905161 54715 solver.cpp:237] Iteration 336, loss = 0.467007
I0605 23:18:22.905211 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.496044 (* 1 = 0.496044 loss)
I0605 23:18:22.905221 54715 sgd_solver.cpp:106] Iteration 336, lr = 0.0099462
I0605 23:18:32.279572 54715 solver.cpp:237] Iteration 339, loss = 0.465994
I0605 23:18:32.279666 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.40717 (* 1 = 0.40717 loss)
I0605 23:18:32.279678 54715 sgd_solver.cpp:106] Iteration 339, lr = 0.00994572
I0605 23:18:32.389036 54715 solver.cpp:341] Iteration 340, Testing net (#0)
I0605 23:18:33.669065 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.747518
I0605 23:18:33.669111 54715 solver.cpp:409] Test net output #1: class_Acc = 0.942078
I0605 23:18:33.669118 54715 solver.cpp:409] Test net output #2: class_Acc = 0.306316
I0605 23:18:33.669127 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.520854 (* 1 = 0.520854 loss)
I0605 23:18:42.933617 54715 solver.cpp:237] Iteration 342, loss = 0.468801
I0605 23:18:42.933670 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.464409 (* 1 = 0.464409 loss)
I0605 23:18:42.933691 54715 sgd_solver.cpp:106] Iteration 342, lr = 0.00994524
I0605 23:18:52.309623 54715 solver.cpp:237] Iteration 345, loss = 0.46642
I0605 23:18:52.309670 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.411263 (* 1 = 0.411263 loss)
I0605 23:18:52.309681 54715 sgd_solver.cpp:106] Iteration 345, lr = 0.00994476
I0605 23:19:01.682848 54715 solver.cpp:237] Iteration 348, loss = 0.464116
I0605 23:19:01.682890 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.436074 (* 1 = 0.436074 loss)
I0605 23:19:01.682902 54715 sgd_solver.cpp:106] Iteration 348, lr = 0.00994428
I0605 23:19:04.917086 54715 solver.cpp:341] Iteration 350, Testing net (#0)
I0605 23:19:06.197911 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.747787
I0605 23:19:06.197957 54715 solver.cpp:409] Test net output #1: class_Acc = 0.922769
I0605 23:19:06.197962 54715 solver.cpp:409] Test net output #2: class_Acc = 0.359097
I0605 23:19:06.197973 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.499076 (* 1 = 0.499076 loss)
I0605 23:19:12.337095 54715 solver.cpp:237] Iteration 351, loss = 0.463036
I0605 23:19:12.337144 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.454045 (* 1 = 0.454045 loss)
I0605 23:19:12.337155 54715 sgd_solver.cpp:106] Iteration 351, lr = 0.0099438
I0605 23:19:21.711081 54715 solver.cpp:237] Iteration 354, loss = 0.460096
I0605 23:19:21.711139 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.430333 (* 1 = 0.430333 loss)
I0605 23:19:21.711156 54715 sgd_solver.cpp:106] Iteration 354, lr = 0.00994332
I0605 23:19:31.084486 54715 solver.cpp:237] Iteration 357, loss = 0.458969
I0605 23:19:31.084533 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.46413 (* 1 = 0.46413 loss)
I0605 23:19:31.084544 54715 sgd_solver.cpp:106] Iteration 357, lr = 0.00994284
I0605 23:19:37.443382 54715 solver.cpp:341] Iteration 360, Testing net (#0)
I0605 23:19:38.726162 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.758302
I0605 23:19:38.726203 54715 solver.cpp:409] Test net output #1: class_Acc = 0.912273
I0605 23:19:38.726210 54715 solver.cpp:409] Test net output #2: class_Acc = 0.395457
I0605 23:19:38.726219 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.478758 (* 1 = 0.478758 loss)
I0605 23:19:41.739871 54715 solver.cpp:237] Iteration 360, loss = 0.459039
I0605 23:19:41.739922 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.444127 (* 1 = 0.444127 loss)
I0605 23:19:41.739933 54715 sgd_solver.cpp:106] Iteration 360, lr = 0.00994236
I0605 23:19:42.341612 54715 softmax_loss_layer.cu:194] weight loss 0 =0.271276 weight loss 1 =1 weight loss 2 =0
I0605 23:19:51.113344 54715 solver.cpp:237] Iteration 363, loss = 0.461565
I0605 23:19:51.113389 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.425326 (* 1 = 0.425326 loss)
I0605 23:19:51.113397 54715 sgd_solver.cpp:106] Iteration 363, lr = 0.00994188
I0605 23:20:00.492907 54715 solver.cpp:237] Iteration 366, loss = 0.465287
I0605 23:20:00.492954 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.466255 (* 1 = 0.466255 loss)
I0605 23:20:00.492965 54715 sgd_solver.cpp:106] Iteration 366, lr = 0.0099414
I0605 23:20:09.868741 54715 solver.cpp:237] Iteration 369, loss = 0.464269
I0605 23:20:09.868803 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.382486 (* 1 = 0.382486 loss)
I0605 23:20:09.868814 54715 sgd_solver.cpp:106] Iteration 369, lr = 0.00994092
I0605 23:20:09.978220 54715 solver.cpp:341] Iteration 370, Testing net (#0)
I0605 23:20:11.261232 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.755896
I0605 23:20:11.261273 54715 solver.cpp:409] Test net output #1: class_Acc = 0.901757
I0605 23:20:11.261281 54715 solver.cpp:409] Test net output #2: class_Acc = 0.427059
I0605 23:20:11.261291 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.498689 (* 1 = 0.498689 loss)
I0605 23:20:20.525712 54715 solver.cpp:237] Iteration 372, loss = 0.461561
I0605 23:20:20.525761 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.513555 (* 1 = 0.513555 loss)
I0605 23:20:20.525771 54715 sgd_solver.cpp:106] Iteration 372, lr = 0.00994044
I0605 23:20:29.897763 54715 solver.cpp:237] Iteration 375, loss = 0.461298
I0605 23:20:29.897814 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.433599 (* 1 = 0.433599 loss)
I0605 23:20:29.897825 54715 sgd_solver.cpp:106] Iteration 375, lr = 0.00993995
I0605 23:20:39.268257 54715 solver.cpp:237] Iteration 378, loss = 0.457287
I0605 23:20:39.268309 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.473148 (* 1 = 0.473148 loss)
I0605 23:20:39.268321 54715 sgd_solver.cpp:106] Iteration 378, lr = 0.00993947
I0605 23:20:42.502560 54715 solver.cpp:341] Iteration 380, Testing net (#0)
I0605 23:20:43.783301 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.752435
I0605 23:20:43.783346 54715 solver.cpp:409] Test net output #1: class_Acc = 0.869969
I0605 23:20:43.783354 54715 solver.cpp:409] Test net output #2: class_Acc = 0.483551
I0605 23:20:43.783363 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.491154 (* 1 = 0.491154 loss)
I0605 23:20:49.922186 54715 solver.cpp:237] Iteration 381, loss = 0.451604
I0605 23:20:49.922237 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.463188 (* 1 = 0.463188 loss)
I0605 23:20:49.922248 54715 sgd_solver.cpp:106] Iteration 381, lr = 0.00993899
I0605 23:20:53.649092 54715 softmax_loss_layer.cu:194] weight loss 0 =0.275974 weight loss 1 =1 weight loss 2 =0
I0605 23:20:59.295202 54715 solver.cpp:237] Iteration 384, loss = 0.451953
I0605 23:20:59.295253 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.578177 (* 1 = 0.578177 loss)
I0605 23:20:59.295264 54715 sgd_solver.cpp:106] Iteration 384, lr = 0.00993851
I0605 23:21:08.476126 54715 softmax_loss_layer.cu:194] weight loss 0 =0.187794 weight loss 1 =1 weight loss 2 =0
I0605 23:21:08.665611 54715 solver.cpp:237] Iteration 387, loss = 0.452709
I0605 23:21:08.665663 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.487749 (* 1 = 0.487749 loss)
I0605 23:21:08.665674 54715 sgd_solver.cpp:106] Iteration 387, lr = 0.00993803
I0605 23:21:15.024035 54715 solver.cpp:341] Iteration 390, Testing net (#0)
I0605 23:21:16.303711 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.745466
I0605 23:21:16.303755 54715 solver.cpp:409] Test net output #1: class_Acc = 0.957215
I0605 23:21:16.303761 54715 solver.cpp:409] Test net output #2: class_Acc = 0.258035
I0605 23:21:16.303771 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.52764 (* 1 = 0.52764 loss)
I0605 23:21:19.315999 54715 solver.cpp:237] Iteration 390, loss = 0.454042
I0605 23:21:19.316047 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.471652 (* 1 = 0.471652 loss)
I0605 23:21:19.316058 54715 sgd_solver.cpp:106] Iteration 390, lr = 0.00993755
I0605 23:21:28.686466 54715 solver.cpp:237] Iteration 393, loss = 0.454782
I0605 23:21:28.686516 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.52416 (* 1 = 0.52416 loss)
I0605 23:21:28.686527 54715 sgd_solver.cpp:106] Iteration 393, lr = 0.00993707
I0605 23:21:38.059684 54715 solver.cpp:237] Iteration 396, loss = 0.454193
I0605 23:21:38.059733 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.443319 (* 1 = 0.443319 loss)
I0605 23:21:38.059744 54715 sgd_solver.cpp:106] Iteration 396, lr = 0.00993659
I0605 23:21:47.428683 54715 solver.cpp:237] Iteration 399, loss = 0.456463
I0605 23:21:47.428772 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.426111 (* 1 = 0.426111 loss)
I0605 23:21:47.428786 54715 sgd_solver.cpp:106] Iteration 399, lr = 0.00993611
I0605 23:21:47.538136 54715 solver.cpp:341] Iteration 400, Testing net (#0)
I0605 23:21:48.819057 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.758494
I0605 23:21:48.819103 54715 solver.cpp:409] Test net output #1: class_Acc = 0.872578
I0605 23:21:48.819121 54715 solver.cpp:409] Test net output #2: class_Acc = 0.498142
I0605 23:21:48.819133 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.478185 (* 1 = 0.478185 loss)
I0605 23:21:58.085341 54715 solver.cpp:237] Iteration 402, loss = 0.456371
I0605 23:21:58.085389 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.459925 (* 1 = 0.459925 loss)
I0605 23:21:58.085399 54715 sgd_solver.cpp:106] Iteration 402, lr = 0.00993563
I0605 23:22:07.457573 54715 solver.cpp:237] Iteration 405, loss = 0.455911
I0605 23:22:07.457628 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.474185 (* 1 = 0.474185 loss)
I0605 23:22:07.457638 54715 sgd_solver.cpp:106] Iteration 405, lr = 0.00993515
I0605 23:22:13.919822 54715 softmax_loss_layer.cu:194] weight loss 0 =0.178125 weight loss 1 =1 weight loss 2 =0
I0605 23:22:16.834168 54715 solver.cpp:237] Iteration 408, loss = 0.453974
I0605 23:22:16.834215 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.420737 (* 1 = 0.420737 loss)
I0605 23:22:16.834225 54715 sgd_solver.cpp:106] Iteration 408, lr = 0.00993467
I0605 23:22:20.068606 54715 solver.cpp:341] Iteration 410, Testing net (#0)
I0605 23:22:21.347599 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.712171
I0605 23:22:21.347641 54715 solver.cpp:409] Test net output #1: class_Acc = 0.930899
I0605 23:22:21.347647 54715 solver.cpp:409] Test net output #2: class_Acc = 0.220005
I0605 23:22:21.347657 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.654926 (* 1 = 0.654926 loss)
I0605 23:22:27.486080 54715 solver.cpp:237] Iteration 411, loss = 0.451566
I0605 23:22:27.486132 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.432981 (* 1 = 0.432981 loss)
I0605 23:22:27.486142 54715 sgd_solver.cpp:106] Iteration 411, lr = 0.00993419
I0605 23:22:36.859433 54715 solver.cpp:237] Iteration 414, loss = 0.451415
I0605 23:22:36.859483 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.508361 (* 1 = 0.508361 loss)
I0605 23:22:36.859494 54715 sgd_solver.cpp:106] Iteration 414, lr = 0.0099337
I0605 23:22:46.233331 54715 solver.cpp:237] Iteration 417, loss = 0.449899
I0605 23:22:46.233381 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.434182 (* 1 = 0.434182 loss)
I0605 23:22:46.233391 54715 sgd_solver.cpp:106] Iteration 417, lr = 0.00993322
I0605 23:22:52.592975 54715 solver.cpp:341] Iteration 420, Testing net (#0)
I0605 23:22:53.875735 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.769601
I0605 23:22:53.875777 54715 solver.cpp:409] Test net output #1: class_Acc = 0.833561
I0605 23:22:53.875784 54715 solver.cpp:409] Test net output #2: class_Acc = 0.611899
I0605 23:22:53.875794 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.469957 (* 1 = 0.469957 loss)
I0605 23:22:56.889621 54715 solver.cpp:237] Iteration 420, loss = 0.447561
I0605 23:22:56.889664 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.488938 (* 1 = 0.488938 loss)
I0605 23:22:56.889675 54715 sgd_solver.cpp:106] Iteration 420, lr = 0.00993274
I0605 23:23:06.262727 54715 solver.cpp:237] Iteration 423, loss = 0.448596
I0605 23:23:06.262780 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.483453 (* 1 = 0.483453 loss)
I0605 23:23:06.262791 54715 sgd_solver.cpp:106] Iteration 423, lr = 0.00993226
I0605 23:23:15.634646 54715 solver.cpp:237] Iteration 426, loss = 0.449548
I0605 23:23:15.634698 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.429747 (* 1 = 0.429747 loss)
I0605 23:23:15.634709 54715 sgd_solver.cpp:106] Iteration 426, lr = 0.00993178
I0605 23:23:25.007241 54715 solver.cpp:237] Iteration 429, loss = 0.450169
I0605 23:23:25.007356 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.380523 (* 1 = 0.380523 loss)
I0605 23:23:25.007369 54715 sgd_solver.cpp:106] Iteration 429, lr = 0.0099313
I0605 23:23:25.116585 54715 solver.cpp:341] Iteration 430, Testing net (#0)
I0605 23:23:26.396822 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.753081
I0605 23:23:26.396869 54715 solver.cpp:409] Test net output #1: class_Acc = 0.93802
I0605 23:23:26.396876 54715 solver.cpp:409] Test net output #2: class_Acc = 0.311392
I0605 23:23:26.396886 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.511101 (* 1 = 0.511101 loss)
I0605 23:23:35.660951 54715 solver.cpp:237] Iteration 432, loss = 0.448204
I0605 23:23:35.661003 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.422956 (* 1 = 0.422956 loss)
I0605 23:23:35.661013 54715 sgd_solver.cpp:106] Iteration 432, lr = 0.00993082
I0605 23:23:45.031935 54715 solver.cpp:237] Iteration 435, loss = 0.449198
I0605 23:23:45.031978 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.401569 (* 1 = 0.401569 loss)
I0605 23:23:45.031989 54715 sgd_solver.cpp:106] Iteration 435, lr = 0.00993034
I0605 23:23:54.402184 54715 solver.cpp:237] Iteration 438, loss = 0.44712
I0605 23:23:54.402242 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.398508 (* 1 = 0.398508 loss)
I0605 23:23:54.402257 54715 sgd_solver.cpp:106] Iteration 438, lr = 0.00992986
I0605 23:23:57.636514 54715 solver.cpp:341] Iteration 440, Testing net (#0)
I0605 23:23:58.915244 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.766772
I0605 23:23:58.915288 54715 solver.cpp:409] Test net output #1: class_Acc = 0.940733
I0605 23:23:58.915295 54715 solver.cpp:409] Test net output #2: class_Acc = 0.30959
I0605 23:23:58.915305 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.482253 (* 1 = 0.482253 loss)
I0605 23:24:05.052026 54715 solver.cpp:237] Iteration 441, loss = 0.44791
I0605 23:24:05.052081 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.41693 (* 1 = 0.41693 loss)
I0605 23:24:05.052093 54715 sgd_solver.cpp:106] Iteration 441, lr = 0.00992938
I0605 23:24:12.677798 54715 softmax_loss_layer.cu:194] weight loss 0 =0.432368 weight loss 1 =1 weight loss 2 =0
I0605 23:24:14.422549 54715 solver.cpp:237] Iteration 444, loss = 0.442941
I0605 23:24:14.422597 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.419855 (* 1 = 0.419855 loss)
I0605 23:24:14.422607 54715 sgd_solver.cpp:106] Iteration 444, lr = 0.0099289
I0605 23:24:23.792937 54715 solver.cpp:237] Iteration 447, loss = 0.443548
I0605 23:24:23.792994 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.46298 (* 1 = 0.46298 loss)
I0605 23:24:23.793004 54715 sgd_solver.cpp:106] Iteration 447, lr = 0.00992842
I0605 23:24:30.152485 54715 solver.cpp:341] Iteration 450, Testing net (#0)
I0605 23:24:31.432162 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.744351
I0605 23:24:31.432205 54715 solver.cpp:409] Test net output #1: class_Acc = 0.923132
I0605 23:24:31.432212 54715 solver.cpp:409] Test net output #2: class_Acc = 0.350286
I0605 23:24:31.432222 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.54976 (* 1 = 0.54976 loss)
I0605 23:24:34.444710 54715 solver.cpp:237] Iteration 450, loss = 0.444661
I0605 23:24:34.444762 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.409518 (* 1 = 0.409518 loss)
I0605 23:24:34.444772 54715 sgd_solver.cpp:106] Iteration 450, lr = 0.00992793
I0605 23:24:43.817138 54715 solver.cpp:237] Iteration 453, loss = 0.444901
I0605 23:24:43.817184 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.511399 (* 1 = 0.511399 loss)
I0605 23:24:43.817196 54715 sgd_solver.cpp:106] Iteration 453, lr = 0.00992745
I0605 23:24:53.188196 54715 solver.cpp:237] Iteration 456, loss = 0.443116
I0605 23:24:53.188246 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.378974 (* 1 = 0.378974 loss)
I0605 23:24:53.188256 54715 sgd_solver.cpp:106] Iteration 456, lr = 0.00992697
I0605 23:25:02.561290 54715 solver.cpp:237] Iteration 459, loss = 0.447827
I0605 23:25:02.561429 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.493509 (* 1 = 0.493509 loss)
I0605 23:25:02.561441 54715 sgd_solver.cpp:106] Iteration 459, lr = 0.00992649
I0605 23:25:02.670805 54715 solver.cpp:341] Iteration 460, Testing net (#0)
I0605 23:25:03.950812 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.73334
I0605 23:25:03.950855 54715 solver.cpp:409] Test net output #1: class_Acc = 0.892485
I0605 23:25:03.950861 54715 solver.cpp:409] Test net output #2: class_Acc = 0.381021
I0605 23:25:03.950871 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.520097 (* 1 = 0.520097 loss)
I0605 23:25:13.214287 54715 solver.cpp:237] Iteration 462, loss = 0.447512
I0605 23:25:13.214336 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.41069 (* 1 = 0.41069 loss)
I0605 23:25:13.214346 54715 sgd_solver.cpp:106] Iteration 462, lr = 0.00992601
I0605 23:25:22.590194 54715 solver.cpp:237] Iteration 465, loss = 0.448185
I0605 23:25:22.590245 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.433773 (* 1 = 0.433773 loss)
I0605 23:25:22.590256 54715 sgd_solver.cpp:106] Iteration 465, lr = 0.00992553
I0605 23:25:31.964856 54715 solver.cpp:237] Iteration 468, loss = 0.451674
I0605 23:25:31.964905 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.408522 (* 1 = 0.408522 loss)
I0605 23:25:31.964916 54715 sgd_solver.cpp:106] Iteration 468, lr = 0.00992505
I0605 23:25:35.200309 54715 solver.cpp:341] Iteration 470, Testing net (#0)
I0605 23:25:36.480674 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.74155
I0605 23:25:36.480713 54715 solver.cpp:409] Test net output #1: class_Acc = 0.87711
I0605 23:25:36.480720 54715 solver.cpp:409] Test net output #2: class_Acc = 0.437992
I0605 23:25:36.480729 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.513776 (* 1 = 0.513776 loss)
I0605 23:25:42.619251 54715 solver.cpp:237] Iteration 471, loss = 0.445062
I0605 23:25:42.619292 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.416155 (* 1 = 0.416155 loss)
I0605 23:25:42.619302 54715 sgd_solver.cpp:106] Iteration 471, lr = 0.00992457
I0605 23:25:51.995107 54715 solver.cpp:237] Iteration 474, loss = 0.443608
I0605 23:25:51.995154 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.43786 (* 1 = 0.43786 loss)
I0605 23:25:51.995164 54715 sgd_solver.cpp:106] Iteration 474, lr = 0.00992409
I0605 23:26:01.369693 54715 solver.cpp:237] Iteration 477, loss = 0.443188
I0605 23:26:01.369747 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.418867 (* 1 = 0.418867 loss)
I0605 23:26:01.369757 54715 sgd_solver.cpp:106] Iteration 477, lr = 0.00992361
I0605 23:26:07.731146 54715 solver.cpp:341] Iteration 480, Testing net (#0)
I0605 23:26:09.012735 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.765776
I0605 23:26:09.012781 54715 solver.cpp:409] Test net output #1: class_Acc = 0.908673
I0605 23:26:09.012789 54715 solver.cpp:409] Test net output #2: class_Acc = 0.418619
I0605 23:26:09.012799 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.471067 (* 1 = 0.471067 loss)
I0605 23:26:12.027211 54715 solver.cpp:237] Iteration 480, loss = 0.442171
I0605 23:26:12.027261 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.462402 (* 1 = 0.462402 loss)
I0605 23:26:12.027271 54715 sgd_solver.cpp:106] Iteration 480, lr = 0.00992313
I0605 23:26:21.403259 54715 solver.cpp:237] Iteration 483, loss = 0.440558
I0605 23:26:21.403312 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.51069 (* 1 = 0.51069 loss)
I0605 23:26:21.403322 54715 sgd_solver.cpp:106] Iteration 483, lr = 0.00992265
I0605 23:26:30.779785 54715 solver.cpp:237] Iteration 486, loss = 0.44164
I0605 23:26:30.779835 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.442288 (* 1 = 0.442288 loss)
I0605 23:26:30.779846 54715 sgd_solver.cpp:106] Iteration 486, lr = 0.00992216
I0605 23:26:40.150138 54715 solver.cpp:237] Iteration 489, loss = 0.443336
I0605 23:26:40.150259 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.448695 (* 1 = 0.448695 loss)
I0605 23:26:40.150276 54715 sgd_solver.cpp:106] Iteration 489, lr = 0.00992168
I0605 23:26:40.259518 54715 solver.cpp:341] Iteration 490, Testing net (#0)
I0605 23:26:41.539016 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.727892
I0605 23:26:41.539058 54715 solver.cpp:409] Test net output #1: class_Acc = 0.875286
I0605 23:26:41.539067 54715 solver.cpp:409] Test net output #2: class_Acc = 0.393948
I0605 23:26:41.539077 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.582534 (* 1 = 0.582534 loss)
I0605 23:26:50.806567 54715 solver.cpp:237] Iteration 492, loss = 0.440881
I0605 23:26:50.806614 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.456406 (* 1 = 0.456406 loss)
I0605 23:26:50.806625 54715 sgd_solver.cpp:106] Iteration 492, lr = 0.0099212
I0605 23:27:00.179659 54715 solver.cpp:237] Iteration 495, loss = 0.440076
I0605 23:27:00.179718 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.433485 (* 1 = 0.433485 loss)
I0605 23:27:00.179729 54715 sgd_solver.cpp:106] Iteration 495, lr = 0.00992072
I0605 23:27:09.552428 54715 solver.cpp:237] Iteration 498, loss = 0.440911
I0605 23:27:09.552477 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.392915 (* 1 = 0.392915 loss)
I0605 23:27:09.552489 54715 sgd_solver.cpp:106] Iteration 498, lr = 0.00992024
I0605 23:27:12.788091 54715 solver.cpp:341] Iteration 500, Testing net (#0)
I0605 23:27:14.068574 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.750634
I0605 23:27:14.068615 54715 solver.cpp:409] Test net output #1: class_Acc = 0.920689
I0605 23:27:14.068621 54715 solver.cpp:409] Test net output #2: class_Acc = 0.352794
I0605 23:27:14.068631 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.496534 (* 1 = 0.496534 loss)
I0605 23:27:20.206449 54715 solver.cpp:237] Iteration 501, loss = 0.438172
I0605 23:27:20.206498 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.427028 (* 1 = 0.427028 loss)
I0605 23:27:20.206508 54715 sgd_solver.cpp:106] Iteration 501, lr = 0.00991976
I0605 23:27:29.581779 54715 solver.cpp:237] Iteration 504, loss = 0.435613
I0605 23:27:29.581830 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.381464 (* 1 = 0.381464 loss)
I0605 23:27:29.581840 54715 sgd_solver.cpp:106] Iteration 504, lr = 0.00991928
I0605 23:27:34.472848 54715 softmax_loss_layer.cu:194] weight loss 0 =0.269624 weight loss 1 =1 weight loss 2 =0
I0605 23:27:38.954965 54715 solver.cpp:237] Iteration 507, loss = 0.436594
I0605 23:27:38.955015 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.392387 (* 1 = 0.392387 loss)
I0605 23:27:38.955026 54715 sgd_solver.cpp:106] Iteration 507, lr = 0.0099188
I0605 23:27:45.312546 54715 solver.cpp:341] Iteration 510, Testing net (#0)
I0605 23:27:46.591488 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.721031
I0605 23:27:46.591532 54715 solver.cpp:409] Test net output #1: class_Acc = 0.945296
I0605 23:27:46.591539 54715 solver.cpp:409] Test net output #2: class_Acc = 0.167547
I0605 23:27:46.591549 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.646255 (* 1 = 0.646255 loss)
I0605 23:27:49.603469 54715 solver.cpp:237] Iteration 510, loss = 0.434333
I0605 23:27:49.603515 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.435617 (* 1 = 0.435617 loss)
I0605 23:27:49.603528 54715 sgd_solver.cpp:106] Iteration 510, lr = 0.00991832
I0605 23:27:58.975226 54715 solver.cpp:237] Iteration 513, loss = 0.436714
I0605 23:27:58.975280 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.375105 (* 1 = 0.375105 loss)
I0605 23:27:58.975291 54715 sgd_solver.cpp:106] Iteration 513, lr = 0.00991784
I0605 23:28:08.347723 54715 solver.cpp:237] Iteration 516, loss = 0.436652
I0605 23:28:08.347776 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.44553 (* 1 = 0.44553 loss)
I0605 23:28:08.347787 54715 sgd_solver.cpp:106] Iteration 516, lr = 0.00991735
I0605 23:28:11.283537 54715 softmax_loss_layer.cu:194] weight loss 0 =0.454595 weight loss 1 =1 weight loss 2 =0
I0605 23:28:17.721480 54715 solver.cpp:237] Iteration 519, loss = 0.436914
I0605 23:28:17.721585 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.398812 (* 1 = 0.398812 loss)
I0605 23:28:17.721596 54715 sgd_solver.cpp:106] Iteration 519, lr = 0.00991687
I0605 23:28:17.830937 54715 solver.cpp:341] Iteration 520, Testing net (#0)
I0605 23:28:19.110191 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.739484
I0605 23:28:19.110235 54715 solver.cpp:409] Test net output #1: class_Acc = 0.930538
I0605 23:28:19.110241 54715 solver.cpp:409] Test net output #2: class_Acc = 0.388059
I0605 23:28:19.110251 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.50962 (* 1 = 0.50962 loss)
I0605 23:28:28.374064 54715 solver.cpp:237] Iteration 522, loss = 0.436365
I0605 23:28:28.374115 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.408007 (* 1 = 0.408007 loss)
I0605 23:28:28.374126 54715 sgd_solver.cpp:106] Iteration 522, lr = 0.00991639
I0605 23:28:37.745268 54715 solver.cpp:237] Iteration 525, loss = 0.4394
I0605 23:28:37.745321 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.411203 (* 1 = 0.411203 loss)
I0605 23:28:37.745332 54715 sgd_solver.cpp:106] Iteration 525, lr = 0.00991591
I0605 23:28:47.119850 54715 solver.cpp:237] Iteration 528, loss = 0.432739
I0605 23:28:47.119902 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.436209 (* 1 = 0.436209 loss)
I0605 23:28:47.119913 54715 sgd_solver.cpp:106] Iteration 528, lr = 0.00991543
I0605 23:28:50.354533 54715 solver.cpp:341] Iteration 530, Testing net (#0)
I0605 23:28:51.634656 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.751754
I0605 23:28:51.634701 54715 solver.cpp:409] Test net output #1: class_Acc = 0.926177
I0605 23:28:51.634709 54715 solver.cpp:409] Test net output #2: class_Acc = 0.368597
I0605 23:28:51.634718 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.506659 (* 1 = 0.506659 loss)
I0605 23:28:57.774436 54715 solver.cpp:237] Iteration 531, loss = 0.433426
I0605 23:28:57.774487 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.394302 (* 1 = 0.394302 loss)
I0605 23:28:57.774497 54715 sgd_solver.cpp:106] Iteration 531, lr = 0.00991495
I0605 23:29:07.144922 54715 solver.cpp:237] Iteration 534, loss = 0.431585
I0605 23:29:07.144973 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.427913 (* 1 = 0.427913 loss)
I0605 23:29:07.144984 54715 sgd_solver.cpp:106] Iteration 534, lr = 0.00991447
I0605 23:29:16.516858 54715 solver.cpp:237] Iteration 537, loss = 0.431399
I0605 23:29:16.516909 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.424783 (* 1 = 0.424783 loss)
I0605 23:29:16.516921 54715 sgd_solver.cpp:106] Iteration 537, lr = 0.00991399
I0605 23:29:22.876410 54715 solver.cpp:341] Iteration 540, Testing net (#0)
I0605 23:29:24.157398 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.757854
I0605 23:29:24.157444 54715 solver.cpp:409] Test net output #1: class_Acc = 0.906519
I0605 23:29:24.157450 54715 solver.cpp:409] Test net output #2: class_Acc = 0.417669
I0605 23:29:24.157460 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.491431 (* 1 = 0.491431 loss)
I0605 23:29:27.169919 54715 solver.cpp:237] Iteration 540, loss = 0.42899
I0605 23:29:27.169971 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350005 (* 1 = 0.350005 loss)
I0605 23:29:27.169982 54715 sgd_solver.cpp:106] Iteration 540, lr = 0.00991351
I0605 23:29:36.543696 54715 solver.cpp:237] Iteration 543, loss = 0.430149
I0605 23:29:36.543727 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.434718 (* 1 = 0.434718 loss)
I0605 23:29:36.543737 54715 sgd_solver.cpp:106] Iteration 543, lr = 0.00991302
I0605 23:29:45.916448 54715 solver.cpp:237] Iteration 546, loss = 0.426937
I0605 23:29:45.916497 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.422072 (* 1 = 0.422072 loss)
I0605 23:29:45.916508 54715 sgd_solver.cpp:106] Iteration 546, lr = 0.00991254
I0605 23:29:55.292220 54715 solver.cpp:237] Iteration 549, loss = 0.425661
I0605 23:29:55.292315 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.474839 (* 1 = 0.474839 loss)
I0605 23:29:55.292326 54715 sgd_solver.cpp:106] Iteration 549, lr = 0.00991206
I0605 23:29:55.401736 54715 solver.cpp:341] Iteration 550, Testing net (#0)
I0605 23:29:56.681715 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.740381
I0605 23:29:56.681761 54715 solver.cpp:409] Test net output #1: class_Acc = 0.934927
I0605 23:29:56.681768 54715 solver.cpp:409] Test net output #2: class_Acc = 0.309554
I0605 23:29:56.681778 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.537817 (* 1 = 0.537817 loss)
I0605 23:29:57.172273 54715 softmax_loss_layer.cu:194] weight loss 0 =0.262648 weight loss 1 =1 weight loss 2 =0
I0605 23:30:05.947582 54715 solver.cpp:237] Iteration 552, loss = 0.42684
I0605 23:30:05.947634 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.428814 (* 1 = 0.428814 loss)
I0605 23:30:05.947645 54715 sgd_solver.cpp:106] Iteration 552, lr = 0.00991158
I0605 23:30:15.322263 54715 solver.cpp:237] Iteration 555, loss = 0.424359
I0605 23:30:15.322309 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.387746 (* 1 = 0.387746 loss)
I0605 23:30:15.322321 54715 sgd_solver.cpp:106] Iteration 555, lr = 0.0099111
I0605 23:30:24.694097 54715 solver.cpp:237] Iteration 558, loss = 0.428024
I0605 23:30:24.694126 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.477839 (* 1 = 0.477839 loss)
I0605 23:30:24.694135 54715 sgd_solver.cpp:106] Iteration 558, lr = 0.00991062
I0605 23:30:27.929281 54715 solver.cpp:341] Iteration 560, Testing net (#0)
I0605 23:30:29.209017 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.739168
I0605 23:30:29.209059 54715 solver.cpp:409] Test net output #1: class_Acc = 0.89549
I0605 23:30:29.209066 54715 solver.cpp:409] Test net output #2: class_Acc = 0.357205
I0605 23:30:29.209076 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.534549 (* 1 = 0.534549 loss)
I0605 23:30:35.349550 54715 solver.cpp:237] Iteration 561, loss = 0.431611
I0605 23:30:35.349601 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.420837 (* 1 = 0.420837 loss)
I0605 23:30:35.349611 54715 sgd_solver.cpp:106] Iteration 561, lr = 0.00991014
I0605 23:30:44.722856 54715 solver.cpp:237] Iteration 564, loss = 0.434254
I0605 23:30:44.722908 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.411108 (* 1 = 0.411108 loss)
I0605 23:30:44.722918 54715 sgd_solver.cpp:106] Iteration 564, lr = 0.00990966
I0605 23:30:54.098645 54715 solver.cpp:237] Iteration 567, loss = 0.431979
I0605 23:30:54.098695 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.398894 (* 1 = 0.398894 loss)
I0605 23:30:54.098706 54715 sgd_solver.cpp:106] Iteration 567, lr = 0.00990918
I0605 23:31:00.456290 54715 solver.cpp:341] Iteration 570, Testing net (#0)
I0605 23:31:01.739254 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.765464
I0605 23:31:01.739295 54715 solver.cpp:409] Test net output #1: class_Acc = 0.89402
I0605 23:31:01.739301 54715 solver.cpp:409] Test net output #2: class_Acc = 0.448464
I0605 23:31:01.739311 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.474927 (* 1 = 0.474927 loss)
I0605 23:31:04.751076 54715 solver.cpp:237] Iteration 570, loss = 0.430262
I0605 23:31:04.751121 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.373808 (* 1 = 0.373808 loss)
I0605 23:31:04.751133 54715 sgd_solver.cpp:106] Iteration 570, lr = 0.0099087
I0605 23:31:14.122679 54715 solver.cpp:237] Iteration 573, loss = 0.431702
I0605 23:31:14.122730 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360169 (* 1 = 0.360169 loss)
I0605 23:31:14.122740 54715 sgd_solver.cpp:106] Iteration 573, lr = 0.00990821
I0605 23:31:23.496127 54715 solver.cpp:237] Iteration 576, loss = 0.429569
I0605 23:31:23.496191 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.462678 (* 1 = 0.462678 loss)
I0605 23:31:23.496212 54715 sgd_solver.cpp:106] Iteration 576, lr = 0.00990773
I0605 23:31:32.867853 54715 solver.cpp:237] Iteration 579, loss = 0.428334
I0605 23:31:32.867952 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.428113 (* 1 = 0.428113 loss)
I0605 23:31:32.867964 54715 sgd_solver.cpp:106] Iteration 579, lr = 0.00990725
I0605 23:31:32.977298 54715 solver.cpp:341] Iteration 580, Testing net (#0)
I0605 23:31:34.255568 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.748623
I0605 23:31:34.255614 54715 solver.cpp:409] Test net output #1: class_Acc = 0.938444
I0605 23:31:34.255620 54715 solver.cpp:409] Test net output #2: class_Acc = 0.269319
I0605 23:31:34.255630 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.537195 (* 1 = 0.537195 loss)
I0605 23:31:43.517714 54715 solver.cpp:237] Iteration 582, loss = 0.432281
I0605 23:31:43.517763 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.391622 (* 1 = 0.391622 loss)
I0605 23:31:43.517773 54715 sgd_solver.cpp:106] Iteration 582, lr = 0.00990677
I0605 23:31:52.891198 54715 solver.cpp:237] Iteration 585, loss = 0.430209
I0605 23:31:52.891247 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351854 (* 1 = 0.351854 loss)
I0605 23:31:52.891258 54715 sgd_solver.cpp:106] Iteration 585, lr = 0.00990629
I0605 23:32:02.262125 54715 solver.cpp:237] Iteration 588, loss = 0.427026
I0605 23:32:02.262176 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.407974 (* 1 = 0.407974 loss)
I0605 23:32:02.262187 54715 sgd_solver.cpp:106] Iteration 588, lr = 0.00990581
I0605 23:32:05.497553 54715 solver.cpp:341] Iteration 590, Testing net (#0)
I0605 23:32:06.777917 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.748366
I0605 23:32:06.777964 54715 solver.cpp:409] Test net output #1: class_Acc = 0.936031
I0605 23:32:06.777971 54715 solver.cpp:409] Test net output #2: class_Acc = 0.311727
I0605 23:32:06.777981 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.520854 (* 1 = 0.520854 loss)
I0605 23:32:12.915189 54715 solver.cpp:237] Iteration 591, loss = 0.426085
I0605 23:32:12.915237 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.448918 (* 1 = 0.448918 loss)
I0605 23:32:12.915249 54715 sgd_solver.cpp:106] Iteration 591, lr = 0.00990533
I0605 23:32:20.929229 54715 softmax_loss_layer.cu:194] weight loss 0 =0.248403 weight loss 1 =1 weight loss 2 =0
I0605 23:32:22.285064 54715 solver.cpp:237] Iteration 594, loss = 0.427354
I0605 23:32:22.285112 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.405828 (* 1 = 0.405828 loss)
I0605 23:32:22.285122 54715 sgd_solver.cpp:106] Iteration 594, lr = 0.00990485
I0605 23:32:31.658912 54715 solver.cpp:237] Iteration 597, loss = 0.425793
I0605 23:32:31.658962 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.406265 (* 1 = 0.406265 loss)
I0605 23:32:31.658972 54715 sgd_solver.cpp:106] Iteration 597, lr = 0.00990437
I0605 23:32:38.015903 54715 solver.cpp:341] Iteration 600, Testing net (#0)
I0605 23:32:39.296368 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.753151
I0605 23:32:39.296412 54715 solver.cpp:409] Test net output #1: class_Acc = 0.930875
I0605 23:32:39.296419 54715 solver.cpp:409] Test net output #2: class_Acc = 0.354482
I0605 23:32:39.296429 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.496833 (* 1 = 0.496833 loss)
I0605 23:32:42.310878 54715 solver.cpp:237] Iteration 600, loss = 0.424031
I0605 23:32:42.310927 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.415755 (* 1 = 0.415755 loss)
I0605 23:32:42.310938 54715 sgd_solver.cpp:106] Iteration 600, lr = 0.00990388
I0605 23:32:51.682834 54715 solver.cpp:237] Iteration 603, loss = 0.424976
I0605 23:32:51.682881 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.374847 (* 1 = 0.374847 loss)
I0605 23:32:51.682893 54715 sgd_solver.cpp:106] Iteration 603, lr = 0.0099034
I0605 23:32:59.700955 54715 softmax_loss_layer.cu:194] weight loss 0 =0.258758 weight loss 1 =1 weight loss 2 =0
I0605 23:33:01.057904 54715 solver.cpp:237] Iteration 606, loss = 0.422061
I0605 23:33:01.057955 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.362045 (* 1 = 0.362045 loss)
I0605 23:33:01.057965 54715 sgd_solver.cpp:106] Iteration 606, lr = 0.00990292
I0605 23:33:10.427592 54715 solver.cpp:237] Iteration 609, loss = 0.420978
I0605 23:33:10.427695 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.373072 (* 1 = 0.373072 loss)
I0605 23:33:10.427706 54715 sgd_solver.cpp:106] Iteration 609, lr = 0.00990244
I0605 23:33:10.537082 54715 solver.cpp:341] Iteration 610, Testing net (#0)
I0605 23:33:11.817072 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.741414
I0605 23:33:11.817116 54715 solver.cpp:409] Test net output #1: class_Acc = 0.926467
I0605 23:33:11.817122 54715 solver.cpp:409] Test net output #2: class_Acc = 0.309421
I0605 23:33:11.817132 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.546626 (* 1 = 0.546626 loss)
I0605 23:33:21.083410 54715 solver.cpp:237] Iteration 612, loss = 0.420662
I0605 23:33:21.083456 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.389991 (* 1 = 0.389991 loss)
I0605 23:33:21.083467 54715 sgd_solver.cpp:106] Iteration 612, lr = 0.00990196
I0605 23:33:30.455325 54715 solver.cpp:237] Iteration 615, loss = 0.419274
I0605 23:33:30.455375 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.36372 (* 1 = 0.36372 loss)
I0605 23:33:30.455386 54715 sgd_solver.cpp:106] Iteration 615, lr = 0.00990148
I0605 23:33:39.828963 54715 solver.cpp:237] Iteration 618, loss = 0.419304
I0605 23:33:39.829016 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.384442 (* 1 = 0.384442 loss)
I0605 23:33:39.829026 54715 sgd_solver.cpp:106] Iteration 618, lr = 0.009901
I0605 23:33:43.065507 54715 solver.cpp:341] Iteration 620, Testing net (#0)
I0605 23:33:44.347333 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.769159
I0605 23:33:44.347378 54715 solver.cpp:409] Test net output #1: class_Acc = 0.887205
I0605 23:33:44.347385 54715 solver.cpp:409] Test net output #2: class_Acc = 0.515761
I0605 23:33:44.347395 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.476081 (* 1 = 0.476081 loss)
I0605 23:33:50.486578 54715 solver.cpp:237] Iteration 621, loss = 0.418247
I0605 23:33:50.486629 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.448308 (* 1 = 0.448308 loss)
I0605 23:33:50.486639 54715 sgd_solver.cpp:106] Iteration 621, lr = 0.00990052
I0605 23:33:59.857587 54715 solver.cpp:237] Iteration 624, loss = 0.41771
I0605 23:33:59.857642 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.414369 (* 1 = 0.414369 loss)
I0605 23:33:59.857653 54715 sgd_solver.cpp:106] Iteration 624, lr = 0.00990003
I0605 23:34:09.231562 54715 solver.cpp:237] Iteration 627, loss = 0.413319
I0605 23:34:09.231616 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.406462 (* 1 = 0.406462 loss)
I0605 23:34:09.231627 54715 sgd_solver.cpp:106] Iteration 627, lr = 0.00989955
I0605 23:34:15.589361 54715 solver.cpp:341] Iteration 630, Testing net (#0)
I0605 23:34:16.870585 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.778155
I0605 23:34:16.870630 54715 solver.cpp:409] Test net output #1: class_Acc = 0.903961
I0605 23:34:16.870636 54715 solver.cpp:409] Test net output #2: class_Acc = 0.485399
I0605 23:34:16.870646 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.454585 (* 1 = 0.454585 loss)
I0605 23:34:19.883292 54715 solver.cpp:237] Iteration 630, loss = 0.412969
I0605 23:34:19.883344 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.413993 (* 1 = 0.413993 loss)
I0605 23:34:19.883357 54715 sgd_solver.cpp:106] Iteration 630, lr = 0.00989907
I0605 23:34:29.255726 54715 solver.cpp:237] Iteration 633, loss = 0.412134
I0605 23:34:29.255779 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.449688 (* 1 = 0.449688 loss)
I0605 23:34:29.255800 54715 sgd_solver.cpp:106] Iteration 633, lr = 0.00989859
I0605 23:34:38.626471 54715 solver.cpp:237] Iteration 636, loss = 0.416669
I0605 23:34:38.626526 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.397711 (* 1 = 0.397711 loss)
I0605 23:34:38.626536 54715 sgd_solver.cpp:106] Iteration 636, lr = 0.00989811
I0605 23:34:48.003033 54715 solver.cpp:237] Iteration 639, loss = 0.415985
I0605 23:34:48.003165 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.425516 (* 1 = 0.425516 loss)
I0605 23:34:48.003177 54715 sgd_solver.cpp:106] Iteration 639, lr = 0.00989763
I0605 23:34:48.112458 54715 solver.cpp:341] Iteration 640, Testing net (#0)
I0605 23:34:49.393847 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.76732
I0605 23:34:49.393890 54715 solver.cpp:409] Test net output #1: class_Acc = 0.850033
I0605 23:34:49.393898 54715 solver.cpp:409] Test net output #2: class_Acc = 0.560379
I0605 23:34:49.393908 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.483476 (* 1 = 0.483476 loss)
I0605 23:34:58.656700 54715 solver.cpp:237] Iteration 642, loss = 0.414672
I0605 23:34:58.656749 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.421658 (* 1 = 0.421658 loss)
I0605 23:34:58.656760 54715 sgd_solver.cpp:106] Iteration 642, lr = 0.00989715
I0605 23:35:08.029939 54715 solver.cpp:237] Iteration 645, loss = 0.415778
I0605 23:35:08.029990 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.418398 (* 1 = 0.418398 loss)
I0605 23:35:08.030001 54715 sgd_solver.cpp:106] Iteration 645, lr = 0.00989667
I0605 23:35:17.405403 54715 solver.cpp:237] Iteration 648, loss = 0.416656
I0605 23:35:17.405453 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.4033 (* 1 = 0.4033 loss)
I0605 23:35:17.405464 54715 sgd_solver.cpp:106] Iteration 648, lr = 0.00989618
I0605 23:35:20.640262 54715 solver.cpp:341] Iteration 650, Testing net (#0)
I0605 23:35:21.921056 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.778275
I0605 23:35:21.921100 54715 solver.cpp:409] Test net output #1: class_Acc = 0.905543
I0605 23:35:21.921108 54715 solver.cpp:409] Test net output #2: class_Acc = 0.453052
I0605 23:35:21.921118 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.467973 (* 1 = 0.467973 loss)
I0605 23:35:28.059464 54715 solver.cpp:237] Iteration 651, loss = 0.41455
I0605 23:35:28.059496 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.379999 (* 1 = 0.379999 loss)
I0605 23:35:28.059507 54715 sgd_solver.cpp:106] Iteration 651, lr = 0.0098957
I0605 23:35:37.437954 54715 solver.cpp:237] Iteration 654, loss = 0.412286
I0605 23:35:37.438000 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.42691 (* 1 = 0.42691 loss)
I0605 23:35:37.438010 54715 sgd_solver.cpp:106] Iteration 654, lr = 0.00989522
I0605 23:35:46.809432 54715 solver.cpp:237] Iteration 657, loss = 0.414959
I0605 23:35:46.809481 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.402359 (* 1 = 0.402359 loss)
I0605 23:35:46.809492 54715 sgd_solver.cpp:106] Iteration 657, lr = 0.00989474
I0605 23:35:53.169164 54715 solver.cpp:341] Iteration 660, Testing net (#0)
I0605 23:35:54.452049 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.788716
I0605 23:35:54.452091 54715 solver.cpp:409] Test net output #1: class_Acc = 0.868905
I0605 23:35:54.452098 54715 solver.cpp:409] Test net output #2: class_Acc = 0.615393
I0605 23:35:54.452108 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.44733 (* 1 = 0.44733 loss)
I0605 23:35:57.463992 54715 solver.cpp:237] Iteration 660, loss = 0.410561
I0605 23:35:57.464042 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345665 (* 1 = 0.345665 loss)
I0605 23:35:57.464053 54715 sgd_solver.cpp:106] Iteration 660, lr = 0.00989426
I0605 23:36:06.836700 54715 solver.cpp:237] Iteration 663, loss = 0.409594
I0605 23:36:06.836748 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.402514 (* 1 = 0.402514 loss)
I0605 23:36:06.836771 54715 sgd_solver.cpp:106] Iteration 663, lr = 0.00989378
I0605 23:36:16.207582 54715 solver.cpp:237] Iteration 666, loss = 0.409587
I0605 23:36:16.207612 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360475 (* 1 = 0.360475 loss)
I0605 23:36:16.207623 54715 sgd_solver.cpp:106] Iteration 666, lr = 0.0098933
I0605 23:36:25.582763 54715 solver.cpp:237] Iteration 669, loss = 0.412929
I0605 23:36:25.582895 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395545 (* 1 = 0.395545 loss)
I0605 23:36:25.582907 54715 sgd_solver.cpp:106] Iteration 669, lr = 0.00989282
I0605 23:36:25.692102 54715 solver.cpp:341] Iteration 670, Testing net (#0)
I0605 23:36:26.973069 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.77762
I0605 23:36:26.973111 54715 solver.cpp:409] Test net output #1: class_Acc = 0.931085
I0605 23:36:26.973119 54715 solver.cpp:409] Test net output #2: class_Acc = 0.435199
I0605 23:36:26.973129 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.471081 (* 1 = 0.471081 loss)
I0605 23:36:32.146579 54715 softmax_loss_layer.cu:194] weight loss 0 =0.228702 weight loss 1 =1 weight loss 2 =0
I0605 23:36:36.239006 54715 solver.cpp:237] Iteration 672, loss = 0.412034
I0605 23:36:36.239059 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.450903 (* 1 = 0.450903 loss)
I0605 23:36:36.239070 54715 sgd_solver.cpp:106] Iteration 672, lr = 0.00989233
I0605 23:36:45.611547 54715 solver.cpp:237] Iteration 675, loss = 0.413334
I0605 23:36:45.611598 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.430506 (* 1 = 0.430506 loss)
I0605 23:36:45.611608 54715 sgd_solver.cpp:106] Iteration 675, lr = 0.00989185
I0605 23:36:54.986657 54715 solver.cpp:237] Iteration 678, loss = 0.415679
I0605 23:36:54.986706 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.402626 (* 1 = 0.402626 loss)
I0605 23:36:54.986716 54715 sgd_solver.cpp:106] Iteration 678, lr = 0.00989137
I0605 23:36:58.220804 54715 solver.cpp:341] Iteration 680, Testing net (#0)
I0605 23:36:59.502831 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.780173
I0605 23:36:59.502876 54715 solver.cpp:409] Test net output #1: class_Acc = 0.916206
I0605 23:36:59.502883 54715 solver.cpp:409] Test net output #2: class_Acc = 0.44479
I0605 23:36:59.502893 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.456916 (* 1 = 0.456916 loss)
I0605 23:37:05.642411 54715 solver.cpp:237] Iteration 681, loss = 0.414528
I0605 23:37:05.642463 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.428857 (* 1 = 0.428857 loss)
I0605 23:37:05.642474 54715 sgd_solver.cpp:106] Iteration 681, lr = 0.00989089
I0605 23:37:15.020448 54715 solver.cpp:237] Iteration 684, loss = 0.413592
I0605 23:37:15.020498 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.443344 (* 1 = 0.443344 loss)
I0605 23:37:15.020509 54715 sgd_solver.cpp:106] Iteration 684, lr = 0.00989041
I0605 23:37:24.397349 54715 solver.cpp:237] Iteration 687, loss = 0.410889
I0605 23:37:24.397399 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.356569 (* 1 = 0.356569 loss)
I0605 23:37:24.397410 54715 sgd_solver.cpp:106] Iteration 687, lr = 0.00988993
I0605 23:37:30.755384 54715 solver.cpp:341] Iteration 690, Testing net (#0)
I0605 23:37:32.034883 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.726094
I0605 23:37:32.034925 54715 solver.cpp:409] Test net output #1: class_Acc = 0.922415
I0605 23:37:32.034934 54715 solver.cpp:409] Test net output #2: class_Acc = 0.235124
I0605 23:37:32.034943 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.614329 (* 1 = 0.614329 loss)
I0605 23:37:35.048074 54715 solver.cpp:237] Iteration 690, loss = 0.412509
I0605 23:37:35.048125 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.49511 (* 1 = 0.49511 loss)
I0605 23:37:35.048136 54715 sgd_solver.cpp:106] Iteration 690, lr = 0.00988945
I0605 23:37:44.421916 54715 solver.cpp:237] Iteration 693, loss = 0.410173
I0605 23:37:44.421977 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.460914 (* 1 = 0.460914 loss)
I0605 23:37:44.422704 54715 sgd_solver.cpp:106] Iteration 693, lr = 0.00988897
I0605 23:37:53.224774 54715 softmax_loss_layer.cu:194] weight loss 0 =0.208262 weight loss 1 =1 weight loss 2 =0
I0605 23:37:53.803884 54715 solver.cpp:237] Iteration 696, loss = 0.407685
I0605 23:37:53.803930 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.381702 (* 1 = 0.381702 loss)
I0605 23:37:53.803941 54715 sgd_solver.cpp:106] Iteration 696, lr = 0.00988848
I0605 23:38:03.178750 54715 solver.cpp:237] Iteration 699, loss = 0.40715
I0605 23:38:03.178844 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.392124 (* 1 = 0.392124 loss)
I0605 23:38:03.178858 54715 sgd_solver.cpp:106] Iteration 699, lr = 0.009888
I0605 23:38:03.288228 54715 solver.cpp:341] Iteration 700, Testing net (#0)
I0605 23:38:04.569048 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.77383
I0605 23:38:04.569093 54715 solver.cpp:409] Test net output #1: class_Acc = 0.936305
I0605 23:38:04.569100 54715 solver.cpp:409] Test net output #2: class_Acc = 0.399004
I0605 23:38:04.569110 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.468625 (* 1 = 0.468625 loss)
I0605 23:38:13.832659 54715 solver.cpp:237] Iteration 702, loss = 0.410945
I0605 23:38:13.832710 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.38514 (* 1 = 0.38514 loss)
I0605 23:38:13.832720 54715 sgd_solver.cpp:106] Iteration 702, lr = 0.00988752
I0605 23:38:23.207712 54715 solver.cpp:237] Iteration 705, loss = 0.412815
I0605 23:38:23.207762 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.434194 (* 1 = 0.434194 loss)
I0605 23:38:23.207773 54715 sgd_solver.cpp:106] Iteration 705, lr = 0.00988704
I0605 23:38:32.585409 54715 solver.cpp:237] Iteration 708, loss = 0.413509
I0605 23:38:32.585461 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.43964 (* 1 = 0.43964 loss)
I0605 23:38:32.585472 54715 sgd_solver.cpp:106] Iteration 708, lr = 0.00988656
I0605 23:38:35.819959 54715 solver.cpp:341] Iteration 710, Testing net (#0)
I0605 23:38:37.102023 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.77138
I0605 23:38:37.102068 54715 solver.cpp:409] Test net output #1: class_Acc = 0.899778
I0605 23:38:37.102075 54715 solver.cpp:409] Test net output #2: class_Acc = 0.50819
I0605 23:38:37.102085 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.478387 (* 1 = 0.478387 loss)
I0605 23:38:43.242486 54715 solver.cpp:237] Iteration 711, loss = 0.412663
I0605 23:38:43.242532 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.41445 (* 1 = 0.41445 loss)
I0605 23:38:43.242543 54715 sgd_solver.cpp:106] Iteration 711, lr = 0.00988608
I0605 23:38:52.617223 54715 solver.cpp:237] Iteration 714, loss = 0.414205
I0605 23:38:52.617274 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.352739 (* 1 = 0.352739 loss)
I0605 23:38:52.617285 54715 sgd_solver.cpp:106] Iteration 714, lr = 0.0098856
I0605 23:39:01.992522 54715 solver.cpp:237] Iteration 717, loss = 0.413973
I0605 23:39:01.992576 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.369594 (* 1 = 0.369594 loss)
I0605 23:39:01.992588 54715 sgd_solver.cpp:106] Iteration 717, lr = 0.00988511
I0605 23:39:08.352286 54715 solver.cpp:341] Iteration 720, Testing net (#0)
I0605 23:39:09.632238 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.761797
I0605 23:39:09.632285 54715 solver.cpp:409] Test net output #1: class_Acc = 0.933079
I0605 23:39:09.632292 54715 solver.cpp:409] Test net output #2: class_Acc = 0.364234
I0605 23:39:09.632302 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.497128 (* 1 = 0.497128 loss)
I0605 23:39:12.644753 54715 solver.cpp:237] Iteration 720, loss = 0.410584
I0605 23:39:12.644801 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.382259 (* 1 = 0.382259 loss)
I0605 23:39:12.644824 54715 sgd_solver.cpp:106] Iteration 720, lr = 0.00988463
I0605 23:39:22.018653 54715 solver.cpp:237] Iteration 723, loss = 0.408552
I0605 23:39:22.018702 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.358999 (* 1 = 0.358999 loss)
I0605 23:39:22.018714 54715 sgd_solver.cpp:106] Iteration 723, lr = 0.00988415
I0605 23:39:31.388538 54715 solver.cpp:237] Iteration 726, loss = 0.407896
I0605 23:39:31.388588 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.380881 (* 1 = 0.380881 loss)
I0605 23:39:31.388600 54715 sgd_solver.cpp:106] Iteration 726, lr = 0.00988367
I0605 23:39:40.761207 54715 solver.cpp:237] Iteration 729, loss = 0.406591
I0605 23:39:40.761348 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.394359 (* 1 = 0.394359 loss)
I0605 23:39:40.761361 54715 sgd_solver.cpp:106] Iteration 729, lr = 0.00988319
I0605 23:39:40.870669 54715 solver.cpp:341] Iteration 730, Testing net (#0)
I0605 23:39:42.152225 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.786272
I0605 23:39:42.152272 54715 solver.cpp:409] Test net output #1: class_Acc = 0.907691
I0605 23:39:42.152279 54715 solver.cpp:409] Test net output #2: class_Acc = 0.485339
I0605 23:39:42.152289 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.447377 (* 1 = 0.447377 loss)
I0605 23:39:51.418241 54715 solver.cpp:237] Iteration 732, loss = 0.406664
I0605 23:39:51.418293 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395149 (* 1 = 0.395149 loss)
I0605 23:39:51.418303 54715 sgd_solver.cpp:106] Iteration 732, lr = 0.00988271
I0605 23:40:00.790588 54715 solver.cpp:237] Iteration 735, loss = 0.405276
I0605 23:40:00.790638 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.419794 (* 1 = 0.419794 loss)
I0605 23:40:00.790649 54715 sgd_solver.cpp:106] Iteration 735, lr = 0.00988223
I0605 23:40:10.162330 54715 solver.cpp:237] Iteration 738, loss = 0.404564
I0605 23:40:10.162374 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.400473 (* 1 = 0.400473 loss)
I0605 23:40:10.162384 54715 sgd_solver.cpp:106] Iteration 738, lr = 0.00988174
I0605 23:40:13.396003 54715 solver.cpp:341] Iteration 740, Testing net (#0)
I0605 23:40:14.676380 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.70293
I0605 23:40:14.676425 54715 solver.cpp:409] Test net output #1: class_Acc = 0.885792
I0605 23:40:14.676432 54715 solver.cpp:409] Test net output #2: class_Acc = 0.270407
I0605 23:40:14.676442 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.627942 (* 1 = 0.627942 loss)
I0605 23:40:20.815129 54715 solver.cpp:237] Iteration 741, loss = 0.404178
I0605 23:40:20.815182 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.401286 (* 1 = 0.401286 loss)
I0605 23:40:20.815193 54715 sgd_solver.cpp:106] Iteration 741, lr = 0.00988126
I0605 23:40:30.189579 54715 solver.cpp:237] Iteration 744, loss = 0.402344
I0605 23:40:30.189635 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.429304 (* 1 = 0.429304 loss)
I0605 23:40:30.189646 54715 sgd_solver.cpp:106] Iteration 744, lr = 0.00988078
I0605 23:40:39.564370 54715 solver.cpp:237] Iteration 747, loss = 0.400508
I0605 23:40:39.564419 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.434151 (* 1 = 0.434151 loss)
I0605 23:40:39.564429 54715 sgd_solver.cpp:106] Iteration 747, lr = 0.0098803
I0605 23:40:45.924427 54715 solver.cpp:341] Iteration 750, Testing net (#0)
I0605 23:40:47.203810 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.767082
I0605 23:40:47.203856 54715 solver.cpp:409] Test net output #1: class_Acc = 0.954872
I0605 23:40:47.203863 54715 solver.cpp:409] Test net output #2: class_Acc = 0.336168
I0605 23:40:47.203873 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.497245 (* 1 = 0.497245 loss)
I0605 23:40:50.218339 54715 solver.cpp:237] Iteration 750, loss = 0.401612
I0605 23:40:50.218391 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.415425 (* 1 = 0.415425 loss)
I0605 23:40:50.218412 54715 sgd_solver.cpp:106] Iteration 750, lr = 0.00987982
I0605 23:40:59.593071 54715 solver.cpp:237] Iteration 753, loss = 0.40113
I0605 23:40:59.593122 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.353743 (* 1 = 0.353743 loss)
I0605 23:40:59.593132 54715 sgd_solver.cpp:106] Iteration 753, lr = 0.00987934
I0605 23:41:08.967799 54715 solver.cpp:237] Iteration 756, loss = 0.396658
I0605 23:41:08.967845 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.341979 (* 1 = 0.341979 loss)
I0605 23:41:08.967857 54715 sgd_solver.cpp:106] Iteration 756, lr = 0.00987886
I0605 23:41:18.339279 54715 solver.cpp:237] Iteration 759, loss = 0.398249
I0605 23:41:18.339412 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.330144 (* 1 = 0.330144 loss)
I0605 23:41:18.339426 54715 sgd_solver.cpp:106] Iteration 759, lr = 0.00987837
I0605 23:41:18.448778 54715 solver.cpp:341] Iteration 760, Testing net (#0)
I0605 23:41:19.730834 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.781836
I0605 23:41:19.730878 54715 solver.cpp:409] Test net output #1: class_Acc = 0.883637
I0605 23:41:19.730885 54715 solver.cpp:409] Test net output #2: class_Acc = 0.52389
I0605 23:41:19.730895 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.465409 (* 1 = 0.465409 loss)
I0605 23:41:28.992794 54715 solver.cpp:237] Iteration 762, loss = 0.399025
I0605 23:41:28.992847 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.398566 (* 1 = 0.398566 loss)
I0605 23:41:28.992858 54715 sgd_solver.cpp:106] Iteration 762, lr = 0.00987789
I0605 23:41:38.365511 54715 solver.cpp:237] Iteration 765, loss = 0.399687
I0605 23:41:38.365558 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.408326 (* 1 = 0.408326 loss)
I0605 23:41:38.365571 54715 sgd_solver.cpp:106] Iteration 765, lr = 0.00987741
I0605 23:41:47.739455 54715 solver.cpp:237] Iteration 768, loss = 0.39857
I0605 23:41:47.739503 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.382854 (* 1 = 0.382854 loss)
I0605 23:41:47.739514 54715 sgd_solver.cpp:106] Iteration 768, lr = 0.00987693
I0605 23:41:50.975224 54715 solver.cpp:341] Iteration 770, Testing net (#0)
I0605 23:41:52.256691 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.784166
I0605 23:41:52.256734 54715 solver.cpp:409] Test net output #1: class_Acc = 0.865372
I0605 23:41:52.256742 54715 solver.cpp:409] Test net output #2: class_Acc = 0.567283
I0605 23:41:52.256752 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.448134 (* 1 = 0.448134 loss)
I0605 23:41:58.395407 54715 solver.cpp:237] Iteration 771, loss = 0.401005
I0605 23:41:58.395459 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.357493 (* 1 = 0.357493 loss)
I0605 23:41:58.395469 54715 sgd_solver.cpp:106] Iteration 771, lr = 0.00987645
I0605 23:42:07.769301 54715 solver.cpp:237] Iteration 774, loss = 0.40335
I0605 23:42:07.769351 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.385611 (* 1 = 0.385611 loss)
I0605 23:42:07.769362 54715 sgd_solver.cpp:106] Iteration 774, lr = 0.00987597
I0605 23:42:13.829001 54715 softmax_loss_layer.cu:194] weight loss 0 =0.237974 weight loss 1 =1 weight loss 2 =0
I0605 23:42:17.143262 54715 solver.cpp:237] Iteration 777, loss = 0.400575
I0605 23:42:17.143321 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.391712 (* 1 = 0.391712 loss)
I0605 23:42:17.143337 54715 sgd_solver.cpp:106] Iteration 777, lr = 0.00987549
I0605 23:42:23.504422 54715 solver.cpp:341] Iteration 780, Testing net (#0)
I0605 23:42:24.784989 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.768465
I0605 23:42:24.785032 54715 solver.cpp:409] Test net output #1: class_Acc = 0.935024
I0605 23:42:24.785038 54715 solver.cpp:409] Test net output #2: class_Acc = 0.353484
I0605 23:42:24.785048 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.505208 (* 1 = 0.505208 loss)
I0605 23:42:27.801551 54715 solver.cpp:237] Iteration 780, loss = 0.397601
I0605 23:42:27.801599 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.409844 (* 1 = 0.409844 loss)
I0605 23:42:27.801610 54715 sgd_solver.cpp:106] Iteration 780, lr = 0.009875
I0605 23:42:37.174881 54715 solver.cpp:237] Iteration 783, loss = 0.39889
I0605 23:42:37.174932 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327343 (* 1 = 0.327343 loss)
I0605 23:42:37.174942 54715 sgd_solver.cpp:106] Iteration 783, lr = 0.00987452
I0605 23:42:46.550874 54715 solver.cpp:237] Iteration 786, loss = 0.397992
I0605 23:42:46.550905 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.399385 (* 1 = 0.399385 loss)
I0605 23:42:46.550915 54715 sgd_solver.cpp:106] Iteration 786, lr = 0.00987404
I0605 23:42:54.568822 54715 softmax_loss_layer.cu:194] weight loss 0 =0.271986 weight loss 1 =1 weight loss 2 =0
I0605 23:42:55.926229 54715 solver.cpp:237] Iteration 789, loss = 0.399134
I0605 23:42:55.926259 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.48309 (* 1 = 0.48309 loss)
I0605 23:42:55.926268 54715 sgd_solver.cpp:106] Iteration 789, lr = 0.00987356
I0605 23:42:56.035704 54715 solver.cpp:341] Iteration 790, Testing net (#0)
I0605 23:42:57.315814 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.777901
I0605 23:42:57.315858 54715 solver.cpp:409] Test net output #1: class_Acc = 0.936985
I0605 23:42:57.315865 54715 solver.cpp:409] Test net output #2: class_Acc = 0.424494
I0605 23:42:57.315876 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.457228 (* 1 = 0.457228 loss)
I0605 23:43:06.580658 54715 solver.cpp:237] Iteration 792, loss = 0.401618
I0605 23:43:06.580703 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.407298 (* 1 = 0.407298 loss)
I0605 23:43:06.580713 54715 sgd_solver.cpp:106] Iteration 792, lr = 0.00987308
I0605 23:43:06.792891 54715 softmax_loss_layer.cu:194] weight loss 0 =0.360468 weight loss 1 =1 weight loss 2 =0
I0605 23:43:07.959846 54715 softmax_loss_layer.cu:194] weight loss 0 =0.295979 weight loss 1 =1 weight loss 2 =0
I0605 23:43:09.916756 54715 softmax_loss_layer.cu:194] weight loss 0 =0.201438 weight loss 1 =1 weight loss 2 =0
I0605 23:43:14.208389 54715 softmax_loss_layer.cu:194] weight loss 0 =0.340454 weight loss 1 =1 weight loss 2 =0
I0605 23:43:15.952957 54715 solver.cpp:237] Iteration 795, loss = 0.402766
I0605 23:43:15.953007 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350916 (* 1 = 0.350916 loss)
I0605 23:43:15.953018 54715 sgd_solver.cpp:106] Iteration 795, lr = 0.0098726
I0605 23:43:25.329069 54715 solver.cpp:237] Iteration 798, loss = 0.401716
I0605 23:43:25.329138 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.383012 (* 1 = 0.383012 loss)
I0605 23:43:25.329150 54715 sgd_solver.cpp:106] Iteration 798, lr = 0.00987212
I0605 23:43:28.564810 54715 solver.cpp:341] Iteration 800, Testing net (#0)
I0605 23:43:29.845677 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.749808
I0605 23:43:29.845721 54715 solver.cpp:409] Test net output #1: class_Acc = 0.940742
I0605 23:43:29.845727 54715 solver.cpp:409] Test net output #2: class_Acc = 0.343193
I0605 23:43:29.845737 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.553364 (* 1 = 0.553364 loss)
I0605 23:43:35.985220 54715 solver.cpp:237] Iteration 801, loss = 0.400905
I0605 23:43:35.985265 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.354272 (* 1 = 0.354272 loss)
I0605 23:43:35.985277 54715 sgd_solver.cpp:106] Iteration 801, lr = 0.00987163
I0605 23:43:45.357460 54715 solver.cpp:237] Iteration 804, loss = 0.398663
I0605 23:43:45.357502 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.382615 (* 1 = 0.382615 loss)
I0605 23:43:45.357513 54715 sgd_solver.cpp:106] Iteration 804, lr = 0.00987115
I0605 23:43:54.735400 54715 solver.cpp:237] Iteration 807, loss = 0.394666
I0605 23:43:54.735453 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.396495 (* 1 = 0.396495 loss)
I0605 23:43:54.735474 54715 sgd_solver.cpp:106] Iteration 807, lr = 0.00987067
I0605 23:44:01.097931 54715 solver.cpp:341] Iteration 810, Testing net (#0)
I0605 23:44:02.378589 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.774467
I0605 23:44:02.378633 54715 solver.cpp:409] Test net output #1: class_Acc = 0.947994
I0605 23:44:02.378640 54715 solver.cpp:409] Test net output #2: class_Acc = 0.353989
I0605 23:44:02.378650 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.496054 (* 1 = 0.496054 loss)
I0605 23:44:04.427940 54715 softmax_loss_layer.cu:194] weight loss 0 =0.231255 weight loss 1 =1 weight loss 2 =0
I0605 23:44:05.396819 54715 solver.cpp:237] Iteration 810, loss = 0.393964
I0605 23:44:05.396867 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345421 (* 1 = 0.345421 loss)
I0605 23:44:05.396878 54715 sgd_solver.cpp:106] Iteration 810, lr = 0.00987019
I0605 23:44:14.769748 54715 solver.cpp:237] Iteration 813, loss = 0.393365
I0605 23:44:14.769798 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368844 (* 1 = 0.368844 loss)
I0605 23:44:14.769809 54715 sgd_solver.cpp:106] Iteration 813, lr = 0.00986971
I0605 23:44:24.142174 54715 solver.cpp:237] Iteration 816, loss = 0.395683
I0605 23:44:24.142225 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.417815 (* 1 = 0.417815 loss)
I0605 23:44:24.142236 54715 sgd_solver.cpp:106] Iteration 816, lr = 0.00986923
I0605 23:44:33.516407 54715 solver.cpp:237] Iteration 819, loss = 0.397818
I0605 23:44:33.516520 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.362697 (* 1 = 0.362697 loss)
I0605 23:44:33.516531 54715 sgd_solver.cpp:106] Iteration 819, lr = 0.00986874
I0605 23:44:33.625838 54715 solver.cpp:341] Iteration 820, Testing net (#0)
I0605 23:44:34.908213 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.775263
I0605 23:44:34.908259 54715 solver.cpp:409] Test net output #1: class_Acc = 0.900019
I0605 23:44:34.908267 54715 solver.cpp:409] Test net output #2: class_Acc = 0.490175
I0605 23:44:34.908277 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.477457 (* 1 = 0.477457 loss)
I0605 23:44:36.176587 54715 softmax_loss_layer.cu:194] weight loss 0 =0.166327 weight loss 1 =1 weight loss 2 =0
I0605 23:44:44.169817 54715 solver.cpp:237] Iteration 822, loss = 0.401437
I0605 23:44:44.169867 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.39735 (* 1 = 0.39735 loss)
I0605 23:44:44.169879 54715 sgd_solver.cpp:106] Iteration 822, lr = 0.00986826
I0605 23:44:53.541980 54715 solver.cpp:237] Iteration 825, loss = 0.401468
I0605 23:44:53.542031 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.425911 (* 1 = 0.425911 loss)
I0605 23:44:53.542042 54715 sgd_solver.cpp:106] Iteration 825, lr = 0.00986778
I0605 23:45:02.911197 54715 solver.cpp:237] Iteration 828, loss = 0.401206
I0605 23:45:02.911242 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.439108 (* 1 = 0.439108 loss)
I0605 23:45:02.911253 54715 sgd_solver.cpp:106] Iteration 828, lr = 0.0098673
I0605 23:45:06.144323 54715 solver.cpp:341] Iteration 830, Testing net (#0)
I0605 23:45:07.427235 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.787827
I0605 23:45:07.427274 54715 solver.cpp:409] Test net output #1: class_Acc = 0.848506
I0605 23:45:07.427281 54715 solver.cpp:409] Test net output #2: class_Acc = 0.643727
I0605 23:45:07.427291 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.452454 (* 1 = 0.452454 loss)
I0605 23:45:13.565922 54715 solver.cpp:237] Iteration 831, loss = 0.398943
I0605 23:45:13.565973 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.405602 (* 1 = 0.405602 loss)
I0605 23:45:13.565985 54715 sgd_solver.cpp:106] Iteration 831, lr = 0.00986682
I0605 23:45:22.937757 54715 solver.cpp:237] Iteration 834, loss = 0.39909
I0605 23:45:22.937811 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.453835 (* 1 = 0.453835 loss)
I0605 23:45:22.937832 54715 sgd_solver.cpp:106] Iteration 834, lr = 0.00986634
I0605 23:45:32.313848 54715 solver.cpp:237] Iteration 837, loss = 0.39887
I0605 23:45:32.313890 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.387833 (* 1 = 0.387833 loss)
I0605 23:45:32.313900 54715 sgd_solver.cpp:106] Iteration 837, lr = 0.00986585
I0605 23:45:38.673177 54715 solver.cpp:341] Iteration 840, Testing net (#0)
I0605 23:45:39.955605 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.788311
I0605 23:45:39.955651 54715 solver.cpp:409] Test net output #1: class_Acc = 0.886014
I0605 23:45:39.955657 54715 solver.cpp:409] Test net output #2: class_Acc = 0.534865
I0605 23:45:39.955668 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.444796 (* 1 = 0.444796 loss)
I0605 23:45:42.969669 54715 solver.cpp:237] Iteration 840, loss = 0.394827
I0605 23:45:42.969717 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.354285 (* 1 = 0.354285 loss)
I0605 23:45:42.969727 54715 sgd_solver.cpp:106] Iteration 840, lr = 0.00986537
I0605 23:45:52.348529 54715 solver.cpp:237] Iteration 843, loss = 0.394802
I0605 23:45:52.348579 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.407293 (* 1 = 0.407293 loss)
I0605 23:45:52.348592 54715 sgd_solver.cpp:106] Iteration 843, lr = 0.00986489
I0605 23:46:01.722661 54715 solver.cpp:237] Iteration 846, loss = 0.391474
I0605 23:46:01.722698 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359953 (* 1 = 0.359953 loss)
I0605 23:46:01.722710 54715 sgd_solver.cpp:106] Iteration 846, lr = 0.00986441
I0605 23:46:05.061303 54715 softmax_loss_layer.cu:194] weight loss 0 =0.371063 weight loss 1 =1 weight loss 2 =0
I0605 23:46:11.098215 54715 solver.cpp:237] Iteration 849, loss = 0.391968
I0605 23:46:11.098333 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.428599 (* 1 = 0.428599 loss)
I0605 23:46:11.098346 54715 sgd_solver.cpp:106] Iteration 849, lr = 0.00986393
I0605 23:46:11.207576 54715 solver.cpp:341] Iteration 850, Testing net (#0)
I0605 23:46:12.490193 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.802463
I0605 23:46:12.490236 54715 solver.cpp:409] Test net output #1: class_Acc = 0.896403
I0605 23:46:12.490243 54715 solver.cpp:409] Test net output #2: class_Acc = 0.591431
I0605 23:46:12.490253 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.425476 (* 1 = 0.425476 loss)
I0605 23:46:16.883785 54715 softmax_loss_layer.cu:194] weight loss 0 =0.246685 weight loss 1 =1 weight loss 2 =0
I0605 23:46:21.562721 54715 softmax_loss_layer.cu:194] weight loss 0 =0.399641 weight loss 1 =1 weight loss 2 =0
I0605 23:46:21.752426 54715 solver.cpp:237] Iteration 852, loss = 0.39039
I0605 23:46:21.752475 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35938 (* 1 = 0.35938 loss)
I0605 23:46:21.752485 54715 sgd_solver.cpp:106] Iteration 852, lr = 0.00986345
I0605 23:46:31.127238 54715 solver.cpp:237] Iteration 855, loss = 0.390179
I0605 23:46:31.127290 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35227 (* 1 = 0.35227 loss)
I0605 23:46:31.127301 54715 sgd_solver.cpp:106] Iteration 855, lr = 0.00986296
I0605 23:46:40.502477 54715 solver.cpp:237] Iteration 858, loss = 0.390434
I0605 23:46:40.502528 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.422827 (* 1 = 0.422827 loss)
I0605 23:46:40.502539 54715 sgd_solver.cpp:106] Iteration 858, lr = 0.00986248
I0605 23:46:43.736063 54715 solver.cpp:341] Iteration 860, Testing net (#0)
I0605 23:46:45.019052 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.793521
I0605 23:46:45.019098 54715 solver.cpp:409] Test net output #1: class_Acc = 0.872762
I0605 23:46:45.019104 54715 solver.cpp:409] Test net output #2: class_Acc = 0.611592
I0605 23:46:45.019115 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.425237 (* 1 = 0.425237 loss)
I0605 23:46:51.155941 54715 solver.cpp:237] Iteration 861, loss = 0.394174
I0605 23:46:51.155987 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.365755 (* 1 = 0.365755 loss)
I0605 23:46:51.156006 54715 sgd_solver.cpp:106] Iteration 861, lr = 0.009862
I0605 23:47:00.530351 54715 solver.cpp:237] Iteration 864, loss = 0.394212
I0605 23:47:00.530398 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.385428 (* 1 = 0.385428 loss)
I0605 23:47:00.530409 54715 sgd_solver.cpp:106] Iteration 864, lr = 0.00986152
I0605 23:47:09.906024 54715 solver.cpp:237] Iteration 867, loss = 0.391192
I0605 23:47:09.906077 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.377983 (* 1 = 0.377983 loss)
I0605 23:47:09.906090 54715 sgd_solver.cpp:106] Iteration 867, lr = 0.00986104
I0605 23:47:16.265499 54715 solver.cpp:341] Iteration 870, Testing net (#0)
I0605 23:47:17.548014 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.792426
I0605 23:47:17.548056 54715 solver.cpp:409] Test net output #1: class_Acc = 0.844755
I0605 23:47:17.548063 54715 solver.cpp:409] Test net output #2: class_Acc = 0.665695
I0605 23:47:17.548072 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.447729 (* 1 = 0.447729 loss)
I0605 23:47:20.565212 54715 solver.cpp:237] Iteration 870, loss = 0.391956
I0605 23:47:20.565265 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.397448 (* 1 = 0.397448 loss)
I0605 23:47:20.565275 54715 sgd_solver.cpp:106] Iteration 870, lr = 0.00986056
I0605 23:47:29.941721 54715 solver.cpp:237] Iteration 873, loss = 0.390466
I0605 23:47:29.941773 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.399337 (* 1 = 0.399337 loss)
I0605 23:47:29.941784 54715 sgd_solver.cpp:106] Iteration 873, lr = 0.00986007
I0605 23:47:39.315030 54715 solver.cpp:237] Iteration 876, loss = 0.389022
I0605 23:47:39.315078 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.375487 (* 1 = 0.375487 loss)
I0605 23:47:39.315088 54715 sgd_solver.cpp:106] Iteration 876, lr = 0.00985959
I0605 23:47:48.688832 54715 solver.cpp:237] Iteration 879, loss = 0.385452
I0605 23:47:48.688902 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326343 (* 1 = 0.326343 loss)
I0605 23:47:48.688913 54715 sgd_solver.cpp:106] Iteration 879, lr = 0.00985911
I0605 23:47:48.798259 54715 solver.cpp:341] Iteration 880, Testing net (#0)
I0605 23:47:50.080615 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.805534
I0605 23:47:50.080641 54715 solver.cpp:409] Test net output #1: class_Acc = 0.878521
I0605 23:47:50.080647 54715 solver.cpp:409] Test net output #2: class_Acc = 0.644698
I0605 23:47:50.080657 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.421102 (* 1 = 0.421102 loss)
I0605 23:47:59.345810 54715 solver.cpp:237] Iteration 882, loss = 0.387938
I0605 23:47:59.345858 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.383894 (* 1 = 0.383894 loss)
I0605 23:47:59.345870 54715 sgd_solver.cpp:106] Iteration 882, lr = 0.00985863
I0605 23:48:08.718777 54715 solver.cpp:237] Iteration 885, loss = 0.387894
I0605 23:48:08.718827 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376788 (* 1 = 0.376788 loss)
I0605 23:48:08.718837 54715 sgd_solver.cpp:106] Iteration 885, lr = 0.00985815
I0605 23:48:18.090453 54715 solver.cpp:237] Iteration 888, loss = 0.384912
I0605 23:48:18.090502 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.423747 (* 1 = 0.423747 loss)
I0605 23:48:18.090513 54715 sgd_solver.cpp:106] Iteration 888, lr = 0.00985767
I0605 23:48:21.326015 54715 solver.cpp:341] Iteration 890, Testing net (#0)
I0605 23:48:22.605973 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.766825
I0605 23:48:22.606016 54715 solver.cpp:409] Test net output #1: class_Acc = 0.925614
I0605 23:48:22.606024 54715 solver.cpp:409] Test net output #2: class_Acc = 0.387163
I0605 23:48:22.606034 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.524276 (* 1 = 0.524276 loss)
I0605 23:48:28.747236 54715 solver.cpp:237] Iteration 891, loss = 0.385266
I0605 23:48:28.747298 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.356697 (* 1 = 0.356697 loss)
I0605 23:48:28.747309 54715 sgd_solver.cpp:106] Iteration 891, lr = 0.00985718
I0605 23:48:38.122891 54715 solver.cpp:237] Iteration 894, loss = 0.384397
I0605 23:48:38.122941 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.419325 (* 1 = 0.419325 loss)
I0605 23:48:38.122951 54715 sgd_solver.cpp:106] Iteration 894, lr = 0.0098567
I0605 23:48:47.494527 54715 solver.cpp:237] Iteration 897, loss = 0.384743
I0605 23:48:47.494566 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.404769 (* 1 = 0.404769 loss)
I0605 23:48:47.494576 54715 sgd_solver.cpp:106] Iteration 897, lr = 0.00985622
I0605 23:48:53.854610 54715 solver.cpp:341] Iteration 900, Testing net (#0)
I0605 23:48:55.138187 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.801057
I0605 23:48:55.138231 54715 solver.cpp:409] Test net output #1: class_Acc = 0.85603
I0605 23:48:55.138238 54715 solver.cpp:409] Test net output #2: class_Acc = 0.670431
I0605 23:48:55.138248 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.437589 (* 1 = 0.437589 loss)
I0605 23:48:58.154043 54715 solver.cpp:237] Iteration 900, loss = 0.384335
I0605 23:48:58.154093 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.397704 (* 1 = 0.397704 loss)
I0605 23:48:58.154105 54715 sgd_solver.cpp:106] Iteration 900, lr = 0.00985574
I0605 23:49:07.526935 54715 solver.cpp:237] Iteration 903, loss = 0.38404
I0605 23:49:07.526980 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.336355 (* 1 = 0.336355 loss)
I0605 23:49:07.526990 54715 sgd_solver.cpp:106] Iteration 903, lr = 0.00985526
I0605 23:49:16.901814 54715 solver.cpp:237] Iteration 906, loss = 0.382943
I0605 23:49:16.901861 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.36552 (* 1 = 0.36552 loss)
I0605 23:49:16.901871 54715 sgd_solver.cpp:106] Iteration 906, lr = 0.00985477
I0605 23:49:26.274451 54715 solver.cpp:237] Iteration 909, loss = 0.382269
I0605 23:49:26.274579 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.342628 (* 1 = 0.342628 loss)
I0605 23:49:26.274591 54715 sgd_solver.cpp:106] Iteration 909, lr = 0.00985429
I0605 23:49:26.383800 54715 solver.cpp:341] Iteration 910, Testing net (#0)
I0605 23:49:27.667744 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.798962
I0605 23:49:27.667788 54715 solver.cpp:409] Test net output #1: class_Acc = 0.854307
I0605 23:49:27.667794 54715 solver.cpp:409] Test net output #2: class_Acc = 0.686444
I0605 23:49:27.667804 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.431052 (* 1 = 0.431052 loss)
I0605 23:49:36.931499 54715 solver.cpp:237] Iteration 912, loss = 0.382425
I0605 23:49:36.931550 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.34666 (* 1 = 0.34666 loss)
I0605 23:49:36.931561 54715 sgd_solver.cpp:106] Iteration 912, lr = 0.00985381
I0605 23:49:46.306696 54715 solver.cpp:237] Iteration 915, loss = 0.380645
I0605 23:49:46.306746 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.389854 (* 1 = 0.389854 loss)
I0605 23:49:46.306756 54715 sgd_solver.cpp:106] Iteration 915, lr = 0.00985333
I0605 23:49:55.677558 54715 solver.cpp:237] Iteration 918, loss = 0.383854
I0605 23:49:55.677610 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.451912 (* 1 = 0.451912 loss)
I0605 23:49:55.677620 54715 sgd_solver.cpp:106] Iteration 918, lr = 0.00985285
I0605 23:49:58.910974 54715 solver.cpp:341] Iteration 920, Testing net (#0)
I0605 23:50:00.192646 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.812063
I0605 23:50:00.192692 54715 solver.cpp:409] Test net output #1: class_Acc = 0.916685
I0605 23:50:00.192699 54715 solver.cpp:409] Test net output #2: class_Acc = 0.563008
I0605 23:50:00.192709 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.406558 (* 1 = 0.406558 loss)
I0605 23:50:06.334918 54715 solver.cpp:237] Iteration 921, loss = 0.384441
I0605 23:50:06.334978 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.474072 (* 1 = 0.474072 loss)
I0605 23:50:06.334990 54715 sgd_solver.cpp:106] Iteration 921, lr = 0.00985237
I0605 23:50:15.710639 54715 solver.cpp:237] Iteration 924, loss = 0.386102
I0605 23:50:15.710690 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.44258 (* 1 = 0.44258 loss)
I0605 23:50:15.710702 54715 sgd_solver.cpp:106] Iteration 924, lr = 0.00985188
I0605 23:50:25.084913 54715 solver.cpp:237] Iteration 927, loss = 0.384069
I0605 23:50:25.084959 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.406534 (* 1 = 0.406534 loss)
I0605 23:50:25.084969 54715 sgd_solver.cpp:106] Iteration 927, lr = 0.0098514
I0605 23:50:28.814143 54715 softmax_loss_layer.cu:194] weight loss 0 =0.278578 weight loss 1 =1 weight loss 2 =0
I0605 23:50:31.447989 54715 solver.cpp:341] Iteration 930, Testing net (#0)
I0605 23:50:32.731854 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.824213
I0605 23:50:32.731897 54715 solver.cpp:409] Test net output #1: class_Acc = 0.911355
I0605 23:50:32.731905 54715 solver.cpp:409] Test net output #2: class_Acc = 0.613616
I0605 23:50:32.731914 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.382101 (* 1 = 0.382101 loss)
I0605 23:50:35.748805 54715 solver.cpp:237] Iteration 930, loss = 0.38436
I0605 23:50:35.748855 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.462974 (* 1 = 0.462974 loss)
I0605 23:50:35.748865 54715 sgd_solver.cpp:106] Iteration 930, lr = 0.00985092
I0605 23:50:42.599922 54715 softmax_loss_layer.cu:194] weight loss 0 =0.299482 weight loss 1 =1 weight loss 2 =0
I0605 23:50:45.123411 54715 solver.cpp:237] Iteration 933, loss = 0.382438
I0605 23:50:45.123461 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.363984 (* 1 = 0.363984 loss)
I0605 23:50:45.123472 54715 sgd_solver.cpp:106] Iteration 933, lr = 0.00985044
I0605 23:50:48.850378 54715 softmax_loss_layer.cu:194] weight loss 0 =0.289712 weight loss 1 =1 weight loss 2 =0
I0605 23:50:53.921079 54715 softmax_loss_layer.cu:194] weight loss 0 =0.297911 weight loss 1 =1 weight loss 2 =0
I0605 23:50:54.499233 54715 solver.cpp:237] Iteration 936, loss = 0.38135
I0605 23:50:54.499277 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.317598 (* 1 = 0.317598 loss)
I0605 23:50:54.499289 54715 sgd_solver.cpp:106] Iteration 936, lr = 0.00984996
I0605 23:51:03.871372 54715 solver.cpp:237] Iteration 939, loss = 0.379801
I0605 23:51:03.871511 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.38068 (* 1 = 0.38068 loss)
I0605 23:51:03.871523 54715 sgd_solver.cpp:106] Iteration 939, lr = 0.00984948
I0605 23:51:03.980777 54715 solver.cpp:341] Iteration 940, Testing net (#0)
I0605 23:51:05.262074 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.776408
I0605 23:51:05.262122 54715 solver.cpp:409] Test net output #1: class_Acc = 0.863269
I0605 23:51:05.262130 54715 solver.cpp:409] Test net output #2: class_Acc = 0.568478
I0605 23:51:05.262140 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.485391 (* 1 = 0.485391 loss)
I0605 23:51:08.878427 54715 softmax_loss_layer.cu:194] weight loss 0 =0.378987 weight loss 1 =1 weight loss 2 =0
I0605 23:51:14.525933 54715 solver.cpp:237] Iteration 942, loss = 0.380265
I0605 23:51:14.525982 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347404 (* 1 = 0.347404 loss)
I0605 23:51:14.525993 54715 sgd_solver.cpp:106] Iteration 942, lr = 0.00984899
I0605 23:51:23.898207 54715 solver.cpp:237] Iteration 945, loss = 0.378512
I0605 23:51:23.898252 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.349623 (* 1 = 0.349623 loss)
I0605 23:51:23.898262 54715 sgd_solver.cpp:106] Iteration 945, lr = 0.00984851
I0605 23:51:29.183825 54715 softmax_loss_layer.cu:194] weight loss 0 =0.280999 weight loss 1 =1 weight loss 2 =0
I0605 23:51:33.280009 54715 solver.cpp:237] Iteration 948, loss = 0.378979
I0605 23:51:33.280040 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.433777 (* 1 = 0.433777 loss)
I0605 23:51:33.280061 54715 sgd_solver.cpp:106] Iteration 948, lr = 0.00984803
I0605 23:51:36.514624 54715 solver.cpp:341] Iteration 950, Testing net (#0)
I0605 23:51:37.796164 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.807713
I0605 23:51:37.796208 54715 solver.cpp:409] Test net output #1: class_Acc = 0.933564
I0605 23:51:37.796216 54715 solver.cpp:409] Test net output #2: class_Acc = 0.52052
I0605 23:51:37.796226 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.409426 (* 1 = 0.409426 loss)
I0605 23:51:37.898226 54715 softmax_loss_layer.cu:194] weight loss 0 =0.260128 weight loss 1 =1 weight loss 2 =0
I0605 23:51:43.941504 54715 solver.cpp:237] Iteration 951, loss = 0.378296
I0605 23:51:43.941550 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350226 (* 1 = 0.350226 loss)
I0605 23:51:43.941560 54715 sgd_solver.cpp:106] Iteration 951, lr = 0.00984755
I0605 23:51:53.317476 54715 solver.cpp:237] Iteration 954, loss = 0.379025
I0605 23:51:53.317525 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35742 (* 1 = 0.35742 loss)
I0605 23:51:53.317536 54715 sgd_solver.cpp:106] Iteration 954, lr = 0.00984707
I0605 23:52:02.694964 54715 solver.cpp:237] Iteration 957, loss = 0.377764
I0605 23:52:02.695017 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.398673 (* 1 = 0.398673 loss)
I0605 23:52:02.695029 54715 sgd_solver.cpp:106] Iteration 957, lr = 0.00984658
I0605 23:52:09.054277 54715 solver.cpp:341] Iteration 960, Testing net (#0)
I0605 23:52:10.335973 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.81768
I0605 23:52:10.336019 54715 solver.cpp:409] Test net output #1: class_Acc = 0.920001
I0605 23:52:10.336026 54715 solver.cpp:409] Test net output #2: class_Acc = 0.58204
I0605 23:52:10.336036 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.401427 (* 1 = 0.401427 loss)
I0605 23:52:13.350139 54715 solver.cpp:237] Iteration 960, loss = 0.378707
I0605 23:52:13.350186 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.380601 (* 1 = 0.380601 loss)
I0605 23:52:13.350198 54715 sgd_solver.cpp:106] Iteration 960, lr = 0.0098461
I0605 23:52:22.720549 54715 solver.cpp:237] Iteration 963, loss = 0.379367
I0605 23:52:22.720595 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.333266 (* 1 = 0.333266 loss)
I0605 23:52:22.720607 54715 sgd_solver.cpp:106] Iteration 963, lr = 0.00984562
I0605 23:52:32.094408 54715 solver.cpp:237] Iteration 966, loss = 0.376709
I0605 23:52:32.094460 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360239 (* 1 = 0.360239 loss)
I0605 23:52:32.094470 54715 sgd_solver.cpp:106] Iteration 966, lr = 0.00984514
I0605 23:52:41.468323 54715 solver.cpp:237] Iteration 969, loss = 0.376984
I0605 23:52:41.468391 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.369066 (* 1 = 0.369066 loss)
I0605 23:52:41.468403 54715 sgd_solver.cpp:106] Iteration 969, lr = 0.00984466
I0605 23:52:41.577746 54715 solver.cpp:341] Iteration 970, Testing net (#0)
I0605 23:52:42.860136 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.803926
I0605 23:52:42.860193 54715 solver.cpp:409] Test net output #1: class_Acc = 0.888638
I0605 23:52:42.860199 54715 solver.cpp:409] Test net output #2: class_Acc = 0.612657
I0605 23:52:42.860209 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.428563 (* 1 = 0.428563 loss)
I0605 23:52:52.129106 54715 solver.cpp:237] Iteration 972, loss = 0.374625
I0605 23:52:52.129158 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.363925 (* 1 = 0.363925 loss)
I0605 23:52:52.129168 54715 sgd_solver.cpp:106] Iteration 972, lr = 0.00984418
I0605 23:53:01.502638 54715 solver.cpp:237] Iteration 975, loss = 0.375486
I0605 23:53:01.502691 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.322202 (* 1 = 0.322202 loss)
I0605 23:53:01.502702 54715 sgd_solver.cpp:106] Iteration 975, lr = 0.00984369
I0605 23:53:10.879863 54715 solver.cpp:237] Iteration 978, loss = 0.375925
I0605 23:53:10.879911 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.344016 (* 1 = 0.344016 loss)
I0605 23:53:10.879921 54715 sgd_solver.cpp:106] Iteration 978, lr = 0.00984321
I0605 23:53:14.114949 54715 solver.cpp:341] Iteration 980, Testing net (#0)
I0605 23:53:15.395342 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.787628
I0605 23:53:15.395387 54715 solver.cpp:409] Test net output #1: class_Acc = 0.898047
I0605 23:53:15.395395 54715 solver.cpp:409] Test net output #2: class_Acc = 0.529922
I0605 23:53:15.395404 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.461822 (* 1 = 0.461822 loss)
I0605 23:53:16.664903 54715 softmax_loss_layer.cu:194] weight loss 0 =0.292479 weight loss 1 =1 weight loss 2 =0
I0605 23:53:21.535353 54715 solver.cpp:237] Iteration 981, loss = 0.376606
I0605 23:53:21.535404 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.336689 (* 1 = 0.336689 loss)
I0605 23:53:21.535415 54715 sgd_solver.cpp:106] Iteration 981, lr = 0.00984273
I0605 23:53:30.908881 54715 solver.cpp:237] Iteration 984, loss = 0.376494
I0605 23:53:30.908931 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.48419 (* 1 = 0.48419 loss)
I0605 23:53:30.908941 54715 sgd_solver.cpp:106] Iteration 984, lr = 0.00984225
I0605 23:53:40.285565 54715 solver.cpp:237] Iteration 987, loss = 0.374985
I0605 23:53:40.285617 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348902 (* 1 = 0.348902 loss)
I0605 23:53:40.285629 54715 sgd_solver.cpp:106] Iteration 987, lr = 0.00984177
I0605 23:53:46.345134 54715 softmax_loss_layer.cu:194] weight loss 0 =0.414279 weight loss 1 =1 weight loss 2 =0
I0605 23:53:46.644096 54715 solver.cpp:341] Iteration 990, Testing net (#0)
I0605 23:53:47.926793 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.784571
I0605 23:53:47.926838 54715 solver.cpp:409] Test net output #1: class_Acc = 0.888924
I0605 23:53:47.926846 54715 solver.cpp:409] Test net output #2: class_Acc = 0.528978
I0605 23:53:47.926856 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.458305 (* 1 = 0.458305 loss)
I0605 23:53:50.941615 54715 solver.cpp:237] Iteration 990, loss = 0.377814
I0605 23:53:50.941668 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.417686 (* 1 = 0.417686 loss)
I0605 23:53:50.941679 54715 sgd_solver.cpp:106] Iteration 990, lr = 0.00984128
I0605 23:54:00.315520 54715 solver.cpp:237] Iteration 993, loss = 0.375146
I0605 23:54:00.315570 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.333467 (* 1 = 0.333467 loss)
I0605 23:54:00.315582 54715 sgd_solver.cpp:106] Iteration 993, lr = 0.0098408
I0605 23:54:09.690827 54715 solver.cpp:237] Iteration 996, loss = 0.376488
I0605 23:54:09.690881 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367832 (* 1 = 0.367832 loss)
I0605 23:54:09.690891 54715 sgd_solver.cpp:106] Iteration 996, lr = 0.00984032
I0605 23:54:19.064932 54715 solver.cpp:237] Iteration 999, loss = 0.37425
I0605 23:54:19.064991 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.408169 (* 1 = 0.408169 loss)
I0605 23:54:19.065002 54715 sgd_solver.cpp:106] Iteration 999, lr = 0.00983984
I0605 23:54:19.174372 54715 solver.cpp:341] Iteration 1000, Testing net (#0)
I0605 23:54:20.455359 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.808114
I0605 23:54:20.455406 54715 solver.cpp:409] Test net output #1: class_Acc = 0.932401
I0605 23:54:20.455415 54715 solver.cpp:409] Test net output #2: class_Acc = 0.532594
I0605 23:54:20.455425 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.407188 (* 1 = 0.407188 loss)
I0605 23:54:29.717674 54715 solver.cpp:237] Iteration 1002, loss = 0.376624
I0605 23:54:29.717722 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.358255 (* 1 = 0.358255 loss)
I0605 23:54:29.717734 54715 sgd_solver.cpp:106] Iteration 1002, lr = 0.00983936
I0605 23:54:39.088136 54715 solver.cpp:237] Iteration 1005, loss = 0.376402
I0605 23:54:39.088202 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.322415 (* 1 = 0.322415 loss)
I0605 23:54:39.088213 54715 sgd_solver.cpp:106] Iteration 1005, lr = 0.00983887
I0605 23:54:48.461758 54715 solver.cpp:237] Iteration 1008, loss = 0.375321
I0605 23:54:48.461807 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.371825 (* 1 = 0.371825 loss)
I0605 23:54:48.461818 54715 sgd_solver.cpp:106] Iteration 1008, lr = 0.00983839
I0605 23:54:51.694921 54715 solver.cpp:341] Iteration 1010, Testing net (#0)
I0605 23:54:52.977557 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.768645
I0605 23:54:52.977600 54715 solver.cpp:409] Test net output #1: class_Acc = 0.81871
I0605 23:54:52.977607 54715 solver.cpp:409] Test net output #2: class_Acc = 0.647785
I0605 23:54:52.977617 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.495203 (* 1 = 0.495203 loss)
I0605 23:54:59.116075 54715 solver.cpp:237] Iteration 1011, loss = 0.377796
I0605 23:54:59.116118 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.343862 (* 1 = 0.343862 loss)
I0605 23:54:59.116127 54715 sgd_solver.cpp:106] Iteration 1011, lr = 0.00983791
I0605 23:55:08.300864 54715 softmax_loss_layer.cu:194] weight loss 0 =0.29574 weight loss 1 =1 weight loss 2 =0
I0605 23:55:08.490454 54715 solver.cpp:237] Iteration 1014, loss = 0.379354
I0605 23:55:08.490501 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.486058 (* 1 = 0.486058 loss)
I0605 23:55:08.490512 54715 sgd_solver.cpp:106] Iteration 1014, lr = 0.00983743
I0605 23:55:17.865872 54715 solver.cpp:237] Iteration 1017, loss = 0.377884
I0605 23:55:17.865921 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376794 (* 1 = 0.376794 loss)
I0605 23:55:17.865932 54715 sgd_solver.cpp:106] Iteration 1017, lr = 0.00983695
I0605 23:55:24.222964 54715 solver.cpp:341] Iteration 1020, Testing net (#0)
I0605 23:55:25.504736 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.801302
I0605 23:55:25.504781 54715 solver.cpp:409] Test net output #1: class_Acc = 0.928832
I0605 23:55:25.504787 54715 solver.cpp:409] Test net output #2: class_Acc = 0.51827
I0605 23:55:25.504798 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.428615 (* 1 = 0.428615 loss)
I0605 23:55:28.516913 54715 solver.cpp:237] Iteration 1020, loss = 0.377101
I0605 23:55:28.516963 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.369912 (* 1 = 0.369912 loss)
I0605 23:55:28.516973 54715 sgd_solver.cpp:106] Iteration 1020, lr = 0.00983646
I0605 23:55:31.064822 54715 softmax_loss_layer.cu:194] weight loss 0 =0.248866 weight loss 1 =1 weight loss 2 =0
I0605 23:55:37.892269 54715 solver.cpp:237] Iteration 1023, loss = 0.374258
I0605 23:55:37.892323 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325153 (* 1 = 0.325153 loss)
I0605 23:55:37.892333 54715 sgd_solver.cpp:106] Iteration 1023, lr = 0.00983598
I0605 23:55:46.687919 54715 softmax_loss_layer.cu:194] weight loss 0 =0.314928 weight loss 1 =1 weight loss 2 =0
I0605 23:55:47.265951 54715 solver.cpp:237] Iteration 1026, loss = 0.369362
I0605 23:55:47.266001 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350065 (* 1 = 0.350065 loss)
I0605 23:55:47.266012 54715 sgd_solver.cpp:106] Iteration 1026, lr = 0.0098355
I0605 23:55:56.059720 54715 softmax_loss_layer.cu:194] weight loss 0 =0.235855 weight loss 1 =1 weight loss 2 =0
I0605 23:55:56.638878 54715 solver.cpp:237] Iteration 1029, loss = 0.367477
I0605 23:55:56.638927 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.349271 (* 1 = 0.349271 loss)
I0605 23:55:56.638938 54715 sgd_solver.cpp:106] Iteration 1029, lr = 0.00983502
I0605 23:55:56.748327 54715 solver.cpp:341] Iteration 1030, Testing net (#0)
I0605 23:55:58.030110 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.813117
I0605 23:55:58.030153 54715 solver.cpp:409] Test net output #1: class_Acc = 0.940218
I0605 23:55:58.030172 54715 solver.cpp:409] Test net output #2: class_Acc = 0.520601
I0605 23:55:58.030184 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.410831 (* 1 = 0.410831 loss)
I0605 23:56:07.296655 54715 solver.cpp:237] Iteration 1032, loss = 0.364526
I0605 23:56:07.296710 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395284 (* 1 = 0.395284 loss)
I0605 23:56:07.296721 54715 sgd_solver.cpp:106] Iteration 1032, lr = 0.00983454
I0605 23:56:16.672327 54715 solver.cpp:237] Iteration 1035, loss = 0.364151
I0605 23:56:16.672375 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.422939 (* 1 = 0.422939 loss)
I0605 23:56:16.672386 54715 sgd_solver.cpp:106] Iteration 1035, lr = 0.00983405
I0605 23:56:26.043901 54715 solver.cpp:237] Iteration 1038, loss = 0.365924
I0605 23:56:26.043954 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.349764 (* 1 = 0.349764 loss)
I0605 23:56:26.043965 54715 sgd_solver.cpp:106] Iteration 1038, lr = 0.00983357
I0605 23:56:29.277259 54715 solver.cpp:341] Iteration 1040, Testing net (#0)
I0605 23:56:30.557334 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.774988
I0605 23:56:30.557377 54715 solver.cpp:409] Test net output #1: class_Acc = 0.908753
I0605 23:56:30.557384 54715 solver.cpp:409] Test net output #2: class_Acc = 0.432041
I0605 23:56:30.557394 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.492322 (* 1 = 0.492322 loss)
I0605 23:56:36.700168 54715 solver.cpp:237] Iteration 1041, loss = 0.368918
I0605 23:56:36.700218 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368429 (* 1 = 0.368429 loss)
I0605 23:56:36.700229 54715 sgd_solver.cpp:106] Iteration 1041, lr = 0.00983309
I0605 23:56:46.075453 54715 solver.cpp:237] Iteration 1044, loss = 0.370549
I0605 23:56:46.075503 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.372607 (* 1 = 0.372607 loss)
I0605 23:56:46.075515 54715 sgd_solver.cpp:106] Iteration 1044, lr = 0.00983261
I0605 23:56:55.448977 54715 solver.cpp:237] Iteration 1047, loss = 0.370283
I0605 23:56:55.449030 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.381602 (* 1 = 0.381602 loss)
I0605 23:56:55.449041 54715 sgd_solver.cpp:106] Iteration 1047, lr = 0.00983213
I0605 23:57:01.805124 54715 solver.cpp:341] Iteration 1050, Testing net (#0)
I0605 23:57:03.087118 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.803892
I0605 23:57:03.087163 54715 solver.cpp:409] Test net output #1: class_Acc = 0.951199
I0605 23:57:03.087170 54715 solver.cpp:409] Test net output #2: class_Acc = 0.4902
I0605 23:57:03.087180 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.415701 (* 1 = 0.415701 loss)
I0605 23:57:06.100087 54715 solver.cpp:237] Iteration 1050, loss = 0.369426
I0605 23:57:06.100150 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395498 (* 1 = 0.395498 loss)
I0605 23:57:06.100164 54715 sgd_solver.cpp:106] Iteration 1050, lr = 0.00983164
I0605 23:57:15.473935 54715 solver.cpp:237] Iteration 1053, loss = 0.366232
I0605 23:57:15.473986 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.442535 (* 1 = 0.442535 loss)
I0605 23:57:15.473997 54715 sgd_solver.cpp:106] Iteration 1053, lr = 0.00983116
I0605 23:57:24.855396 54715 solver.cpp:237] Iteration 1056, loss = 0.368183
I0605 23:57:24.855448 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.380925 (* 1 = 0.380925 loss)
I0605 23:57:24.855459 54715 sgd_solver.cpp:106] Iteration 1056, lr = 0.00983068
I0605 23:57:34.228097 54715 solver.cpp:237] Iteration 1059, loss = 0.367277
I0605 23:57:34.228181 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366207 (* 1 = 0.366207 loss)
I0605 23:57:34.228193 54715 sgd_solver.cpp:106] Iteration 1059, lr = 0.0098302
I0605 23:57:34.337479 54715 solver.cpp:341] Iteration 1060, Testing net (#0)
I0605 23:57:35.618088 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.779762
I0605 23:57:35.618136 54715 solver.cpp:409] Test net output #1: class_Acc = 0.934512
I0605 23:57:35.618155 54715 solver.cpp:409] Test net output #2: class_Acc = 0.417157
I0605 23:57:35.618165 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.498573 (* 1 = 0.498573 loss)
I0605 23:57:44.884057 54715 solver.cpp:237] Iteration 1062, loss = 0.366832
I0605 23:57:44.884106 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.364597 (* 1 = 0.364597 loss)
I0605 23:57:44.884116 54715 sgd_solver.cpp:106] Iteration 1062, lr = 0.00982972
I0605 23:57:54.260129 54715 solver.cpp:237] Iteration 1065, loss = 0.370221
I0605 23:57:54.260190 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360334 (* 1 = 0.360334 loss)
I0605 23:57:54.260200 54715 sgd_solver.cpp:106] Iteration 1065, lr = 0.00982923
I0605 23:58:03.636350 54715 solver.cpp:237] Iteration 1068, loss = 0.373369
I0605 23:58:03.636402 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347748 (* 1 = 0.347748 loss)
I0605 23:58:03.636411 54715 sgd_solver.cpp:106] Iteration 1068, lr = 0.00982875
I0605 23:58:06.869226 54715 solver.cpp:341] Iteration 1070, Testing net (#0)
I0605 23:58:08.149564 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.774047
I0605 23:58:08.149611 54715 solver.cpp:409] Test net output #1: class_Acc = 0.93898
I0605 23:58:08.149618 54715 solver.cpp:409] Test net output #2: class_Acc = 0.39201
I0605 23:58:08.149628 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.50133 (* 1 = 0.50133 loss)
I0605 23:58:14.288547 54715 solver.cpp:237] Iteration 1071, loss = 0.369217
I0605 23:58:14.288595 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.356787 (* 1 = 0.356787 loss)
I0605 23:58:14.288607 54715 sgd_solver.cpp:106] Iteration 1071, lr = 0.00982827
I0605 23:58:23.662549 54715 solver.cpp:237] Iteration 1074, loss = 0.36906
I0605 23:58:23.662597 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366781 (* 1 = 0.366781 loss)
I0605 23:58:23.662607 54715 sgd_solver.cpp:106] Iteration 1074, lr = 0.00982779
I0605 23:58:28.165439 54715 softmax_loss_layer.cu:194] weight loss 0 =0.402409 weight loss 1 =1 weight loss 2 =0
I0605 23:58:30.122880 54715 softmax_loss_layer.cu:194] weight loss 0 =0.279335 weight loss 1 =1 weight loss 2 =0
I0605 23:58:33.034451 54715 solver.cpp:237] Iteration 1077, loss = 0.370132
I0605 23:58:33.034502 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.396647 (* 1 = 0.396647 loss)
I0605 23:58:33.034512 54715 sgd_solver.cpp:106] Iteration 1077, lr = 0.00982731
I0605 23:58:39.391280 54715 solver.cpp:341] Iteration 1080, Testing net (#0)
I0605 23:58:40.672827 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.793246
I0605 23:58:40.672874 54715 solver.cpp:409] Test net output #1: class_Acc = 0.936053
I0605 23:58:40.672881 54715 solver.cpp:409] Test net output #2: class_Acc = 0.480089
I0605 23:58:40.672893 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.436357 (* 1 = 0.436357 loss)
I0605 23:58:43.685833 54715 solver.cpp:237] Iteration 1080, loss = 0.365253
I0605 23:58:43.685881 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348539 (* 1 = 0.348539 loss)
I0605 23:58:43.685894 54715 sgd_solver.cpp:106] Iteration 1080, lr = 0.00982682
I0605 23:58:53.057701 54715 solver.cpp:237] Iteration 1083, loss = 0.365059
I0605 23:58:53.057752 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.39916 (* 1 = 0.39916 loss)
I0605 23:58:53.057762 54715 sgd_solver.cpp:106] Iteration 1083, lr = 0.00982634
I0605 23:59:02.430567 54715 solver.cpp:237] Iteration 1086, loss = 0.367043
I0605 23:59:02.430618 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.455715 (* 1 = 0.455715 loss)
I0605 23:59:02.430629 54715 sgd_solver.cpp:106] Iteration 1086, lr = 0.00982586
I0605 23:59:11.801313 54715 solver.cpp:237] Iteration 1089, loss = 0.368421
I0605 23:59:11.801465 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.320649 (* 1 = 0.320649 loss)
I0605 23:59:11.801478 54715 sgd_solver.cpp:106] Iteration 1089, lr = 0.00982538
I0605 23:59:11.910748 54715 solver.cpp:341] Iteration 1090, Testing net (#0)
I0605 23:59:13.192804 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.788205
I0605 23:59:13.192847 54715 solver.cpp:409] Test net output #1: class_Acc = 0.843527
I0605 23:59:13.192853 54715 solver.cpp:409] Test net output #2: class_Acc = 0.649497
I0605 23:59:13.192864 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.459278 (* 1 = 0.459278 loss)
I0605 23:59:22.457808 54715 solver.cpp:237] Iteration 1092, loss = 0.366939
I0605 23:59:22.457861 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.36387 (* 1 = 0.36387 loss)
I0605 23:59:22.457871 54715 sgd_solver.cpp:106] Iteration 1092, lr = 0.0098249
I0605 23:59:31.831836 54715 solver.cpp:237] Iteration 1095, loss = 0.367447
I0605 23:59:31.831889 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334374 (* 1 = 0.334374 loss)
I0605 23:59:31.831900 54715 sgd_solver.cpp:106] Iteration 1095, lr = 0.00982441
I0605 23:59:41.203765 54715 solver.cpp:237] Iteration 1098, loss = 0.370452
I0605 23:59:41.203811 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359078 (* 1 = 0.359078 loss)
I0605 23:59:41.203822 54715 sgd_solver.cpp:106] Iteration 1098, lr = 0.00982393
I0605 23:59:44.436329 54715 solver.cpp:341] Iteration 1100, Testing net (#0)
I0605 23:59:45.719516 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.807552
I0605 23:59:45.719557 54715 solver.cpp:409] Test net output #1: class_Acc = 0.907331
I0605 23:59:45.719563 54715 solver.cpp:409] Test net output #2: class_Acc = 0.589245
I0605 23:59:45.719573 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.421448 (* 1 = 0.421448 loss)
I0605 23:59:51.858846 54715 solver.cpp:237] Iteration 1101, loss = 0.36934
I0605 23:59:51.858892 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.323236 (* 1 = 0.323236 loss)
I0605 23:59:51.858903 54715 sgd_solver.cpp:106] Iteration 1101, lr = 0.00982345
I0606 00:00:01.231309 54715 solver.cpp:237] Iteration 1104, loss = 0.369605
I0606 00:00:01.231364 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.406297 (* 1 = 0.406297 loss)
I0606 00:00:01.231374 54715 sgd_solver.cpp:106] Iteration 1104, lr = 0.00982297
I0606 00:00:10.608597 54715 solver.cpp:237] Iteration 1107, loss = 0.368956
I0606 00:00:10.608649 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.383679 (* 1 = 0.383679 loss)
I0606 00:00:10.608659 54715 sgd_solver.cpp:106] Iteration 1107, lr = 0.00982248
I0606 00:00:16.967855 54715 solver.cpp:341] Iteration 1110, Testing net (#0)
I0606 00:00:18.250612 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.772157
I0606 00:00:18.250659 54715 solver.cpp:409] Test net output #1: class_Acc = 0.9059
I0606 00:00:18.250666 54715 solver.cpp:409] Test net output #2: class_Acc = 0.481151
I0606 00:00:18.250676 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.496155 (* 1 = 0.496155 loss)
I0606 00:00:21.263804 54715 solver.cpp:237] Iteration 1110, loss = 0.364176
I0606 00:00:21.263855 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.339804 (* 1 = 0.339804 loss)
I0606 00:00:21.263866 54715 sgd_solver.cpp:106] Iteration 1110, lr = 0.009822
I0606 00:00:30.639132 54715 solver.cpp:237] Iteration 1113, loss = 0.365496
I0606 00:00:30.639183 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395947 (* 1 = 0.395947 loss)
I0606 00:00:30.639195 54715 sgd_solver.cpp:106] Iteration 1113, lr = 0.00982152
I0606 00:00:40.008966 54715 solver.cpp:237] Iteration 1116, loss = 0.365652
I0606 00:00:40.009017 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395349 (* 1 = 0.395349 loss)
I0606 00:00:40.009027 54715 sgd_solver.cpp:106] Iteration 1116, lr = 0.00982104
I0606 00:00:49.381461 54715 solver.cpp:237] Iteration 1119, loss = 0.363495
I0606 00:00:49.381577 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.373522 (* 1 = 0.373522 loss)
I0606 00:00:49.381593 54715 sgd_solver.cpp:106] Iteration 1119, lr = 0.00982056
I0606 00:00:49.490896 54715 solver.cpp:341] Iteration 1120, Testing net (#0)
I0606 00:00:50.774052 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.7971
I0606 00:00:50.774098 54715 solver.cpp:409] Test net output #1: class_Acc = 0.856924
I0606 00:00:50.774104 54715 solver.cpp:409] Test net output #2: class_Acc = 0.652794
I0606 00:00:50.774113 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.444405 (* 1 = 0.444405 loss)
I0606 00:01:00.031803 54715 solver.cpp:237] Iteration 1122, loss = 0.363032
I0606 00:01:00.031858 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.333215 (* 1 = 0.333215 loss)
I0606 00:01:00.031870 54715 sgd_solver.cpp:106] Iteration 1122, lr = 0.00982007
I0606 00:01:09.405028 54715 solver.cpp:237] Iteration 1125, loss = 0.364176
I0606 00:01:09.405077 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.38357 (* 1 = 0.38357 loss)
I0606 00:01:09.405087 54715 sgd_solver.cpp:106] Iteration 1125, lr = 0.00981959
I0606 00:01:18.778343 54715 solver.cpp:237] Iteration 1128, loss = 0.36494
I0606 00:01:18.778388 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366519 (* 1 = 0.366519 loss)
I0606 00:01:18.778398 54715 sgd_solver.cpp:106] Iteration 1128, lr = 0.00981911
I0606 00:01:22.013070 54715 solver.cpp:341] Iteration 1130, Testing net (#0)
I0606 00:01:23.295753 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.807984
I0606 00:01:23.295796 54715 solver.cpp:409] Test net output #1: class_Acc = 0.933305
I0606 00:01:23.295804 54715 solver.cpp:409] Test net output #2: class_Acc = 0.516732
I0606 00:01:23.295814 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.41722 (* 1 = 0.41722 loss)
I0606 00:01:29.433594 54715 solver.cpp:237] Iteration 1131, loss = 0.359818
I0606 00:01:29.433647 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.38434 (* 1 = 0.38434 loss)
I0606 00:01:29.433657 54715 sgd_solver.cpp:106] Iteration 1131, lr = 0.00981863
I0606 00:01:38.808154 54715 solver.cpp:237] Iteration 1134, loss = 0.362697
I0606 00:01:38.808200 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.402935 (* 1 = 0.402935 loss)
I0606 00:01:38.808210 54715 sgd_solver.cpp:106] Iteration 1134, lr = 0.00981815
I0606 00:01:48.180025 54715 solver.cpp:237] Iteration 1137, loss = 0.364692
I0606 00:01:48.180076 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.428551 (* 1 = 0.428551 loss)
I0606 00:01:48.180086 54715 sgd_solver.cpp:106] Iteration 1137, lr = 0.00981766
I0606 00:01:54.538660 54715 solver.cpp:341] Iteration 1140, Testing net (#0)
I0606 00:01:55.821429 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.8178
I0606 00:01:55.821478 54715 solver.cpp:409] Test net output #1: class_Acc = 0.923987
I0606 00:01:55.821485 54715 solver.cpp:409] Test net output #2: class_Acc = 0.567833
I0606 00:01:55.821496 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.395423 (* 1 = 0.395423 loss)
I0606 00:01:58.835397 54715 solver.cpp:237] Iteration 1140, loss = 0.363582
I0606 00:01:58.835448 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3764 (* 1 = 0.3764 loss)
I0606 00:01:58.835459 54715 sgd_solver.cpp:106] Iteration 1140, lr = 0.00981718
I0606 00:02:08.207537 54715 solver.cpp:237] Iteration 1143, loss = 0.36498
I0606 00:02:08.207581 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.458357 (* 1 = 0.458357 loss)
I0606 00:02:08.207592 54715 sgd_solver.cpp:106] Iteration 1143, lr = 0.0098167
I0606 00:02:17.577834 54715 solver.cpp:237] Iteration 1146, loss = 0.368046
I0606 00:02:17.577884 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.38804 (* 1 = 0.38804 loss)
I0606 00:02:17.577896 54715 sgd_solver.cpp:106] Iteration 1146, lr = 0.00981622
I0606 00:02:26.949985 54715 solver.cpp:237] Iteration 1149, loss = 0.364827
I0606 00:02:26.950099 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.336525 (* 1 = 0.336525 loss)
I0606 00:02:26.950116 54715 sgd_solver.cpp:106] Iteration 1149, lr = 0.00981573
I0606 00:02:27.059442 54715 solver.cpp:341] Iteration 1150, Testing net (#0)
I0606 00:02:28.340028 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.767877
I0606 00:02:28.340070 54715 solver.cpp:409] Test net output #1: class_Acc = 0.924725
I0606 00:02:28.340076 54715 solver.cpp:409] Test net output #2: class_Acc = 0.394894
I0606 00:02:28.340086 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.543181 (* 1 = 0.543181 loss)
I0606 00:02:37.603593 54715 solver.cpp:237] Iteration 1152, loss = 0.360894
I0606 00:02:37.603639 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.409131 (* 1 = 0.409131 loss)
I0606 00:02:37.603649 54715 sgd_solver.cpp:106] Iteration 1152, lr = 0.00981525
I0606 00:02:46.975229 54715 solver.cpp:237] Iteration 1155, loss = 0.360904
I0606 00:02:46.975276 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.426272 (* 1 = 0.426272 loss)
I0606 00:02:46.975286 54715 sgd_solver.cpp:106] Iteration 1155, lr = 0.00981477
I0606 00:02:56.346837 54715 solver.cpp:237] Iteration 1158, loss = 0.360293
I0606 00:02:56.346889 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.332133 (* 1 = 0.332133 loss)
I0606 00:02:56.346899 54715 sgd_solver.cpp:106] Iteration 1158, lr = 0.00981429
I0606 00:02:59.580016 54715 solver.cpp:341] Iteration 1160, Testing net (#0)
I0606 00:03:00.862896 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.825836
I0606 00:03:00.862943 54715 solver.cpp:409] Test net output #1: class_Acc = 0.920554
I0606 00:03:00.862951 54715 solver.cpp:409] Test net output #2: class_Acc = 0.590485
I0606 00:03:00.862960 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.382029 (* 1 = 0.382029 loss)
I0606 00:03:07.001708 54715 solver.cpp:237] Iteration 1161, loss = 0.358119
I0606 00:03:07.001757 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.355092 (* 1 = 0.355092 loss)
I0606 00:03:07.001768 54715 sgd_solver.cpp:106] Iteration 1161, lr = 0.0098138
I0606 00:03:15.015967 54715 softmax_loss_layer.cu:194] weight loss 0 =0.253246 weight loss 1 =1 weight loss 2 =0
I0606 00:03:16.373194 54715 solver.cpp:237] Iteration 1164, loss = 0.358314
I0606 00:03:16.373244 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.344676 (* 1 = 0.344676 loss)
I0606 00:03:16.373255 54715 sgd_solver.cpp:106] Iteration 1164, lr = 0.00981332
I0606 00:03:25.746243 54715 solver.cpp:237] Iteration 1167, loss = 0.361208
I0606 00:03:25.746295 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.393131 (* 1 = 0.393131 loss)
I0606 00:03:25.746306 54715 sgd_solver.cpp:106] Iteration 1167, lr = 0.00981284
I0606 00:03:32.103263 54715 solver.cpp:341] Iteration 1170, Testing net (#0)
I0606 00:03:33.385839 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.819203
I0606 00:03:33.385885 54715 solver.cpp:409] Test net output #1: class_Acc = 0.913226
I0606 00:03:33.385892 54715 solver.cpp:409] Test net output #2: class_Acc = 0.596745
I0606 00:03:33.385903 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.396157 (* 1 = 0.396157 loss)
I0606 00:03:36.398591 54715 solver.cpp:237] Iteration 1170, loss = 0.35922
I0606 00:03:36.398643 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351015 (* 1 = 0.351015 loss)
I0606 00:03:36.398655 54715 sgd_solver.cpp:106] Iteration 1170, lr = 0.00981236
I0606 00:03:45.768715 54715 solver.cpp:237] Iteration 1173, loss = 0.36187
I0606 00:03:45.768767 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.315201 (* 1 = 0.315201 loss)
I0606 00:03:45.768776 54715 sgd_solver.cpp:106] Iteration 1173, lr = 0.00981188
I0606 00:03:55.140076 54715 solver.cpp:237] Iteration 1176, loss = 0.363006
I0606 00:03:55.140126 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350386 (* 1 = 0.350386 loss)
I0606 00:03:55.140137 54715 sgd_solver.cpp:106] Iteration 1176, lr = 0.00981139
I0606 00:04:04.514483 54715 solver.cpp:237] Iteration 1179, loss = 0.361996
I0606 00:04:04.514588 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.402449 (* 1 = 0.402449 loss)
I0606 00:04:04.514601 54715 sgd_solver.cpp:106] Iteration 1179, lr = 0.00981091
I0606 00:04:04.623926 54715 solver.cpp:341] Iteration 1180, Testing net (#0)
I0606 00:04:05.906762 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.824714
I0606 00:04:05.906805 54715 solver.cpp:409] Test net output #1: class_Acc = 0.932513
I0606 00:04:05.906812 54715 solver.cpp:409] Test net output #2: class_Acc = 0.543201
I0606 00:04:05.906822 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.385836 (* 1 = 0.385836 loss)
I0606 00:04:15.171217 54715 solver.cpp:237] Iteration 1182, loss = 0.360967
I0606 00:04:15.171267 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348778 (* 1 = 0.348778 loss)
I0606 00:04:15.171277 54715 sgd_solver.cpp:106] Iteration 1182, lr = 0.00981043
I0606 00:04:18.106827 54715 softmax_loss_layer.cu:194] weight loss 0 =0.293128 weight loss 1 =1 weight loss 2 =0
I0606 00:04:24.547578 54715 solver.cpp:237] Iteration 1185, loss = 0.359715
I0606 00:04:24.547632 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.381854 (* 1 = 0.381854 loss)
I0606 00:04:24.547644 54715 sgd_solver.cpp:106] Iteration 1185, lr = 0.00980995
I0606 00:04:33.921087 54715 solver.cpp:237] Iteration 1188, loss = 0.358966
I0606 00:04:33.921133 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.399668 (* 1 = 0.399668 loss)
I0606 00:04:33.921142 54715 sgd_solver.cpp:106] Iteration 1188, lr = 0.00980946
I0606 00:04:37.153051 54715 solver.cpp:341] Iteration 1190, Testing net (#0)
I0606 00:04:38.436153 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.777423
I0606 00:04:38.436198 54715 solver.cpp:409] Test net output #1: class_Acc = 0.818301
I0606 00:04:38.436205 54715 solver.cpp:409] Test net output #2: class_Acc = 0.68356
I0606 00:04:38.436216 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.477286 (* 1 = 0.477286 loss)
I0606 00:04:44.573582 54715 solver.cpp:237] Iteration 1191, loss = 0.360215
I0606 00:04:44.573632 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.392725 (* 1 = 0.392725 loss)
I0606 00:04:44.573643 54715 sgd_solver.cpp:106] Iteration 1191, lr = 0.00980898
I0606 00:04:53.942168 54715 solver.cpp:237] Iteration 1194, loss = 0.357084
I0606 00:04:53.942222 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.319134 (* 1 = 0.319134 loss)
I0606 00:04:53.942232 54715 sgd_solver.cpp:106] Iteration 1194, lr = 0.0098085
I0606 00:05:03.315670 54715 solver.cpp:237] Iteration 1197, loss = 0.357261
I0606 00:05:03.315721 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.394259 (* 1 = 0.394259 loss)
I0606 00:05:03.315731 54715 sgd_solver.cpp:106] Iteration 1197, lr = 0.00980802
I0606 00:05:04.696841 54715 softmax_loss_layer.cu:194] weight loss 0 =0.276588 weight loss 1 =1 weight loss 2 =0
I0606 00:05:09.677572 54715 solver.cpp:341] Iteration 1200, Testing net (#0)
I0606 00:05:10.959241 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.785518
I0606 00:05:10.959286 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893926
I0606 00:05:10.959293 54715 solver.cpp:409] Test net output #2: class_Acc = 0.556044
I0606 00:05:10.959303 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.453677 (* 1 = 0.453677 loss)
I0606 00:05:13.972553 54715 solver.cpp:237] Iteration 1200, loss = 0.35891
I0606 00:05:13.972604 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.372768 (* 1 = 0.372768 loss)
I0606 00:05:13.972615 54715 sgd_solver.cpp:106] Iteration 1200, lr = 0.00980753
I0606 00:05:23.347393 54715 solver.cpp:237] Iteration 1203, loss = 0.36002
I0606 00:05:23.347447 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.329368 (* 1 = 0.329368 loss)
I0606 00:05:23.347458 54715 sgd_solver.cpp:106] Iteration 1203, lr = 0.00980705
I0606 00:05:32.722057 54715 solver.cpp:237] Iteration 1206, loss = 0.361242
I0606 00:05:32.722116 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.343051 (* 1 = 0.343051 loss)
I0606 00:05:32.722129 54715 sgd_solver.cpp:106] Iteration 1206, lr = 0.00980657
I0606 00:05:39.573932 54715 softmax_loss_layer.cu:194] weight loss 0 =0.572844 weight loss 1 =1 weight loss 2 =0
I0606 00:05:42.099850 54715 solver.cpp:237] Iteration 1209, loss = 0.360232
I0606 00:05:42.099951 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.328763 (* 1 = 0.328763 loss)
I0606 00:05:42.099963 54715 sgd_solver.cpp:106] Iteration 1209, lr = 0.00980609
I0606 00:05:42.209257 54715 solver.cpp:341] Iteration 1210, Testing net (#0)
I0606 00:05:43.491279 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.811323
I0606 00:05:43.491325 54715 solver.cpp:409] Test net output #1: class_Acc = 0.889306
I0606 00:05:43.491333 54715 solver.cpp:409] Test net output #2: class_Acc = 0.648852
I0606 00:05:43.491343 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.416069 (* 1 = 0.416069 loss)
I0606 00:05:52.756093 54715 solver.cpp:237] Iteration 1212, loss = 0.359534
I0606 00:05:52.756160 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292737 (* 1 = 0.292737 loss)
I0606 00:05:52.756173 54715 sgd_solver.cpp:106] Iteration 1212, lr = 0.0098056
I0606 00:06:01.941458 54715 softmax_loss_layer.cu:194] weight loss 0 =0.229363 weight loss 1 =1 weight loss 2 =0
I0606 00:06:02.130970 54715 solver.cpp:237] Iteration 1215, loss = 0.357793
I0606 00:06:02.131016 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.364225 (* 1 = 0.364225 loss)
I0606 00:06:02.131026 54715 sgd_solver.cpp:106] Iteration 1215, lr = 0.00980512
I0606 00:06:11.504415 54715 solver.cpp:237] Iteration 1218, loss = 0.3574
I0606 00:06:11.504468 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337255 (* 1 = 0.337255 loss)
I0606 00:06:11.504480 54715 sgd_solver.cpp:106] Iteration 1218, lr = 0.00980464
I0606 00:06:14.740837 54715 solver.cpp:341] Iteration 1220, Testing net (#0)
I0606 00:06:16.021328 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.790938
I0606 00:06:16.021373 54715 solver.cpp:409] Test net output #1: class_Acc = 0.938721
I0606 00:06:16.021379 54715 solver.cpp:409] Test net output #2: class_Acc = 0.447834
I0606 00:06:16.021389 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.462753 (* 1 = 0.462753 loss)
I0606 00:06:22.160244 54715 solver.cpp:237] Iteration 1221, loss = 0.354744
I0606 00:06:22.160300 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318168 (* 1 = 0.318168 loss)
I0606 00:06:22.160311 54715 sgd_solver.cpp:106] Iteration 1221, lr = 0.00980416
I0606 00:06:31.533310 54715 solver.cpp:237] Iteration 1224, loss = 0.35398
I0606 00:06:31.533357 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347715 (* 1 = 0.347715 loss)
I0606 00:06:31.533368 54715 sgd_solver.cpp:106] Iteration 1224, lr = 0.00980368
I0606 00:06:37.204237 54715 softmax_loss_layer.cu:194] weight loss 0 =0.420068 weight loss 1 =1 weight loss 2 =0
I0606 00:06:38.771953 54715 softmax_loss_layer.cu:194] weight loss 0 =0.150549 weight loss 1 =1 weight loss 2 =0
I0606 00:06:40.905941 54715 solver.cpp:237] Iteration 1227, loss = 0.357315
I0606 00:06:40.905989 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367657 (* 1 = 0.367657 loss)
I0606 00:06:40.906000 54715 sgd_solver.cpp:106] Iteration 1227, lr = 0.00980319
I0606 00:06:46.187903 54715 softmax_loss_layer.cu:194] weight loss 0 =0.217815 weight loss 1 =1 weight loss 2 =0
I0606 00:06:47.264603 54715 solver.cpp:341] Iteration 1230, Testing net (#0)
I0606 00:06:48.547204 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.808951
I0606 00:06:48.547248 54715 solver.cpp:409] Test net output #1: class_Acc = 0.886879
I0606 00:06:48.547255 54715 solver.cpp:409] Test net output #2: class_Acc = 0.626345
I0606 00:06:48.547264 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.411477 (* 1 = 0.411477 loss)
I0606 00:06:51.559799 54715 solver.cpp:237] Iteration 1230, loss = 0.356738
I0606 00:06:51.559849 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318807 (* 1 = 0.318807 loss)
I0606 00:06:51.559859 54715 sgd_solver.cpp:106] Iteration 1230, lr = 0.00980271
I0606 00:06:59.967630 54715 softmax_loss_layer.cu:194] weight loss 0 =0.275339 weight loss 1 =1 weight loss 2 =0
I0606 00:07:00.935299 54715 solver.cpp:237] Iteration 1233, loss = 0.357141
I0606 00:07:00.935348 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.365154 (* 1 = 0.365154 loss)
I0606 00:07:00.935359 54715 sgd_solver.cpp:106] Iteration 1233, lr = 0.00980223
I0606 00:07:10.310151 54715 solver.cpp:237] Iteration 1236, loss = 0.359728
I0606 00:07:10.310202 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.387114 (* 1 = 0.387114 loss)
I0606 00:07:10.310214 54715 sgd_solver.cpp:106] Iteration 1236, lr = 0.00980175
I0606 00:07:19.683185 54715 solver.cpp:237] Iteration 1239, loss = 0.359951
I0606 00:07:19.683280 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345327 (* 1 = 0.345327 loss)
I0606 00:07:19.683291 54715 sgd_solver.cpp:106] Iteration 1239, lr = 0.00980126
I0606 00:07:19.792675 54715 solver.cpp:341] Iteration 1240, Testing net (#0)
I0606 00:07:21.075363 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.816021
I0606 00:07:21.075410 54715 solver.cpp:409] Test net output #1: class_Acc = 0.932488
I0606 00:07:21.075417 54715 solver.cpp:409] Test net output #2: class_Acc = 0.577134
I0606 00:07:21.075426 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.406092 (* 1 = 0.406092 loss)
I0606 00:07:30.340994 54715 solver.cpp:237] Iteration 1242, loss = 0.359706
I0606 00:07:30.341043 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.375061 (* 1 = 0.375061 loss)
I0606 00:07:30.341054 54715 sgd_solver.cpp:106] Iteration 1242, lr = 0.00980078
I0606 00:07:39.713915 54715 solver.cpp:237] Iteration 1245, loss = 0.355869
I0606 00:07:39.713965 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305957 (* 1 = 0.305957 loss)
I0606 00:07:39.713975 54715 sgd_solver.cpp:106] Iteration 1245, lr = 0.0098003
I0606 00:07:49.084214 54715 solver.cpp:237] Iteration 1248, loss = 0.35677
I0606 00:07:49.084259 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.393225 (* 1 = 0.393225 loss)
I0606 00:07:49.084270 54715 sgd_solver.cpp:106] Iteration 1248, lr = 0.00979982
I0606 00:07:52.318641 54715 solver.cpp:341] Iteration 1250, Testing net (#0)
I0606 00:07:53.599707 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.80183
I0606 00:07:53.599750 54715 solver.cpp:409] Test net output #1: class_Acc = 0.93683
I0606 00:07:53.599757 54715 solver.cpp:409] Test net output #2: class_Acc = 0.520672
I0606 00:07:53.599767 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.426694 (* 1 = 0.426694 loss)
I0606 00:07:59.739164 54715 solver.cpp:237] Iteration 1251, loss = 0.354954
I0606 00:07:59.739212 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35154 (* 1 = 0.35154 loss)
I0606 00:07:59.739223 54715 sgd_solver.cpp:106] Iteration 1251, lr = 0.00979933
I0606 00:08:09.112001 54715 solver.cpp:237] Iteration 1254, loss = 0.352165
I0606 00:08:09.112048 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.398824 (* 1 = 0.398824 loss)
I0606 00:08:09.112059 54715 sgd_solver.cpp:106] Iteration 1254, lr = 0.00979885
I0606 00:08:15.169134 54715 softmax_loss_layer.cu:194] weight loss 0 =0.292531 weight loss 1 =1 weight loss 2 =0
I0606 00:08:18.481943 54715 solver.cpp:237] Iteration 1257, loss = 0.352948
I0606 00:08:18.481992 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3601 (* 1 = 0.3601 loss)
I0606 00:08:18.482002 54715 sgd_solver.cpp:106] Iteration 1257, lr = 0.00979837
I0606 00:08:20.249104 54715 softmax_loss_layer.cu:194] weight loss 0 =0.329919 weight loss 1 =1 weight loss 2 =0
I0606 00:08:24.837968 54715 solver.cpp:341] Iteration 1260, Testing net (#0)
I0606 00:08:26.121757 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.827638
I0606 00:08:26.121800 54715 solver.cpp:409] Test net output #1: class_Acc = 0.927667
I0606 00:08:26.121807 54715 solver.cpp:409] Test net output #2: class_Acc = 0.574052
I0606 00:08:26.121816 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.376101 (* 1 = 0.376101 loss)
I0606 00:08:29.140080 54715 solver.cpp:237] Iteration 1260, loss = 0.354297
I0606 00:08:29.140128 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.328447 (* 1 = 0.328447 loss)
I0606 00:08:29.140151 54715 sgd_solver.cpp:106] Iteration 1260, lr = 0.00979789
I0606 00:08:38.516245 54715 solver.cpp:237] Iteration 1263, loss = 0.357088
I0606 00:08:38.516297 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.391275 (* 1 = 0.391275 loss)
I0606 00:08:38.516309 54715 sgd_solver.cpp:106] Iteration 1263, lr = 0.0097974
I0606 00:08:47.891655 54715 solver.cpp:237] Iteration 1266, loss = 0.35613
I0606 00:08:47.891703 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.405751 (* 1 = 0.405751 loss)
I0606 00:08:47.891713 54715 sgd_solver.cpp:106] Iteration 1266, lr = 0.00979692
I0606 00:08:57.267508 54715 solver.cpp:237] Iteration 1269, loss = 0.356576
I0606 00:08:57.267627 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.32697 (* 1 = 0.32697 loss)
I0606 00:08:57.267640 54715 sgd_solver.cpp:106] Iteration 1269, lr = 0.00979644
I0606 00:08:57.376888 54715 solver.cpp:341] Iteration 1270, Testing net (#0)
I0606 00:08:58.658988 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.811596
I0606 00:08:58.659034 54715 solver.cpp:409] Test net output #1: class_Acc = 0.95008
I0606 00:08:58.659040 54715 solver.cpp:409] Test net output #2: class_Acc = 0.496341
I0606 00:08:58.659049 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.403742 (* 1 = 0.403742 loss)
I0606 00:09:05.787832 54715 softmax_loss_layer.cu:194] weight loss 0 =0.229933 weight loss 1 =1 weight loss 2 =0
I0606 00:09:07.921967 54715 solver.cpp:237] Iteration 1272, loss = 0.357433
I0606 00:09:07.922019 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327407 (* 1 = 0.327407 loss)
I0606 00:09:07.922029 54715 sgd_solver.cpp:106] Iteration 1272, lr = 0.00979596
I0606 00:09:17.294929 54715 solver.cpp:237] Iteration 1275, loss = 0.356823
I0606 00:09:17.294980 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.386611 (* 1 = 0.386611 loss)
I0606 00:09:17.294989 54715 sgd_solver.cpp:106] Iteration 1275, lr = 0.00979547
I0606 00:09:26.667611 54715 solver.cpp:237] Iteration 1278, loss = 0.353376
I0606 00:09:26.667663 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.342357 (* 1 = 0.342357 loss)
I0606 00:09:26.667673 54715 sgd_solver.cpp:106] Iteration 1278, lr = 0.00979499
I0606 00:09:29.905776 54715 solver.cpp:341] Iteration 1280, Testing net (#0)
I0606 00:09:31.188947 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.83702
I0606 00:09:31.188993 54715 solver.cpp:409] Test net output #1: class_Acc = 0.8749
I0606 00:09:31.189000 54715 solver.cpp:409] Test net output #2: class_Acc = 0.747159
I0606 00:09:31.189009 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.361064 (* 1 = 0.361064 loss)
I0606 00:09:37.327491 54715 solver.cpp:237] Iteration 1281, loss = 0.353152
I0606 00:09:37.327539 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337712 (* 1 = 0.337712 loss)
I0606 00:09:37.327550 54715 sgd_solver.cpp:106] Iteration 1281, lr = 0.00979451
I0606 00:09:46.698102 54715 solver.cpp:237] Iteration 1284, loss = 0.351822
I0606 00:09:46.698150 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.314308 (* 1 = 0.314308 loss)
I0606 00:09:46.698160 54715 sgd_solver.cpp:106] Iteration 1284, lr = 0.00979403
I0606 00:09:56.070894 54715 solver.cpp:237] Iteration 1287, loss = 0.353618
I0606 00:09:56.070946 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.336427 (* 1 = 0.336427 loss)
I0606 00:09:56.070966 54715 sgd_solver.cpp:106] Iteration 1287, lr = 0.00979354
I0606 00:10:02.430474 54715 solver.cpp:341] Iteration 1290, Testing net (#0)
I0606 00:10:03.714360 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.811657
I0606 00:10:03.714406 54715 solver.cpp:409] Test net output #1: class_Acc = 0.871252
I0606 00:10:03.714411 54715 solver.cpp:409] Test net output #2: class_Acc = 0.674871
I0606 00:10:03.714422 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.413075 (* 1 = 0.413075 loss)
I0606 00:10:06.727650 54715 solver.cpp:237] Iteration 1290, loss = 0.357418
I0606 00:10:06.727700 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.372612 (* 1 = 0.372612 loss)
I0606 00:10:06.727710 54715 sgd_solver.cpp:106] Iteration 1290, lr = 0.00979306
I0606 00:10:16.102342 54715 solver.cpp:237] Iteration 1293, loss = 0.356464
I0606 00:10:16.102391 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366077 (* 1 = 0.366077 loss)
I0606 00:10:16.102401 54715 sgd_solver.cpp:106] Iteration 1293, lr = 0.00979258
I0606 00:10:18.646706 54715 softmax_loss_layer.cu:194] weight loss 0 =0.313605 weight loss 1 =1 weight loss 2 =0
I0606 00:10:25.472875 54715 solver.cpp:237] Iteration 1296, loss = 0.358578
I0606 00:10:25.472925 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.427203 (* 1 = 0.427203 loss)
I0606 00:10:25.472935 54715 sgd_solver.cpp:106] Iteration 1296, lr = 0.0097921
I0606 00:10:34.846173 54715 solver.cpp:237] Iteration 1299, loss = 0.36302
I0606 00:10:34.846244 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3752 (* 1 = 0.3752 loss)
I0606 00:10:34.846257 54715 sgd_solver.cpp:106] Iteration 1299, lr = 0.00979161
I0606 00:10:34.955627 54715 solver.cpp:341] Iteration 1300, Testing net (#0)
I0606 00:10:36.239213 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.823978
I0606 00:10:36.239255 54715 solver.cpp:409] Test net output #1: class_Acc = 0.889675
I0606 00:10:36.239262 54715 solver.cpp:409] Test net output #2: class_Acc = 0.673868
I0606 00:10:36.239272 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.395136 (* 1 = 0.395136 loss)
I0606 00:10:45.501933 54715 solver.cpp:237] Iteration 1302, loss = 0.36077
I0606 00:10:45.501984 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360312 (* 1 = 0.360312 loss)
I0606 00:10:45.501996 54715 sgd_solver.cpp:106] Iteration 1302, lr = 0.00979113
I0606 00:10:54.873630 54715 solver.cpp:237] Iteration 1305, loss = 0.356824
I0606 00:10:54.873680 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.320437 (* 1 = 0.320437 loss)
I0606 00:10:54.873692 54715 sgd_solver.cpp:106] Iteration 1305, lr = 0.00979065
I0606 00:11:04.247735 54715 solver.cpp:237] Iteration 1308, loss = 0.356124
I0606 00:11:04.247784 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.342346 (* 1 = 0.342346 loss)
I0606 00:11:04.247794 54715 sgd_solver.cpp:106] Iteration 1308, lr = 0.00979017
I0606 00:11:07.480082 54715 solver.cpp:341] Iteration 1310, Testing net (#0)
I0606 00:11:08.762895 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.821542
I0606 00:11:08.762941 54715 solver.cpp:409] Test net output #1: class_Acc = 0.91466
I0606 00:11:08.762948 54715 solver.cpp:409] Test net output #2: class_Acc = 0.594881
I0606 00:11:08.762959 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.390792 (* 1 = 0.390792 loss)
I0606 00:11:14.902977 54715 solver.cpp:237] Iteration 1311, loss = 0.356333
I0606 00:11:14.903028 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3852 (* 1 = 0.3852 loss)
I0606 00:11:14.903038 54715 sgd_solver.cpp:106] Iteration 1311, lr = 0.00978968
I0606 00:11:24.276564 54715 solver.cpp:237] Iteration 1314, loss = 0.352187
I0606 00:11:24.276612 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.330895 (* 1 = 0.330895 loss)
I0606 00:11:24.276623 54715 sgd_solver.cpp:106] Iteration 1314, lr = 0.0097892
I0606 00:11:33.647532 54715 solver.cpp:237] Iteration 1317, loss = 0.349024
I0606 00:11:33.647594 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340289 (* 1 = 0.340289 loss)
I0606 00:11:33.647606 54715 sgd_solver.cpp:106] Iteration 1317, lr = 0.00978872
I0606 00:11:40.005654 54715 solver.cpp:341] Iteration 1320, Testing net (#0)
I0606 00:11:41.289008 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.842513
I0606 00:11:41.289054 54715 solver.cpp:409] Test net output #1: class_Acc = 0.902037
I0606 00:11:41.289060 54715 solver.cpp:409] Test net output #2: class_Acc = 0.681857
I0606 00:11:41.289070 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.350321 (* 1 = 0.350321 loss)
I0606 00:11:44.302613 54715 solver.cpp:237] Iteration 1320, loss = 0.347963
I0606 00:11:44.302666 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368176 (* 1 = 0.368176 loss)
I0606 00:11:44.302677 54715 sgd_solver.cpp:106] Iteration 1320, lr = 0.00978824
I0606 00:11:53.674296 54715 solver.cpp:237] Iteration 1323, loss = 0.34899
I0606 00:11:53.674343 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.34099 (* 1 = 0.34099 loss)
I0606 00:11:53.674355 54715 sgd_solver.cpp:106] Iteration 1323, lr = 0.00978775
I0606 00:12:03.049489 54715 solver.cpp:237] Iteration 1326, loss = 0.347783
I0606 00:12:03.049541 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.395695 (* 1 = 0.395695 loss)
I0606 00:12:03.049552 54715 sgd_solver.cpp:106] Iteration 1326, lr = 0.00978727
I0606 00:12:12.425683 54715 solver.cpp:237] Iteration 1329, loss = 0.348514
I0606 00:12:12.425809 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361394 (* 1 = 0.361394 loss)
I0606 00:12:12.425822 54715 sgd_solver.cpp:106] Iteration 1329, lr = 0.00978679
I0606 00:12:12.535131 54715 solver.cpp:341] Iteration 1330, Testing net (#0)
I0606 00:12:13.816963 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.834438
I0606 00:12:13.817008 54715 solver.cpp:409] Test net output #1: class_Acc = 0.923221
I0606 00:12:13.817015 54715 solver.cpp:409] Test net output #2: class_Acc = 0.634254
I0606 00:12:13.817025 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.369423 (* 1 = 0.369423 loss)
I0606 00:12:23.081885 54715 solver.cpp:237] Iteration 1332, loss = 0.346953
I0606 00:12:23.081938 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340789 (* 1 = 0.340789 loss)
I0606 00:12:23.081950 54715 sgd_solver.cpp:106] Iteration 1332, lr = 0.00978631
I0606 00:12:32.459197 54715 solver.cpp:237] Iteration 1335, loss = 0.34824
I0606 00:12:32.459245 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.302914 (* 1 = 0.302914 loss)
I0606 00:12:32.459257 54715 sgd_solver.cpp:106] Iteration 1335, lr = 0.00978582
I0606 00:12:41.829951 54715 solver.cpp:237] Iteration 1338, loss = 0.347275
I0606 00:12:41.829995 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310617 (* 1 = 0.310617 loss)
I0606 00:12:41.830005 54715 sgd_solver.cpp:106] Iteration 1338, lr = 0.00978534
I0606 00:12:45.062193 54715 solver.cpp:341] Iteration 1340, Testing net (#0)
I0606 00:12:46.343956 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.825377
I0606 00:12:46.343997 54715 solver.cpp:409] Test net output #1: class_Acc = 0.919425
I0606 00:12:46.344004 54715 solver.cpp:409] Test net output #2: class_Acc = 0.57128
I0606 00:12:46.344015 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.385515 (* 1 = 0.385515 loss)
I0606 00:12:52.483114 54715 solver.cpp:237] Iteration 1341, loss = 0.34606
I0606 00:12:52.483165 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.436333 (* 1 = 0.436333 loss)
I0606 00:12:52.483176 54715 sgd_solver.cpp:106] Iteration 1341, lr = 0.00978486
I0606 00:13:01.859469 54715 solver.cpp:237] Iteration 1344, loss = 0.347084
I0606 00:13:01.859527 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359151 (* 1 = 0.359151 loss)
I0606 00:13:01.859539 54715 sgd_solver.cpp:106] Iteration 1344, lr = 0.00978438
I0606 00:13:11.232930 54715 solver.cpp:237] Iteration 1347, loss = 0.350559
I0606 00:13:11.232990 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.358063 (* 1 = 0.358063 loss)
I0606 00:13:11.233001 54715 sgd_solver.cpp:106] Iteration 1347, lr = 0.00978389
I0606 00:13:17.591783 54715 solver.cpp:341] Iteration 1350, Testing net (#0)
I0606 00:13:18.874291 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.802664
I0606 00:13:18.874336 54715 solver.cpp:409] Test net output #1: class_Acc = 0.891311
I0606 00:13:18.874343 54715 solver.cpp:409] Test net output #2: class_Acc = 0.581189
I0606 00:13:18.874353 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.445194 (* 1 = 0.445194 loss)
I0606 00:13:21.889784 54715 solver.cpp:237] Iteration 1350, loss = 0.347979
I0606 00:13:21.889834 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.317728 (* 1 = 0.317728 loss)
I0606 00:13:21.889845 54715 sgd_solver.cpp:106] Iteration 1350, lr = 0.00978341
I0606 00:13:31.262425 54715 solver.cpp:237] Iteration 1353, loss = 0.348601
I0606 00:13:31.262477 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.341286 (* 1 = 0.341286 loss)
I0606 00:13:31.262490 54715 sgd_solver.cpp:106] Iteration 1353, lr = 0.00978293
I0606 00:13:40.636575 54715 solver.cpp:237] Iteration 1356, loss = 0.347889
I0606 00:13:40.636623 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31163 (* 1 = 0.31163 loss)
I0606 00:13:40.636636 54715 sgd_solver.cpp:106] Iteration 1356, lr = 0.00978244
I0606 00:13:50.012693 54715 solver.cpp:237] Iteration 1359, loss = 0.35016
I0606 00:13:50.012763 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.290519 (* 1 = 0.290519 loss)
I0606 00:13:50.012774 54715 sgd_solver.cpp:106] Iteration 1359, lr = 0.00978196
I0606 00:13:50.122171 54715 solver.cpp:341] Iteration 1360, Testing net (#0)
I0606 00:13:51.404754 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.830842
I0606 00:13:51.404803 54715 solver.cpp:409] Test net output #1: class_Acc = 0.913616
I0606 00:13:51.404808 54715 solver.cpp:409] Test net output #2: class_Acc = 0.654457
I0606 00:13:51.404819 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.380419 (* 1 = 0.380419 loss)
I0606 00:14:00.665208 54715 solver.cpp:237] Iteration 1362, loss = 0.347824
I0606 00:14:00.665263 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.393201 (* 1 = 0.393201 loss)
I0606 00:14:00.665272 54715 sgd_solver.cpp:106] Iteration 1362, lr = 0.00978148
I0606 00:14:10.040801 54715 solver.cpp:237] Iteration 1365, loss = 0.349542
I0606 00:14:10.040848 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.40894 (* 1 = 0.40894 loss)
I0606 00:14:10.040859 54715 sgd_solver.cpp:106] Iteration 1365, lr = 0.009781
I0606 00:14:19.412979 54715 solver.cpp:237] Iteration 1368, loss = 0.351698
I0606 00:14:19.413022 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.317112 (* 1 = 0.317112 loss)
I0606 00:14:19.413033 54715 sgd_solver.cpp:106] Iteration 1368, lr = 0.00978051
I0606 00:14:22.648916 54715 solver.cpp:341] Iteration 1370, Testing net (#0)
I0606 00:14:23.932147 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.842242
I0606 00:14:23.932194 54715 solver.cpp:409] Test net output #1: class_Acc = 0.915815
I0606 00:14:23.932201 54715 solver.cpp:409] Test net output #2: class_Acc = 0.661821
I0606 00:14:23.932211 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.351745 (* 1 = 0.351745 loss)
I0606 00:14:30.070194 54715 solver.cpp:237] Iteration 1371, loss = 0.354991
I0606 00:14:30.070245 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.324262 (* 1 = 0.324262 loss)
I0606 00:14:30.070255 54715 sgd_solver.cpp:106] Iteration 1371, lr = 0.00978003
I0606 00:14:39.445915 54715 solver.cpp:237] Iteration 1374, loss = 0.352163
I0606 00:14:39.445963 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286413 (* 1 = 0.286413 loss)
I0606 00:14:39.445974 54715 sgd_solver.cpp:106] Iteration 1374, lr = 0.00977955
I0606 00:14:48.823473 54715 solver.cpp:237] Iteration 1377, loss = 0.347252
I0606 00:14:48.823521 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.349622 (* 1 = 0.349622 loss)
I0606 00:14:48.823530 54715 sgd_solver.cpp:106] Iteration 1377, lr = 0.00977907
I0606 00:14:55.183485 54715 solver.cpp:341] Iteration 1380, Testing net (#0)
I0606 00:14:56.465240 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.811778
I0606 00:14:56.465284 54715 solver.cpp:409] Test net output #1: class_Acc = 0.953368
I0606 00:14:56.465291 54715 solver.cpp:409] Test net output #2: class_Acc = 0.492881
I0606 00:14:56.465301 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.403601 (* 1 = 0.403601 loss)
I0606 00:14:59.481971 54715 solver.cpp:237] Iteration 1380, loss = 0.345228
I0606 00:14:59.482020 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35475 (* 1 = 0.35475 loss)
I0606 00:14:59.482031 54715 sgd_solver.cpp:106] Iteration 1380, lr = 0.00977858
I0606 00:15:08.856915 54715 solver.cpp:237] Iteration 1383, loss = 0.34353
I0606 00:15:08.856968 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.263913 (* 1 = 0.263913 loss)
I0606 00:15:08.856978 54715 sgd_solver.cpp:106] Iteration 1383, lr = 0.0097781
I0606 00:15:18.228847 54715 solver.cpp:237] Iteration 1386, loss = 0.340106
I0606 00:15:18.228894 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376292 (* 1 = 0.376292 loss)
I0606 00:15:18.228905 54715 sgd_solver.cpp:106] Iteration 1386, lr = 0.00977762
I0606 00:15:20.773741 54715 softmax_loss_layer.cu:194] weight loss 0 =0.269781 weight loss 1 =1 weight loss 2 =0
I0606 00:15:27.599607 54715 solver.cpp:237] Iteration 1389, loss = 0.340908
I0606 00:15:27.599679 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350147 (* 1 = 0.350147 loss)
I0606 00:15:27.599691 54715 sgd_solver.cpp:106] Iteration 1389, lr = 0.00977714
I0606 00:15:27.709070 54715 solver.cpp:341] Iteration 1390, Testing net (#0)
I0606 00:15:28.991195 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.817465
I0606 00:15:28.991245 54715 solver.cpp:409] Test net output #1: class_Acc = 0.905358
I0606 00:15:28.991251 54715 solver.cpp:409] Test net output #2: class_Acc = 0.612285
I0606 00:15:28.991261 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.422841 (* 1 = 0.422841 loss)
I0606 00:15:35.338589 54715 softmax_loss_layer.cu:194] weight loss 0 =0.374515 weight loss 1 =1 weight loss 2 =0
I0606 00:15:38.250355 54715 solver.cpp:237] Iteration 1392, loss = 0.345256
I0606 00:15:38.250406 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.418315 (* 1 = 0.418315 loss)
I0606 00:15:38.250416 54715 sgd_solver.cpp:106] Iteration 1392, lr = 0.00977665
I0606 00:15:47.625149 54715 solver.cpp:237] Iteration 1395, loss = 0.346779
I0606 00:15:47.625195 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318189 (* 1 = 0.318189 loss)
I0606 00:15:47.625206 54715 sgd_solver.cpp:106] Iteration 1395, lr = 0.00977617
I0606 00:15:56.995265 54715 solver.cpp:237] Iteration 1398, loss = 0.346007
I0606 00:15:56.995313 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321299 (* 1 = 0.321299 loss)
I0606 00:15:56.995323 54715 sgd_solver.cpp:106] Iteration 1398, lr = 0.00977569
I0606 00:16:00.229799 54715 solver.cpp:341] Iteration 1400, Testing net (#0)
I0606 00:16:01.511848 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.81943
I0606 00:16:01.511894 54715 solver.cpp:409] Test net output #1: class_Acc = 0.913595
I0606 00:16:01.511901 54715 solver.cpp:409] Test net output #2: class_Acc = 0.575962
I0606 00:16:01.511911 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.396563 (* 1 = 0.396563 loss)
I0606 00:16:07.648545 54715 solver.cpp:237] Iteration 1401, loss = 0.352715
I0606 00:16:07.648598 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.317068 (* 1 = 0.317068 loss)
I0606 00:16:07.648609 54715 sgd_solver.cpp:106] Iteration 1401, lr = 0.0097752
I0606 00:16:17.021844 54715 solver.cpp:237] Iteration 1404, loss = 0.353341
I0606 00:16:17.021893 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.288095 (* 1 = 0.288095 loss)
I0606 00:16:17.021903 54715 sgd_solver.cpp:106] Iteration 1404, lr = 0.00977472
I0606 00:16:26.395267 54715 solver.cpp:237] Iteration 1407, loss = 0.35126
I0606 00:16:26.395318 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.32373 (* 1 = 0.32373 loss)
I0606 00:16:26.395328 54715 sgd_solver.cpp:106] Iteration 1407, lr = 0.00977424
I0606 00:16:32.753116 54715 solver.cpp:341] Iteration 1410, Testing net (#0)
I0606 00:16:34.035763 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.831437
I0606 00:16:34.035807 54715 solver.cpp:409] Test net output #1: class_Acc = 0.92335
I0606 00:16:34.035814 54715 solver.cpp:409] Test net output #2: class_Acc = 0.614717
I0606 00:16:34.035823 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.370954 (* 1 = 0.370954 loss)
I0606 00:16:37.049299 54715 solver.cpp:237] Iteration 1410, loss = 0.348827
I0606 00:16:37.049348 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.404333 (* 1 = 0.404333 loss)
I0606 00:16:37.049360 54715 sgd_solver.cpp:106] Iteration 1410, lr = 0.00977376
I0606 00:16:46.422823 54715 solver.cpp:237] Iteration 1413, loss = 0.347457
I0606 00:16:46.422855 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.37281 (* 1 = 0.37281 loss)
I0606 00:16:46.422866 54715 sgd_solver.cpp:106] Iteration 1413, lr = 0.00977327
I0606 00:16:55.794492 54715 solver.cpp:237] Iteration 1416, loss = 0.345561
I0606 00:16:55.794543 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3662 (* 1 = 0.3662 loss)
I0606 00:16:55.794555 54715 sgd_solver.cpp:106] Iteration 1416, lr = 0.00977279
I0606 00:17:05.166378 54715 solver.cpp:237] Iteration 1419, loss = 0.343405
I0606 00:17:05.166491 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376853 (* 1 = 0.376853 loss)
I0606 00:17:05.166502 54715 sgd_solver.cpp:106] Iteration 1419, lr = 0.00977231
I0606 00:17:05.275844 54715 solver.cpp:341] Iteration 1420, Testing net (#0)
I0606 00:17:06.558786 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.843164
I0606 00:17:06.558832 54715 solver.cpp:409] Test net output #1: class_Acc = 0.942832
I0606 00:17:06.558840 54715 solver.cpp:409] Test net output #2: class_Acc = 0.628446
I0606 00:17:06.558850 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.348612 (* 1 = 0.348612 loss)
I0606 00:17:15.823312 54715 solver.cpp:237] Iteration 1422, loss = 0.345344
I0606 00:17:15.823360 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.362539 (* 1 = 0.362539 loss)
I0606 00:17:15.823372 54715 sgd_solver.cpp:106] Iteration 1422, lr = 0.00977182
I0606 00:17:25.196007 54715 solver.cpp:237] Iteration 1425, loss = 0.345656
I0606 00:17:25.196058 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.296401 (* 1 = 0.296401 loss)
I0606 00:17:25.196069 54715 sgd_solver.cpp:106] Iteration 1425, lr = 0.00977134
I0606 00:17:34.569710 54715 solver.cpp:237] Iteration 1428, loss = 0.348418
I0606 00:17:34.569763 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347289 (* 1 = 0.347289 loss)
I0606 00:17:34.569775 54715 sgd_solver.cpp:106] Iteration 1428, lr = 0.00977086
I0606 00:17:37.802876 54715 solver.cpp:341] Iteration 1430, Testing net (#0)
I0606 00:17:39.085821 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.836335
I0606 00:17:39.085870 54715 solver.cpp:409] Test net output #1: class_Acc = 0.934165
I0606 00:17:39.085877 54715 solver.cpp:409] Test net output #2: class_Acc = 0.586055
I0606 00:17:39.085887 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.357677 (* 1 = 0.357677 loss)
I0606 00:17:45.228652 54715 solver.cpp:237] Iteration 1431, loss = 0.348093
I0606 00:17:45.228701 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.363324 (* 1 = 0.363324 loss)
I0606 00:17:45.228713 54715 sgd_solver.cpp:106] Iteration 1431, lr = 0.00977038
I0606 00:17:54.602524 54715 solver.cpp:237] Iteration 1434, loss = 0.346604
I0606 00:17:54.602568 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.331818 (* 1 = 0.331818 loss)
I0606 00:17:54.602579 54715 sgd_solver.cpp:106] Iteration 1434, lr = 0.00976989
I0606 00:18:03.975435 54715 solver.cpp:237] Iteration 1437, loss = 0.34841
I0606 00:18:03.975484 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351758 (* 1 = 0.351758 loss)
I0606 00:18:03.975495 54715 sgd_solver.cpp:106] Iteration 1437, lr = 0.00976941
I0606 00:18:10.335104 54715 solver.cpp:341] Iteration 1440, Testing net (#0)
I0606 00:18:11.618074 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.813105
I0606 00:18:11.618119 54715 solver.cpp:409] Test net output #1: class_Acc = 0.945365
I0606 00:18:11.618125 54715 solver.cpp:409] Test net output #2: class_Acc = 0.529902
I0606 00:18:11.618136 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.406153 (* 1 = 0.406153 loss)
I0606 00:18:14.633123 54715 solver.cpp:237] Iteration 1440, loss = 0.348136
I0606 00:18:14.633170 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337637 (* 1 = 0.337637 loss)
I0606 00:18:14.633180 54715 sgd_solver.cpp:106] Iteration 1440, lr = 0.00976893
I0606 00:18:24.006873 54715 solver.cpp:237] Iteration 1443, loss = 0.347086
I0606 00:18:24.006924 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.308099 (* 1 = 0.308099 loss)
I0606 00:18:24.006935 54715 sgd_solver.cpp:106] Iteration 1443, lr = 0.00976845
I0606 00:18:33.375792 54715 solver.cpp:237] Iteration 1446, loss = 0.344402
I0606 00:18:33.375844 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.410031 (* 1 = 0.410031 loss)
I0606 00:18:33.375855 54715 sgd_solver.cpp:106] Iteration 1446, lr = 0.00976796
I0606 00:18:42.749831 54715 solver.cpp:237] Iteration 1449, loss = 0.34299
I0606 00:18:42.749883 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347887 (* 1 = 0.347887 loss)
I0606 00:18:42.749894 54715 sgd_solver.cpp:106] Iteration 1449, lr = 0.00976748
I0606 00:18:42.859338 54715 solver.cpp:341] Iteration 1450, Testing net (#0)
I0606 00:18:44.141525 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.821331
I0606 00:18:44.141571 54715 solver.cpp:409] Test net output #1: class_Acc = 0.90387
I0606 00:18:44.141577 54715 solver.cpp:409] Test net output #2: class_Acc = 0.640579
I0606 00:18:44.141587 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.399147 (* 1 = 0.399147 loss)
I0606 00:18:53.402809 54715 solver.cpp:237] Iteration 1452, loss = 0.344896
I0606 00:18:53.402859 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340792 (* 1 = 0.340792 loss)
I0606 00:18:53.402870 54715 sgd_solver.cpp:106] Iteration 1452, lr = 0.009767
I0606 00:19:02.775584 54715 solver.cpp:237] Iteration 1455, loss = 0.341953
I0606 00:19:02.775635 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.293717 (* 1 = 0.293717 loss)
I0606 00:19:02.775647 54715 sgd_solver.cpp:106] Iteration 1455, lr = 0.00976651
I0606 00:19:12.148264 54715 solver.cpp:237] Iteration 1458, loss = 0.34353
I0606 00:19:12.148314 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.386801 (* 1 = 0.386801 loss)
I0606 00:19:12.148324 54715 sgd_solver.cpp:106] Iteration 1458, lr = 0.00976603
I0606 00:19:15.382784 54715 solver.cpp:341] Iteration 1460, Testing net (#0)
I0606 00:19:16.665535 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.83386
I0606 00:19:16.665582 54715 solver.cpp:409] Test net output #1: class_Acc = 0.933443
I0606 00:19:16.665590 54715 solver.cpp:409] Test net output #2: class_Acc = 0.623969
I0606 00:19:16.665598 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.364804 (* 1 = 0.364804 loss)
I0606 00:19:22.802556 54715 solver.cpp:237] Iteration 1461, loss = 0.345151
I0606 00:19:22.802608 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.332297 (* 1 = 0.332297 loss)
I0606 00:19:22.802618 54715 sgd_solver.cpp:106] Iteration 1461, lr = 0.00976555
I0606 00:19:32.173007 54715 solver.cpp:237] Iteration 1464, loss = 0.345863
I0606 00:19:32.173058 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367092 (* 1 = 0.367092 loss)
I0606 00:19:32.173069 54715 sgd_solver.cpp:106] Iteration 1464, lr = 0.00976507
I0606 00:19:41.547632 54715 solver.cpp:237] Iteration 1467, loss = 0.343552
I0606 00:19:41.547683 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286945 (* 1 = 0.286945 loss)
I0606 00:19:41.547694 54715 sgd_solver.cpp:106] Iteration 1467, lr = 0.00976458
I0606 00:19:47.905983 54715 solver.cpp:341] Iteration 1470, Testing net (#0)
I0606 00:19:49.191663 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.830965
I0606 00:19:49.191694 54715 solver.cpp:409] Test net output #1: class_Acc = 0.882523
I0606 00:19:49.191702 54715 solver.cpp:409] Test net output #2: class_Acc = 0.69567
I0606 00:19:49.191712 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.37704 (* 1 = 0.37704 loss)
I0606 00:19:52.204354 54715 solver.cpp:237] Iteration 1470, loss = 0.340043
I0606 00:19:52.204401 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327761 (* 1 = 0.327761 loss)
I0606 00:19:52.204411 54715 sgd_solver.cpp:106] Iteration 1470, lr = 0.0097641
I0606 00:19:55.541867 54715 softmax_loss_layer.cu:194] weight loss 0 =0.352644 weight loss 1 =1 weight loss 2 =0
I0606 00:20:01.577059 54715 solver.cpp:237] Iteration 1473, loss = 0.339499
I0606 00:20:01.577112 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.329332 (* 1 = 0.329332 loss)
I0606 00:20:01.577123 54715 sgd_solver.cpp:106] Iteration 1473, lr = 0.00976362
I0606 00:20:10.949846 54715 solver.cpp:237] Iteration 1476, loss = 0.340323
I0606 00:20:10.949896 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.329912 (* 1 = 0.329912 loss)
I0606 00:20:10.949908 54715 sgd_solver.cpp:106] Iteration 1476, lr = 0.00976313
I0606 00:20:20.323638 54715 solver.cpp:237] Iteration 1479, loss = 0.338564
I0606 00:20:20.323706 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311935 (* 1 = 0.311935 loss)
I0606 00:20:20.323717 54715 sgd_solver.cpp:106] Iteration 1479, lr = 0.00976265
I0606 00:20:20.433089 54715 solver.cpp:341] Iteration 1480, Testing net (#0)
I0606 00:20:21.715811 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.734254
I0606 00:20:21.715853 54715 solver.cpp:409] Test net output #1: class_Acc = 0.75127
I0606 00:20:21.715860 54715 solver.cpp:409] Test net output #2: class_Acc = 0.687521
I0606 00:20:21.715869 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.533839 (* 1 = 0.533839 loss)
I0606 00:20:30.977128 54715 solver.cpp:237] Iteration 1482, loss = 0.338094
I0606 00:20:30.977177 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.319071 (* 1 = 0.319071 loss)
I0606 00:20:30.977187 54715 sgd_solver.cpp:106] Iteration 1482, lr = 0.00976217
I0606 00:20:40.351451 54715 solver.cpp:237] Iteration 1485, loss = 0.338837
I0606 00:20:40.351506 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366341 (* 1 = 0.366341 loss)
I0606 00:20:40.351517 54715 sgd_solver.cpp:106] Iteration 1485, lr = 0.00976169
I0606 00:20:49.731643 54715 solver.cpp:237] Iteration 1488, loss = 0.339796
I0606 00:20:49.731693 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.291332 (* 1 = 0.291332 loss)
I0606 00:20:49.731704 54715 sgd_solver.cpp:106] Iteration 1488, lr = 0.0097612
I0606 00:20:52.965045 54715 solver.cpp:341] Iteration 1490, Testing net (#0)
I0606 00:20:54.248996 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.813947
I0606 00:20:54.249039 54715 solver.cpp:409] Test net output #1: class_Acc = 0.865003
I0606 00:20:54.249047 54715 solver.cpp:409] Test net output #2: class_Acc = 0.697747
I0606 00:20:54.249058 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.412543 (* 1 = 0.412543 loss)
I0606 00:20:54.350610 54715 softmax_loss_layer.cu:194] weight loss 0 =0.264104 weight loss 1 =1 weight loss 2 =0
I0606 00:21:00.385905 54715 solver.cpp:237] Iteration 1491, loss = 0.340128
I0606 00:21:00.385951 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35248 (* 1 = 0.35248 loss)
I0606 00:21:00.385962 54715 sgd_solver.cpp:106] Iteration 1491, lr = 0.00976072
I0606 00:21:09.761593 54715 solver.cpp:237] Iteration 1494, loss = 0.339654
I0606 00:21:09.761639 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359638 (* 1 = 0.359638 loss)
I0606 00:21:09.761651 54715 sgd_solver.cpp:106] Iteration 1494, lr = 0.00976024
I0606 00:21:19.137948 54715 solver.cpp:237] Iteration 1497, loss = 0.340134
I0606 00:21:19.138000 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345196 (* 1 = 0.345196 loss)
I0606 00:21:19.138011 54715 sgd_solver.cpp:106] Iteration 1497, lr = 0.00975975
I0606 00:21:25.496229 54715 solver.cpp:341] Iteration 1500, Testing net (#0)
I0606 00:21:26.778349 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.817433
I0606 00:21:26.778394 54715 solver.cpp:409] Test net output #1: class_Acc = 0.931296
I0606 00:21:26.778401 54715 solver.cpp:409] Test net output #2: class_Acc = 0.562779
I0606 00:21:26.778411 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.396058 (* 1 = 0.396058 loss)
I0606 00:21:29.793273 54715 solver.cpp:237] Iteration 1500, loss = 0.340447
I0606 00:21:29.793325 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.328671 (* 1 = 0.328671 loss)
I0606 00:21:29.793336 54715 sgd_solver.cpp:106] Iteration 1500, lr = 0.00975927
I0606 00:21:39.170420 54715 solver.cpp:237] Iteration 1503, loss = 0.342749
I0606 00:21:39.170471 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340107 (* 1 = 0.340107 loss)
I0606 00:21:39.170481 54715 sgd_solver.cpp:106] Iteration 1503, lr = 0.00975879
I0606 00:21:48.543668 54715 solver.cpp:237] Iteration 1506, loss = 0.342612
I0606 00:21:48.543717 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.352101 (* 1 = 0.352101 loss)
I0606 00:21:48.543728 54715 sgd_solver.cpp:106] Iteration 1506, lr = 0.0097583
I0606 00:21:57.920647 54715 solver.cpp:237] Iteration 1509, loss = 0.344271
I0606 00:21:57.920742 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31303 (* 1 = 0.31303 loss)
I0606 00:21:57.920755 54715 sgd_solver.cpp:106] Iteration 1509, lr = 0.00975782
I0606 00:21:58.030278 54715 solver.cpp:341] Iteration 1510, Testing net (#0)
I0606 00:21:59.314321 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.825072
I0606 00:21:59.314369 54715 solver.cpp:409] Test net output #1: class_Acc = 0.88574
I0606 00:21:59.314376 54715 solver.cpp:409] Test net output #2: class_Acc = 0.680431
I0606 00:21:59.314386 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.389661 (* 1 = 0.389661 loss)
I0606 00:22:08.577081 54715 solver.cpp:237] Iteration 1512, loss = 0.340143
I0606 00:22:08.577131 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.329506 (* 1 = 0.329506 loss)
I0606 00:22:08.577142 54715 sgd_solver.cpp:106] Iteration 1512, lr = 0.00975734
I0606 00:22:17.953577 54715 solver.cpp:237] Iteration 1515, loss = 0.339033
I0606 00:22:17.953627 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361247 (* 1 = 0.361247 loss)
I0606 00:22:17.953639 54715 sgd_solver.cpp:106] Iteration 1515, lr = 0.00975686
I0606 00:22:27.331851 54715 solver.cpp:237] Iteration 1518, loss = 0.338091
I0606 00:22:27.331902 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.331619 (* 1 = 0.331619 loss)
I0606 00:22:27.331913 54715 sgd_solver.cpp:106] Iteration 1518, lr = 0.00975637
I0606 00:22:30.566503 54715 solver.cpp:341] Iteration 1520, Testing net (#0)
I0606 00:22:31.849584 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.840385
I0606 00:22:31.849627 54715 solver.cpp:409] Test net output #1: class_Acc = 0.882702
I0606 00:22:31.849634 54715 solver.cpp:409] Test net output #2: class_Acc = 0.731262
I0606 00:22:31.849644 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.356578 (* 1 = 0.356578 loss)
I0606 00:22:37.991580 54715 solver.cpp:237] Iteration 1521, loss = 0.337531
I0606 00:22:37.991627 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361329 (* 1 = 0.361329 loss)
I0606 00:22:37.991638 54715 sgd_solver.cpp:106] Iteration 1521, lr = 0.00975589
I0606 00:22:47.366148 54715 solver.cpp:237] Iteration 1524, loss = 0.337919
I0606 00:22:47.366202 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.324496 (* 1 = 0.324496 loss)
I0606 00:22:47.366214 54715 sgd_solver.cpp:106] Iteration 1524, lr = 0.00975541
I0606 00:22:56.745462 54715 solver.cpp:237] Iteration 1527, loss = 0.336635
I0606 00:22:56.745512 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350936 (* 1 = 0.350936 loss)
I0606 00:22:56.745522 54715 sgd_solver.cpp:106] Iteration 1527, lr = 0.00975492
I0606 00:23:03.106835 54715 solver.cpp:341] Iteration 1530, Testing net (#0)
I0606 00:23:04.391019 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.847642
I0606 00:23:04.391067 54715 solver.cpp:409] Test net output #1: class_Acc = 0.913795
I0606 00:23:04.391074 54715 solver.cpp:409] Test net output #2: class_Acc = 0.68823
I0606 00:23:04.391084 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.343924 (* 1 = 0.343924 loss)
I0606 00:23:07.404215 54715 solver.cpp:237] Iteration 1530, loss = 0.337642
I0606 00:23:07.404264 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.314377 (* 1 = 0.314377 loss)
I0606 00:23:07.404275 54715 sgd_solver.cpp:106] Iteration 1530, lr = 0.00975444
I0606 00:23:16.780073 54715 solver.cpp:237] Iteration 1533, loss = 0.336486
I0606 00:23:16.780120 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.396392 (* 1 = 0.396392 loss)
I0606 00:23:16.780143 54715 sgd_solver.cpp:106] Iteration 1533, lr = 0.00975396
I0606 00:23:26.154983 54715 solver.cpp:237] Iteration 1536, loss = 0.335366
I0606 00:23:26.155033 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.329263 (* 1 = 0.329263 loss)
I0606 00:23:26.155045 54715 sgd_solver.cpp:106] Iteration 1536, lr = 0.00975347
I0606 00:23:35.533010 54715 solver.cpp:237] Iteration 1539, loss = 0.334847
I0606 00:23:35.533079 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.358031 (* 1 = 0.358031 loss)
I0606 00:23:35.533092 54715 sgd_solver.cpp:106] Iteration 1539, lr = 0.00975299
I0606 00:23:35.642432 54715 solver.cpp:341] Iteration 1540, Testing net (#0)
I0606 00:23:36.925065 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.841906
I0606 00:23:36.925104 54715 solver.cpp:409] Test net output #1: class_Acc = 0.919783
I0606 00:23:36.925112 54715 solver.cpp:409] Test net output #2: class_Acc = 0.655153
I0606 00:23:36.925122 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.351869 (* 1 = 0.351869 loss)
I0606 00:23:46.187379 54715 solver.cpp:237] Iteration 1542, loss = 0.33728
I0606 00:23:46.187430 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.406424 (* 1 = 0.406424 loss)
I0606 00:23:46.187443 54715 sgd_solver.cpp:106] Iteration 1542, lr = 0.00975251
I0606 00:23:55.561483 54715 solver.cpp:237] Iteration 1545, loss = 0.336251
I0606 00:23:55.561534 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.284428 (* 1 = 0.284428 loss)
I0606 00:23:55.561545 54715 sgd_solver.cpp:106] Iteration 1545, lr = 0.00975203
I0606 00:24:04.936262 54715 solver.cpp:237] Iteration 1548, loss = 0.338744
I0606 00:24:04.936313 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.328154 (* 1 = 0.328154 loss)
I0606 00:24:04.936324 54715 sgd_solver.cpp:106] Iteration 1548, lr = 0.00975154
I0606 00:24:06.703934 54715 softmax_loss_layer.cu:194] weight loss 0 =0.238264 weight loss 1 =1 weight loss 2 =0
I0606 00:24:08.170819 54715 solver.cpp:341] Iteration 1550, Testing net (#0)
I0606 00:24:09.454946 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.839107
I0606 00:24:09.454993 54715 solver.cpp:409] Test net output #1: class_Acc = 0.903638
I0606 00:24:09.455011 54715 solver.cpp:409] Test net output #2: class_Acc = 0.688156
I0606 00:24:09.455022 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.359355 (* 1 = 0.359355 loss)
I0606 00:24:15.590242 54715 solver.cpp:237] Iteration 1551, loss = 0.34113
I0606 00:24:15.590292 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292071 (* 1 = 0.292071 loss)
I0606 00:24:15.590303 54715 sgd_solver.cpp:106] Iteration 1551, lr = 0.00975106
I0606 00:24:17.747056 54715 softmax_loss_layer.cu:194] weight loss 0 =0.273793 weight loss 1 =1 weight loss 2 =0
I0606 00:24:24.960182 54715 solver.cpp:237] Iteration 1554, loss = 0.343114
I0606 00:24:24.960229 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376858 (* 1 = 0.376858 loss)
I0606 00:24:24.960239 54715 sgd_solver.cpp:106] Iteration 1554, lr = 0.00975058
I0606 00:24:34.334978 54715 solver.cpp:237] Iteration 1557, loss = 0.339133
I0606 00:24:34.335028 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.410914 (* 1 = 0.410914 loss)
I0606 00:24:34.335039 54715 sgd_solver.cpp:106] Iteration 1557, lr = 0.00975009
I0606 00:24:40.696357 54715 solver.cpp:341] Iteration 1560, Testing net (#0)
I0606 00:24:41.978641 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.8258
I0606 00:24:41.978688 54715 solver.cpp:409] Test net output #1: class_Acc = 0.958973
I0606 00:24:41.978694 54715 solver.cpp:409] Test net output #2: class_Acc = 0.530793
I0606 00:24:41.978704 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.376009 (* 1 = 0.376009 loss)
I0606 00:24:44.993682 54715 solver.cpp:237] Iteration 1560, loss = 0.341281
I0606 00:24:44.993732 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.346516 (* 1 = 0.346516 loss)
I0606 00:24:44.993743 54715 sgd_solver.cpp:106] Iteration 1560, lr = 0.00974961
I0606 00:24:54.366436 54715 solver.cpp:237] Iteration 1563, loss = 0.34191
I0606 00:24:54.366487 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.379529 (* 1 = 0.379529 loss)
I0606 00:24:54.366498 54715 sgd_solver.cpp:106] Iteration 1563, lr = 0.00974913
I0606 00:25:03.737423 54715 solver.cpp:237] Iteration 1566, loss = 0.340329
I0606 00:25:03.737471 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337228 (* 1 = 0.337228 loss)
I0606 00:25:03.737483 54715 sgd_solver.cpp:106] Iteration 1566, lr = 0.00974865
I0606 00:25:13.111073 54715 solver.cpp:237] Iteration 1569, loss = 0.339454
I0606 00:25:13.111191 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340813 (* 1 = 0.340813 loss)
I0606 00:25:13.111204 54715 sgd_solver.cpp:106] Iteration 1569, lr = 0.00974816
I0606 00:25:13.220506 54715 solver.cpp:341] Iteration 1570, Testing net (#0)
I0606 00:25:14.502188 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.817656
I0606 00:25:14.502233 54715 solver.cpp:409] Test net output #1: class_Acc = 0.939698
I0606 00:25:14.502239 54715 solver.cpp:409] Test net output #2: class_Acc = 0.543371
I0606 00:25:14.502250 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.406957 (* 1 = 0.406957 loss)
I0606 00:25:23.762459 54715 solver.cpp:237] Iteration 1572, loss = 0.341472
I0606 00:25:23.762508 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.300106 (* 1 = 0.300106 loss)
I0606 00:25:23.762519 54715 sgd_solver.cpp:106] Iteration 1572, lr = 0.00974768
I0606 00:25:33.135952 54715 solver.cpp:237] Iteration 1575, loss = 0.341585
I0606 00:25:33.136000 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345126 (* 1 = 0.345126 loss)
I0606 00:25:33.136011 54715 sgd_solver.cpp:106] Iteration 1575, lr = 0.0097472
I0606 00:25:42.511528 54715 solver.cpp:237] Iteration 1578, loss = 0.339121
I0606 00:25:42.511579 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.270002 (* 1 = 0.270002 loss)
I0606 00:25:42.511590 54715 sgd_solver.cpp:106] Iteration 1578, lr = 0.00974671
I0606 00:25:45.749394 54715 solver.cpp:341] Iteration 1580, Testing net (#0)
I0606 00:25:47.031919 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.843672
I0606 00:25:47.031963 54715 solver.cpp:409] Test net output #1: class_Acc = 0.910899
I0606 00:25:47.031970 54715 solver.cpp:409] Test net output #2: class_Acc = 0.696979
I0606 00:25:47.031978 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.352105 (* 1 = 0.352105 loss)
I0606 00:25:53.171623 54715 solver.cpp:237] Iteration 1581, loss = 0.339823
I0606 00:25:53.171675 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.408778 (* 1 = 0.408778 loss)
I0606 00:25:53.171686 54715 sgd_solver.cpp:106] Iteration 1581, lr = 0.00974623
I0606 00:26:02.544102 54715 solver.cpp:237] Iteration 1584, loss = 0.335947
I0606 00:26:02.544173 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.316483 (* 1 = 0.316483 loss)
I0606 00:26:02.544186 54715 sgd_solver.cpp:106] Iteration 1584, lr = 0.00974575
I0606 00:26:11.914186 54715 solver.cpp:237] Iteration 1587, loss = 0.334729
I0606 00:26:11.914235 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.281085 (* 1 = 0.281085 loss)
I0606 00:26:11.914247 54715 sgd_solver.cpp:106] Iteration 1587, lr = 0.00974526
I0606 00:26:18.275431 54715 solver.cpp:341] Iteration 1590, Testing net (#0)
I0606 00:26:19.557494 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.83516
I0606 00:26:19.557536 54715 solver.cpp:409] Test net output #1: class_Acc = 0.936115
I0606 00:26:19.557544 54715 solver.cpp:409] Test net output #2: class_Acc = 0.610836
I0606 00:26:19.557554 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.359787 (* 1 = 0.359787 loss)
I0606 00:26:22.571867 54715 solver.cpp:237] Iteration 1590, loss = 0.336121
I0606 00:26:22.571910 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.323946 (* 1 = 0.323946 loss)
I0606 00:26:22.571920 54715 sgd_solver.cpp:106] Iteration 1590, lr = 0.00974478
I0606 00:26:31.949515 54715 solver.cpp:237] Iteration 1593, loss = 0.334805
I0606 00:26:31.949568 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.324858 (* 1 = 0.324858 loss)
I0606 00:26:31.949579 54715 sgd_solver.cpp:106] Iteration 1593, lr = 0.0097443
I0606 00:26:41.324645 54715 solver.cpp:237] Iteration 1596, loss = 0.335042
I0606 00:26:41.324693 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.331946 (* 1 = 0.331946 loss)
I0606 00:26:41.324704 54715 sgd_solver.cpp:106] Iteration 1596, lr = 0.00974381
I0606 00:26:50.699451 54715 solver.cpp:237] Iteration 1599, loss = 0.338056
I0606 00:26:50.699563 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.369659 (* 1 = 0.369659 loss)
I0606 00:26:50.699578 54715 sgd_solver.cpp:106] Iteration 1599, lr = 0.00974333
I0606 00:26:50.808909 54715 solver.cpp:341] Iteration 1600, Testing net (#0)
I0606 00:26:52.093683 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.843769
I0606 00:26:52.093730 54715 solver.cpp:409] Test net output #1: class_Acc = 0.874542
I0606 00:26:52.093737 54715 solver.cpp:409] Test net output #2: class_Acc = 0.769634
I0606 00:26:52.093747 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.347926 (* 1 = 0.347926 loss)
I0606 00:27:01.354801 54715 solver.cpp:237] Iteration 1602, loss = 0.339417
I0606 00:27:01.354854 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.270354 (* 1 = 0.270354 loss)
I0606 00:27:01.354866 54715 sgd_solver.cpp:106] Iteration 1602, lr = 0.00974285
I0606 00:27:10.728766 54715 solver.cpp:237] Iteration 1605, loss = 0.339785
I0606 00:27:10.728818 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318486 (* 1 = 0.318486 loss)
I0606 00:27:10.728829 54715 sgd_solver.cpp:106] Iteration 1605, lr = 0.00974236
I0606 00:27:20.109926 54715 solver.cpp:237] Iteration 1608, loss = 0.341307
I0606 00:27:20.109979 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325566 (* 1 = 0.325566 loss)
I0606 00:27:20.109990 54715 sgd_solver.cpp:106] Iteration 1608, lr = 0.00974188
I0606 00:27:23.342811 54715 solver.cpp:341] Iteration 1610, Testing net (#0)
I0606 00:27:24.625418 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.826243
I0606 00:27:24.625463 54715 solver.cpp:409] Test net output #1: class_Acc = 0.92993
I0606 00:27:24.625469 54715 solver.cpp:409] Test net output #2: class_Acc = 0.579005
I0606 00:27:24.625479 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.375628 (* 1 = 0.375628 loss)
I0606 00:27:30.766878 54715 solver.cpp:237] Iteration 1611, loss = 0.339509
I0606 00:27:30.766932 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.306414 (* 1 = 0.306414 loss)
I0606 00:27:30.766942 54715 sgd_solver.cpp:106] Iteration 1611, lr = 0.0097414
I0606 00:27:40.140550 54715 solver.cpp:237] Iteration 1614, loss = 0.339352
I0606 00:27:40.140599 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321265 (* 1 = 0.321265 loss)
I0606 00:27:40.140609 54715 sgd_solver.cpp:106] Iteration 1614, lr = 0.00974092
I0606 00:27:41.130956 54715 softmax_loss_layer.cu:194] weight loss 0 =0.312905 weight loss 1 =1 weight loss 2 =0
I0606 00:27:49.518357 54715 solver.cpp:237] Iteration 1617, loss = 0.335855
I0606 00:27:49.518407 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.352099 (* 1 = 0.352099 loss)
I0606 00:27:49.518417 54715 sgd_solver.cpp:106] Iteration 1617, lr = 0.00974043
I0606 00:27:55.876505 54715 solver.cpp:341] Iteration 1620, Testing net (#0)
I0606 00:27:57.159541 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.845266
I0606 00:27:57.159584 54715 solver.cpp:409] Test net output #1: class_Acc = 0.930244
I0606 00:27:57.159591 54715 solver.cpp:409] Test net output #2: class_Acc = 0.635169
I0606 00:27:57.159601 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.344566 (* 1 = 0.344566 loss)
I0606 00:28:00.174937 54715 solver.cpp:237] Iteration 1620, loss = 0.337274
I0606 00:28:00.174988 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.324141 (* 1 = 0.324141 loss)
I0606 00:28:00.174999 54715 sgd_solver.cpp:106] Iteration 1620, lr = 0.00973995
I0606 00:28:09.550060 54715 solver.cpp:237] Iteration 1623, loss = 0.334386
I0606 00:28:09.550109 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.28613 (* 1 = 0.28613 loss)
I0606 00:28:09.550120 54715 sgd_solver.cpp:106] Iteration 1623, lr = 0.00973947
I0606 00:28:18.925637 54715 solver.cpp:237] Iteration 1626, loss = 0.332948
I0606 00:28:18.925683 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.320222 (* 1 = 0.320222 loss)
I0606 00:28:18.925694 54715 sgd_solver.cpp:106] Iteration 1626, lr = 0.00973898
I0606 00:28:22.262259 54715 softmax_loss_layer.cu:194] weight loss 0 =0.578313 weight loss 1 =1 weight loss 2 =0
I0606 00:28:28.301046 54715 solver.cpp:237] Iteration 1629, loss = 0.331621
I0606 00:28:28.301147 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337948 (* 1 = 0.337948 loss)
I0606 00:28:28.301160 54715 sgd_solver.cpp:106] Iteration 1629, lr = 0.0097385
I0606 00:28:28.410487 54715 solver.cpp:341] Iteration 1630, Testing net (#0)
I0606 00:28:29.692822 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.824184
I0606 00:28:29.692867 54715 solver.cpp:409] Test net output #1: class_Acc = 0.904198
I0606 00:28:29.692873 54715 solver.cpp:409] Test net output #2: class_Acc = 0.656112
I0606 00:28:29.692884 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.398093 (* 1 = 0.398093 loss)
I0606 00:28:38.957173 54715 solver.cpp:237] Iteration 1632, loss = 0.334055
I0606 00:28:38.957214 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292553 (* 1 = 0.292553 loss)
I0606 00:28:38.957226 54715 sgd_solver.cpp:106] Iteration 1632, lr = 0.00973802
I0606 00:28:48.333012 54715 solver.cpp:237] Iteration 1635, loss = 0.335947
I0606 00:28:48.333060 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.365381 (* 1 = 0.365381 loss)
I0606 00:28:48.333071 54715 sgd_solver.cpp:106] Iteration 1635, lr = 0.00973753
I0606 00:28:57.707610 54715 solver.cpp:237] Iteration 1638, loss = 0.335531
I0606 00:28:57.707666 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.293994 (* 1 = 0.293994 loss)
I0606 00:28:57.707677 54715 sgd_solver.cpp:106] Iteration 1638, lr = 0.00973705
I0606 00:29:00.941967 54715 solver.cpp:341] Iteration 1640, Testing net (#0)
I0606 00:29:02.224784 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.838626
I0606 00:29:02.224828 54715 solver.cpp:409] Test net output #1: class_Acc = 0.887012
I0606 00:29:02.224834 54715 solver.cpp:409] Test net output #2: class_Acc = 0.712282
I0606 00:29:02.224844 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.360924 (* 1 = 0.360924 loss)
I0606 00:29:08.365780 54715 solver.cpp:237] Iteration 1641, loss = 0.33482
I0606 00:29:08.365828 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.27642 (* 1 = 0.27642 loss)
I0606 00:29:08.365839 54715 sgd_solver.cpp:106] Iteration 1641, lr = 0.00973657
I0606 00:29:17.738865 54715 solver.cpp:237] Iteration 1644, loss = 0.337293
I0606 00:29:17.738914 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.355223 (* 1 = 0.355223 loss)
I0606 00:29:17.738926 54715 sgd_solver.cpp:106] Iteration 1644, lr = 0.00973608
I0606 00:29:27.112152 54715 solver.cpp:237] Iteration 1647, loss = 0.338361
I0606 00:29:27.112200 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.374262 (* 1 = 0.374262 loss)
I0606 00:29:27.112211 54715 sgd_solver.cpp:106] Iteration 1647, lr = 0.0097356
I0606 00:29:33.471469 54715 solver.cpp:341] Iteration 1650, Testing net (#0)
I0606 00:29:34.754696 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.851004
I0606 00:29:34.754743 54715 solver.cpp:409] Test net output #1: class_Acc = 0.912121
I0606 00:29:34.754750 54715 solver.cpp:409] Test net output #2: class_Acc = 0.686272
I0606 00:29:34.754760 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.333834 (* 1 = 0.333834 loss)
I0606 00:29:37.770256 54715 solver.cpp:237] Iteration 1650, loss = 0.335643
I0606 00:29:37.770303 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.416244 (* 1 = 0.416244 loss)
I0606 00:29:37.770313 54715 sgd_solver.cpp:106] Iteration 1650, lr = 0.00973512
I0606 00:29:47.143209 54715 solver.cpp:237] Iteration 1653, loss = 0.334758
I0606 00:29:47.143261 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367396 (* 1 = 0.367396 loss)
I0606 00:29:47.143271 54715 sgd_solver.cpp:106] Iteration 1653, lr = 0.00973463
I0606 00:29:56.520812 54715 solver.cpp:237] Iteration 1656, loss = 0.337214
I0606 00:29:56.520861 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326172 (* 1 = 0.326172 loss)
I0606 00:29:56.520872 54715 sgd_solver.cpp:106] Iteration 1656, lr = 0.00973415
I0606 00:30:05.893401 54715 solver.cpp:237] Iteration 1659, loss = 0.340401
I0606 00:30:05.893497 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321714 (* 1 = 0.321714 loss)
I0606 00:30:05.893510 54715 sgd_solver.cpp:106] Iteration 1659, lr = 0.00973367
I0606 00:30:06.002828 54715 solver.cpp:341] Iteration 1660, Testing net (#0)
I0606 00:30:07.285181 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848644
I0606 00:30:07.285225 54715 solver.cpp:409] Test net output #1: class_Acc = 0.903469
I0606 00:30:07.285233 54715 solver.cpp:409] Test net output #2: class_Acc = 0.705724
I0606 00:30:07.285243 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.339978 (* 1 = 0.339978 loss)
I0606 00:30:11.681447 54715 softmax_loss_layer.cu:194] weight loss 0 =0.219646 weight loss 1 =1 weight loss 2 =0
I0606 00:30:16.550760 54715 solver.cpp:237] Iteration 1662, loss = 0.337005
I0606 00:30:16.550789 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.370832 (* 1 = 0.370832 loss)
I0606 00:30:16.550799 54715 sgd_solver.cpp:106] Iteration 1662, lr = 0.00973318
I0606 00:30:25.929350 54715 solver.cpp:237] Iteration 1665, loss = 0.33699
I0606 00:30:25.929406 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.287027 (* 1 = 0.287027 loss)
I0606 00:30:25.929428 54715 sgd_solver.cpp:106] Iteration 1665, lr = 0.0097327
I0606 00:30:35.304774 54715 solver.cpp:237] Iteration 1668, loss = 0.334852
I0606 00:30:35.304821 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334982 (* 1 = 0.334982 loss)
I0606 00:30:35.304831 54715 sgd_solver.cpp:106] Iteration 1668, lr = 0.00973222
I0606 00:30:38.540886 54715 solver.cpp:341] Iteration 1670, Testing net (#0)
I0606 00:30:39.823842 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.775989
I0606 00:30:39.823881 54715 solver.cpp:409] Test net output #1: class_Acc = 0.783355
I0606 00:30:39.823889 54715 solver.cpp:409] Test net output #2: class_Acc = 0.755896
I0606 00:30:39.823899 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.469977 (* 1 = 0.469977 loss)
I0606 00:30:45.964349 54715 solver.cpp:237] Iteration 1671, loss = 0.333958
I0606 00:30:45.964398 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368111 (* 1 = 0.368111 loss)
I0606 00:30:45.964408 54715 sgd_solver.cpp:106] Iteration 1671, lr = 0.00973173
I0606 00:30:55.338548 54715 solver.cpp:237] Iteration 1674, loss = 0.334342
I0606 00:30:55.338600 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345028 (* 1 = 0.345028 loss)
I0606 00:30:55.338611 54715 sgd_solver.cpp:106] Iteration 1674, lr = 0.00973125
I0606 00:31:04.714114 54715 solver.cpp:237] Iteration 1677, loss = 0.333575
I0606 00:31:04.714165 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.338256 (* 1 = 0.338256 loss)
I0606 00:31:04.714177 54715 sgd_solver.cpp:106] Iteration 1677, lr = 0.00973077
I0606 00:31:11.072680 54715 solver.cpp:341] Iteration 1680, Testing net (#0)
I0606 00:31:12.357405 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.847164
I0606 00:31:12.357451 54715 solver.cpp:409] Test net output #1: class_Acc = 0.912878
I0606 00:31:12.357457 54715 solver.cpp:409] Test net output #2: class_Acc = 0.695443
I0606 00:31:12.357467 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.348361 (* 1 = 0.348361 loss)
I0606 00:31:15.372517 54715 solver.cpp:237] Iteration 1680, loss = 0.334867
I0606 00:31:15.372565 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361702 (* 1 = 0.361702 loss)
I0606 00:31:15.372577 54715 sgd_solver.cpp:106] Iteration 1680, lr = 0.00973028
I0606 00:31:24.746048 54715 solver.cpp:237] Iteration 1683, loss = 0.337847
I0606 00:31:24.746098 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360672 (* 1 = 0.360672 loss)
I0606 00:31:24.746109 54715 sgd_solver.cpp:106] Iteration 1683, lr = 0.0097298
I0606 00:31:34.119113 54715 solver.cpp:237] Iteration 1686, loss = 0.340916
I0606 00:31:34.119163 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367119 (* 1 = 0.367119 loss)
I0606 00:31:34.119174 54715 sgd_solver.cpp:106] Iteration 1686, lr = 0.00972932
I0606 00:31:43.494383 54715 solver.cpp:237] Iteration 1689, loss = 0.338466
I0606 00:31:43.494493 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.30858 (* 1 = 0.30858 loss)
I0606 00:31:43.494505 54715 sgd_solver.cpp:106] Iteration 1689, lr = 0.00972883
I0606 00:31:43.603770 54715 solver.cpp:341] Iteration 1690, Testing net (#0)
I0606 00:31:44.886467 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.831576
I0606 00:31:44.886512 54715 solver.cpp:409] Test net output #1: class_Acc = 0.922186
I0606 00:31:44.886518 54715 solver.cpp:409] Test net output #2: class_Acc = 0.611575
I0606 00:31:44.886528 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.366837 (* 1 = 0.366837 loss)
I0606 00:31:54.149116 54715 solver.cpp:237] Iteration 1692, loss = 0.341937
I0606 00:31:54.149166 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.36012 (* 1 = 0.36012 loss)
I0606 00:31:54.149178 54715 sgd_solver.cpp:106] Iteration 1692, lr = 0.00972835
I0606 00:32:03.522104 54715 solver.cpp:237] Iteration 1695, loss = 0.339342
I0606 00:32:03.522155 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.333021 (* 1 = 0.333021 loss)
I0606 00:32:03.522174 54715 sgd_solver.cpp:106] Iteration 1695, lr = 0.00972787
I0606 00:32:12.898212 54715 solver.cpp:237] Iteration 1698, loss = 0.338871
I0606 00:32:12.898262 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.299125 (* 1 = 0.299125 loss)
I0606 00:32:12.898272 54715 sgd_solver.cpp:106] Iteration 1698, lr = 0.00972738
I0606 00:32:16.131295 54715 solver.cpp:341] Iteration 1700, Testing net (#0)
I0606 00:32:17.414564 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.831627
I0606 00:32:17.414613 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893945
I0606 00:32:17.414619 54715 solver.cpp:409] Test net output #2: class_Acc = 0.68592
I0606 00:32:17.414628 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.375448 (* 1 = 0.375448 loss)
I0606 00:32:23.555966 54715 solver.cpp:237] Iteration 1701, loss = 0.339343
I0606 00:32:23.556016 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.323235 (* 1 = 0.323235 loss)
I0606 00:32:23.556027 54715 sgd_solver.cpp:106] Iteration 1701, lr = 0.0097269
I0606 00:32:32.928422 54715 solver.cpp:237] Iteration 1704, loss = 0.337366
I0606 00:32:32.928472 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.411085 (* 1 = 0.411085 loss)
I0606 00:32:32.928483 54715 sgd_solver.cpp:106] Iteration 1704, lr = 0.00972642
I0606 00:32:38.210006 54715 softmax_loss_layer.cu:194] weight loss 0 =0.329701 weight loss 1 =1 weight loss 2 =0
I0606 00:32:42.304770 54715 solver.cpp:237] Iteration 1707, loss = 0.335245
I0606 00:32:42.304821 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321886 (* 1 = 0.321886 loss)
I0606 00:32:42.304831 54715 sgd_solver.cpp:106] Iteration 1707, lr = 0.00972593
I0606 00:32:48.665855 54715 solver.cpp:341] Iteration 1710, Testing net (#0)
I0606 00:32:49.948493 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848624
I0606 00:32:49.948536 54715 solver.cpp:409] Test net output #1: class_Acc = 0.930662
I0606 00:32:49.948544 54715 solver.cpp:409] Test net output #2: class_Acc = 0.673356
I0606 00:32:49.948554 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.340255 (* 1 = 0.340255 loss)
I0606 00:32:52.964987 54715 solver.cpp:237] Iteration 1710, loss = 0.334136
I0606 00:32:52.965039 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.354873 (* 1 = 0.354873 loss)
I0606 00:32:52.965049 54715 sgd_solver.cpp:106] Iteration 1710, lr = 0.00972545
I0606 00:33:02.340636 54715 solver.cpp:237] Iteration 1713, loss = 0.330765
I0606 00:33:02.340689 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.287825 (* 1 = 0.287825 loss)
I0606 00:33:02.340700 54715 sgd_solver.cpp:106] Iteration 1713, lr = 0.00972497
I0606 00:33:11.718890 54715 solver.cpp:237] Iteration 1716, loss = 0.331612
I0606 00:33:11.718937 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327654 (* 1 = 0.327654 loss)
I0606 00:33:11.718948 54715 sgd_solver.cpp:106] Iteration 1716, lr = 0.00972448
I0606 00:33:21.094005 54715 solver.cpp:237] Iteration 1719, loss = 0.330282
I0606 00:33:21.094116 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.315976 (* 1 = 0.315976 loss)
I0606 00:33:21.094130 54715 sgd_solver.cpp:106] Iteration 1719, lr = 0.009724
I0606 00:33:21.203433 54715 solver.cpp:341] Iteration 1720, Testing net (#0)
I0606 00:33:22.486493 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.833765
I0606 00:33:22.486538 54715 solver.cpp:409] Test net output #1: class_Acc = 0.908169
I0606 00:33:22.486546 54715 solver.cpp:409] Test net output #2: class_Acc = 0.660176
I0606 00:33:22.486555 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.363313 (* 1 = 0.363313 loss)
I0606 00:33:31.750130 54715 solver.cpp:237] Iteration 1722, loss = 0.330709
I0606 00:33:31.750183 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326676 (* 1 = 0.326676 loss)
I0606 00:33:31.750195 54715 sgd_solver.cpp:106] Iteration 1722, lr = 0.00972352
I0606 00:33:41.128387 54715 solver.cpp:237] Iteration 1725, loss = 0.332444
I0606 00:33:41.128440 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376101 (* 1 = 0.376101 loss)
I0606 00:33:41.128451 54715 sgd_solver.cpp:106] Iteration 1725, lr = 0.00972303
I0606 00:33:50.504763 54715 solver.cpp:237] Iteration 1728, loss = 0.332789
I0606 00:33:50.504815 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326026 (* 1 = 0.326026 loss)
I0606 00:33:50.504827 54715 sgd_solver.cpp:106] Iteration 1728, lr = 0.00972255
I0606 00:33:53.737221 54715 solver.cpp:341] Iteration 1730, Testing net (#0)
I0606 00:33:55.018445 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.814579
I0606 00:33:55.018491 54715 solver.cpp:409] Test net output #1: class_Acc = 0.924355
I0606 00:33:55.018498 54715 solver.cpp:409] Test net output #2: class_Acc = 0.563929
I0606 00:33:55.018508 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.410072 (* 1 = 0.410072 loss)
I0606 00:34:01.156285 54715 solver.cpp:237] Iteration 1731, loss = 0.33295
I0606 00:34:01.156332 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.363423 (* 1 = 0.363423 loss)
I0606 00:34:01.156342 54715 sgd_solver.cpp:106] Iteration 1731, lr = 0.00972207
I0606 00:34:10.532963 54715 solver.cpp:237] Iteration 1734, loss = 0.333229
I0606 00:34:10.533013 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.364181 (* 1 = 0.364181 loss)
I0606 00:34:10.533025 54715 sgd_solver.cpp:106] Iteration 1734, lr = 0.00972158
I0606 00:34:19.906581 54715 solver.cpp:237] Iteration 1737, loss = 0.336708
I0606 00:34:19.906635 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.356707 (* 1 = 0.356707 loss)
I0606 00:34:19.906646 54715 sgd_solver.cpp:106] Iteration 1737, lr = 0.0097211
I0606 00:34:26.267119 54715 solver.cpp:341] Iteration 1740, Testing net (#0)
I0606 00:34:27.551002 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.782501
I0606 00:34:27.551046 54715 solver.cpp:409] Test net output #1: class_Acc = 0.784127
I0606 00:34:27.551054 54715 solver.cpp:409] Test net output #2: class_Acc = 0.776144
I0606 00:34:27.551064 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.462334 (* 1 = 0.462334 loss)
I0606 00:34:30.566139 54715 solver.cpp:237] Iteration 1740, loss = 0.334013
I0606 00:34:30.566188 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361916 (* 1 = 0.361916 loss)
I0606 00:34:30.566200 54715 sgd_solver.cpp:106] Iteration 1740, lr = 0.00972062
I0606 00:34:39.940120 54715 solver.cpp:237] Iteration 1743, loss = 0.335111
I0606 00:34:39.940182 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.37725 (* 1 = 0.37725 loss)
I0606 00:34:39.940194 54715 sgd_solver.cpp:106] Iteration 1743, lr = 0.00972013
I0606 00:34:49.310636 54715 solver.cpp:237] Iteration 1746, loss = 0.334787
I0606 00:34:49.310688 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.284526 (* 1 = 0.284526 loss)
I0606 00:34:49.310699 54715 sgd_solver.cpp:106] Iteration 1746, lr = 0.00971965
I0606 00:34:58.681864 54715 solver.cpp:237] Iteration 1749, loss = 0.335873
I0606 00:34:58.681922 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348392 (* 1 = 0.348392 loss)
I0606 00:34:58.681932 54715 sgd_solver.cpp:106] Iteration 1749, lr = 0.00971917
I0606 00:34:58.791287 54715 solver.cpp:341] Iteration 1750, Testing net (#0)
I0606 00:35:00.074079 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.837582
I0606 00:35:00.074126 54715 solver.cpp:409] Test net output #1: class_Acc = 0.904215
I0606 00:35:00.074132 54715 solver.cpp:409] Test net output #2: class_Acc = 0.676733
I0606 00:35:00.074142 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.361642 (* 1 = 0.361642 loss)
I0606 00:35:09.337751 54715 solver.cpp:237] Iteration 1752, loss = 0.334677
I0606 00:35:09.337800 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.319873 (* 1 = 0.319873 loss)
I0606 00:35:09.337810 54715 sgd_solver.cpp:106] Iteration 1752, lr = 0.00971868
I0606 00:35:18.710166 54715 solver.cpp:237] Iteration 1755, loss = 0.333445
I0606 00:35:18.710216 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.328064 (* 1 = 0.328064 loss)
I0606 00:35:18.710227 54715 sgd_solver.cpp:106] Iteration 1755, lr = 0.0097182
I0606 00:35:28.083252 54715 solver.cpp:237] Iteration 1758, loss = 0.33132
I0606 00:35:28.083299 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.332208 (* 1 = 0.332208 loss)
I0606 00:35:28.083310 54715 sgd_solver.cpp:106] Iteration 1758, lr = 0.00971772
I0606 00:35:31.317802 54715 solver.cpp:341] Iteration 1760, Testing net (#0)
I0606 00:35:32.601537 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.822084
I0606 00:35:32.601578 54715 solver.cpp:409] Test net output #1: class_Acc = 0.846064
I0606 00:35:32.601585 54715 solver.cpp:409] Test net output #2: class_Acc = 0.766964
I0606 00:35:32.601595 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.39516 (* 1 = 0.39516 loss)
I0606 00:35:38.741191 54715 solver.cpp:237] Iteration 1761, loss = 0.332182
I0606 00:35:38.741242 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.420152 (* 1 = 0.420152 loss)
I0606 00:35:38.741253 54715 sgd_solver.cpp:106] Iteration 1761, lr = 0.00971723
I0606 00:35:48.112414 54715 solver.cpp:237] Iteration 1764, loss = 0.328123
I0606 00:35:48.112465 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.313291 (* 1 = 0.313291 loss)
I0606 00:35:48.112475 54715 sgd_solver.cpp:106] Iteration 1764, lr = 0.00971675
I0606 00:35:57.488529 54715 solver.cpp:237] Iteration 1767, loss = 0.328967
I0606 00:35:57.488579 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311744 (* 1 = 0.311744 loss)
I0606 00:35:57.488589 54715 sgd_solver.cpp:106] Iteration 1767, lr = 0.00971627
I0606 00:36:03.846374 54715 solver.cpp:341] Iteration 1770, Testing net (#0)
I0606 00:36:05.131810 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848567
I0606 00:36:05.131855 54715 solver.cpp:409] Test net output #1: class_Acc = 0.923084
I0606 00:36:05.131862 54715 solver.cpp:409] Test net output #2: class_Acc = 0.687148
I0606 00:36:05.131871 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.338402 (* 1 = 0.338402 loss)
I0606 00:36:08.145611 54715 solver.cpp:237] Iteration 1770, loss = 0.326914
I0606 00:36:08.145663 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.271624 (* 1 = 0.271624 loss)
I0606 00:36:08.145680 54715 sgd_solver.cpp:106] Iteration 1770, lr = 0.00971578
I0606 00:36:17.519368 54715 solver.cpp:237] Iteration 1773, loss = 0.329514
I0606 00:36:17.519404 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.330473 (* 1 = 0.330473 loss)
I0606 00:36:17.519415 54715 sgd_solver.cpp:106] Iteration 1773, lr = 0.0097153
I0606 00:36:26.894964 54715 solver.cpp:237] Iteration 1776, loss = 0.326434
I0606 00:36:26.895014 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305715 (* 1 = 0.305715 loss)
I0606 00:36:26.895025 54715 sgd_solver.cpp:106] Iteration 1776, lr = 0.00971482
I0606 00:36:36.267763 54715 solver.cpp:237] Iteration 1779, loss = 0.325919
I0606 00:36:36.267822 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.316882 (* 1 = 0.316882 loss)
I0606 00:36:36.267833 54715 sgd_solver.cpp:106] Iteration 1779, lr = 0.00971433
I0606 00:36:36.377256 54715 solver.cpp:341] Iteration 1780, Testing net (#0)
I0606 00:36:37.661180 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.833474
I0606 00:36:37.661218 54715 solver.cpp:409] Test net output #1: class_Acc = 0.85016
I0606 00:36:37.661224 54715 solver.cpp:409] Test net output #2: class_Acc = 0.797272
I0606 00:36:37.661234 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.37397 (* 1 = 0.37397 loss)
I0606 00:36:46.924098 54715 solver.cpp:237] Iteration 1782, loss = 0.329074
I0606 00:36:46.924161 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.316964 (* 1 = 0.316964 loss)
I0606 00:36:46.924185 54715 sgd_solver.cpp:106] Iteration 1782, lr = 0.00971385
I0606 00:36:56.298492 54715 solver.cpp:237] Iteration 1785, loss = 0.327658
I0606 00:36:56.298543 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.279578 (* 1 = 0.279578 loss)
I0606 00:36:56.298553 54715 sgd_solver.cpp:106] Iteration 1785, lr = 0.00971336
I0606 00:37:05.677038 54715 solver.cpp:237] Iteration 1788, loss = 0.331761
I0606 00:37:05.677088 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.399029 (* 1 = 0.399029 loss)
I0606 00:37:05.677099 54715 sgd_solver.cpp:106] Iteration 1788, lr = 0.00971288
I0606 00:37:08.910507 54715 solver.cpp:341] Iteration 1790, Testing net (#0)
I0606 00:37:10.193589 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.847978
I0606 00:37:10.193634 54715 solver.cpp:409] Test net output #1: class_Acc = 0.910648
I0606 00:37:10.193641 54715 solver.cpp:409] Test net output #2: class_Acc = 0.700677
I0606 00:37:10.193651 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.340566 (* 1 = 0.340566 loss)
I0606 00:37:16.332422 54715 solver.cpp:237] Iteration 1791, loss = 0.330114
I0606 00:37:16.332471 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.276026 (* 1 = 0.276026 loss)
I0606 00:37:16.332482 54715 sgd_solver.cpp:106] Iteration 1791, lr = 0.0097124
I0606 00:37:25.705034 54715 solver.cpp:237] Iteration 1794, loss = 0.329736
I0606 00:37:25.705085 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326335 (* 1 = 0.326335 loss)
I0606 00:37:25.705096 54715 sgd_solver.cpp:106] Iteration 1794, lr = 0.00971191
I0606 00:37:35.079803 54715 solver.cpp:237] Iteration 1797, loss = 0.32914
I0606 00:37:35.079854 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.40445 (* 1 = 0.40445 loss)
I0606 00:37:35.079865 54715 sgd_solver.cpp:106] Iteration 1797, lr = 0.00971143
I0606 00:37:41.439831 54715 solver.cpp:341] Iteration 1800, Testing net (#0)
I0606 00:37:42.724042 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.851068
I0606 00:37:42.724087 54715 solver.cpp:409] Test net output #1: class_Acc = 0.900446
I0606 00:37:42.724093 54715 solver.cpp:409] Test net output #2: class_Acc = 0.736333
I0606 00:37:42.724103 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.338921 (* 1 = 0.338921 loss)
I0606 00:37:45.739852 54715 solver.cpp:237] Iteration 1800, loss = 0.330124
I0606 00:37:45.739902 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351551 (* 1 = 0.351551 loss)
I0606 00:37:45.739912 54715 sgd_solver.cpp:106] Iteration 1800, lr = 0.00971095
I0606 00:37:55.114737 54715 solver.cpp:237] Iteration 1803, loss = 0.329999
I0606 00:37:55.114783 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.381465 (* 1 = 0.381465 loss)
I0606 00:37:55.114794 54715 sgd_solver.cpp:106] Iteration 1803, lr = 0.00971046
I0606 00:38:04.488593 54715 solver.cpp:237] Iteration 1806, loss = 0.330152
I0606 00:38:04.488643 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.306919 (* 1 = 0.306919 loss)
I0606 00:38:04.488654 54715 sgd_solver.cpp:106] Iteration 1806, lr = 0.00970998
I0606 00:38:13.866266 54715 solver.cpp:237] Iteration 1809, loss = 0.330431
I0606 00:38:13.866376 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.353574 (* 1 = 0.353574 loss)
I0606 00:38:13.866390 54715 sgd_solver.cpp:106] Iteration 1809, lr = 0.0097095
I0606 00:38:13.975656 54715 solver.cpp:341] Iteration 1810, Testing net (#0)
I0606 00:38:15.258986 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.836266
I0606 00:38:15.259032 54715 solver.cpp:409] Test net output #1: class_Acc = 0.878297
I0606 00:38:15.259039 54715 solver.cpp:409] Test net output #2: class_Acc = 0.73077
I0606 00:38:15.259050 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.360099 (* 1 = 0.360099 loss)
I0606 00:38:18.082823 54715 softmax_loss_layer.cu:194] weight loss 0 =0.244186 weight loss 1 =1 weight loss 2 =0
I0606 00:38:24.521375 54715 solver.cpp:237] Iteration 1812, loss = 0.332892
I0606 00:38:24.521435 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.296041 (* 1 = 0.296041 loss)
I0606 00:38:24.521447 54715 sgd_solver.cpp:106] Iteration 1812, lr = 0.00970901
I0606 00:38:33.895284 54715 solver.cpp:237] Iteration 1815, loss = 0.327974
I0606 00:38:33.895325 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325761 (* 1 = 0.325761 loss)
I0606 00:38:33.895335 54715 sgd_solver.cpp:106] Iteration 1815, lr = 0.00970853
I0606 00:38:43.268803 54715 solver.cpp:237] Iteration 1818, loss = 0.328285
I0606 00:38:43.268852 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345628 (* 1 = 0.345628 loss)
I0606 00:38:43.268862 54715 sgd_solver.cpp:106] Iteration 1818, lr = 0.00970805
I0606 00:38:46.503302 54715 solver.cpp:341] Iteration 1820, Testing net (#0)
I0606 00:38:47.787806 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.858435
I0606 00:38:47.787849 54715 solver.cpp:409] Test net output #1: class_Acc = 0.897878
I0606 00:38:47.787856 54715 solver.cpp:409] Test net output #2: class_Acc = 0.764089
I0606 00:38:47.787866 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.32184 (* 1 = 0.32184 loss)
I0606 00:38:52.962205 54715 softmax_loss_layer.cu:194] weight loss 0 =0.307757 weight loss 1 =1 weight loss 2 =0
I0606 00:38:53.929932 54715 solver.cpp:237] Iteration 1821, loss = 0.327025
I0606 00:38:53.929986 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337849 (* 1 = 0.337849 loss)
I0606 00:38:53.929996 54715 sgd_solver.cpp:106] Iteration 1821, lr = 0.00970756
I0606 00:39:03.306064 54715 solver.cpp:237] Iteration 1824, loss = 0.32352
I0606 00:39:03.306113 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.365911 (* 1 = 0.365911 loss)
I0606 00:39:03.306123 54715 sgd_solver.cpp:106] Iteration 1824, lr = 0.00970708
I0606 00:39:12.681885 54715 solver.cpp:237] Iteration 1827, loss = 0.323938
I0606 00:39:12.681933 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.372076 (* 1 = 0.372076 loss)
I0606 00:39:12.681944 54715 sgd_solver.cpp:106] Iteration 1827, lr = 0.0097066
I0606 00:39:19.040621 54715 solver.cpp:341] Iteration 1830, Testing net (#0)
I0606 00:39:20.324240 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848747
I0606 00:39:20.324285 54715 solver.cpp:409] Test net output #1: class_Acc = 0.895875
I0606 00:39:20.324290 54715 solver.cpp:409] Test net output #2: class_Acc = 0.741473
I0606 00:39:20.324301 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.341532 (* 1 = 0.341532 loss)
I0606 00:39:23.338682 54715 solver.cpp:237] Iteration 1830, loss = 0.325987
I0606 00:39:23.338713 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361694 (* 1 = 0.361694 loss)
I0606 00:39:23.338722 54715 sgd_solver.cpp:106] Iteration 1830, lr = 0.00970611
I0606 00:39:32.713580 54715 solver.cpp:237] Iteration 1833, loss = 0.32835
I0606 00:39:32.713626 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.319906 (* 1 = 0.319906 loss)
I0606 00:39:32.713637 54715 sgd_solver.cpp:106] Iteration 1833, lr = 0.00970563
I0606 00:39:42.087370 54715 solver.cpp:237] Iteration 1836, loss = 0.327255
I0606 00:39:42.087419 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.297168 (* 1 = 0.297168 loss)
I0606 00:39:42.087430 54715 sgd_solver.cpp:106] Iteration 1836, lr = 0.00970514
I0606 00:39:51.462174 54715 solver.cpp:237] Iteration 1839, loss = 0.33237
I0606 00:39:51.462240 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.303565 (* 1 = 0.303565 loss)
I0606 00:39:51.462251 54715 sgd_solver.cpp:106] Iteration 1839, lr = 0.00970466
I0606 00:39:51.571607 54715 solver.cpp:341] Iteration 1840, Testing net (#0)
I0606 00:39:52.854773 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.842074
I0606 00:39:52.854801 54715 solver.cpp:409] Test net output #1: class_Acc = 0.901463
I0606 00:39:52.854809 54715 solver.cpp:409] Test net output #2: class_Acc = 0.713187
I0606 00:39:52.854818 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.357558 (* 1 = 0.357558 loss)
I0606 00:40:02.120406 54715 solver.cpp:237] Iteration 1842, loss = 0.332976
I0606 00:40:02.120457 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351573 (* 1 = 0.351573 loss)
I0606 00:40:02.120467 54715 sgd_solver.cpp:106] Iteration 1842, lr = 0.00970418
I0606 00:40:11.493440 54715 solver.cpp:237] Iteration 1845, loss = 0.332893
I0606 00:40:11.493489 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325273 (* 1 = 0.325273 loss)
I0606 00:40:11.493499 54715 sgd_solver.cpp:106] Iteration 1845, lr = 0.00970369
I0606 00:40:20.868522 54715 solver.cpp:237] Iteration 1848, loss = 0.335379
I0606 00:40:20.868566 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347211 (* 1 = 0.347211 loss)
I0606 00:40:20.868578 54715 sgd_solver.cpp:106] Iteration 1848, lr = 0.00970321
I0606 00:40:24.101855 54715 solver.cpp:341] Iteration 1850, Testing net (#0)
I0606 00:40:25.384439 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.829975
I0606 00:40:25.384485 54715 solver.cpp:409] Test net output #1: class_Acc = 0.924267
I0606 00:40:25.384493 54715 solver.cpp:409] Test net output #2: class_Acc = 0.628943
I0606 00:40:25.384503 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.376948 (* 1 = 0.376948 loss)
I0606 00:40:31.524377 54715 solver.cpp:237] Iteration 1851, loss = 0.33651
I0606 00:40:31.524425 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305118 (* 1 = 0.305118 loss)
I0606 00:40:31.524437 54715 sgd_solver.cpp:106] Iteration 1851, lr = 0.00970273
I0606 00:40:40.898016 54715 solver.cpp:237] Iteration 1854, loss = 0.334198
I0606 00:40:40.898063 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.272952 (* 1 = 0.272952 loss)
I0606 00:40:40.898075 54715 sgd_solver.cpp:106] Iteration 1854, lr = 0.00970224
I0606 00:40:50.272917 54715 solver.cpp:237] Iteration 1857, loss = 0.331036
I0606 00:40:50.272969 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334535 (* 1 = 0.334535 loss)
I0606 00:40:50.272979 54715 sgd_solver.cpp:106] Iteration 1857, lr = 0.00970176
I0606 00:40:56.629395 54715 solver.cpp:341] Iteration 1860, Testing net (#0)
I0606 00:40:57.912847 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.686852
I0606 00:40:57.912894 54715 solver.cpp:409] Test net output #1: class_Acc = 0.657657
I0606 00:40:57.912900 54715 solver.cpp:409] Test net output #2: class_Acc = 0.756811
I0606 00:40:57.912910 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.651706 (* 1 = 0.651706 loss)
I0606 00:41:00.926846 54715 solver.cpp:237] Iteration 1860, loss = 0.332196
I0606 00:41:00.926893 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.339481 (* 1 = 0.339481 loss)
I0606 00:41:00.926903 54715 sgd_solver.cpp:106] Iteration 1860, lr = 0.00970128
I0606 00:41:10.297459 54715 solver.cpp:237] Iteration 1863, loss = 0.330859
I0606 00:41:10.297507 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.364053 (* 1 = 0.364053 loss)
I0606 00:41:10.297516 54715 sgd_solver.cpp:106] Iteration 1863, lr = 0.00970079
I0606 00:41:19.669596 54715 solver.cpp:237] Iteration 1866, loss = 0.327859
I0606 00:41:19.669648 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.336288 (* 1 = 0.336288 loss)
I0606 00:41:19.669661 54715 sgd_solver.cpp:106] Iteration 1866, lr = 0.00970031
I0606 00:41:29.046609 54715 solver.cpp:237] Iteration 1869, loss = 0.328909
I0606 00:41:29.046670 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.319768 (* 1 = 0.319768 loss)
I0606 00:41:29.046682 54715 sgd_solver.cpp:106] Iteration 1869, lr = 0.00969983
I0606 00:41:29.156110 54715 solver.cpp:341] Iteration 1870, Testing net (#0)
I0606 00:41:30.439618 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.850049
I0606 00:41:30.439666 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893531
I0606 00:41:30.439673 54715 solver.cpp:409] Test net output #2: class_Acc = 0.744084
I0606 00:41:30.439692 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.337841 (* 1 = 0.337841 loss)
I0606 00:41:39.702985 54715 solver.cpp:237] Iteration 1872, loss = 0.327461
I0606 00:41:39.703029 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.30082 (* 1 = 0.30082 loss)
I0606 00:41:39.703040 54715 sgd_solver.cpp:106] Iteration 1872, lr = 0.00969934
I0606 00:41:49.074499 54715 solver.cpp:237] Iteration 1875, loss = 0.323259
I0606 00:41:49.074548 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.313288 (* 1 = 0.313288 loss)
I0606 00:41:49.074558 54715 sgd_solver.cpp:106] Iteration 1875, lr = 0.00969886
I0606 00:41:58.447239 54715 solver.cpp:237] Iteration 1878, loss = 0.324329
I0606 00:41:58.447288 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326474 (* 1 = 0.326474 loss)
I0606 00:41:58.447299 54715 sgd_solver.cpp:106] Iteration 1878, lr = 0.00969837
I0606 00:41:59.825565 54715 softmax_loss_layer.cu:194] weight loss 0 =0.238585 weight loss 1 =1 weight loss 2 =0
I0606 00:42:01.682184 54715 solver.cpp:341] Iteration 1880, Testing net (#0)
I0606 00:42:02.966536 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.852752
I0606 00:42:02.966579 54715 solver.cpp:409] Test net output #1: class_Acc = 0.919483
I0606 00:42:02.966586 54715 solver.cpp:409] Test net output #2: class_Acc = 0.688059
I0606 00:42:02.966596 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.334727 (* 1 = 0.334727 loss)
I0606 00:42:09.105012 54715 solver.cpp:237] Iteration 1881, loss = 0.324398
I0606 00:42:09.105058 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.295661 (* 1 = 0.295661 loss)
I0606 00:42:09.105068 54715 sgd_solver.cpp:106] Iteration 1881, lr = 0.00969789
I0606 00:42:17.121168 54715 softmax_loss_layer.cu:194] weight loss 0 =0.274986 weight loss 1 =1 weight loss 2 =0
I0606 00:42:18.477695 54715 solver.cpp:237] Iteration 1884, loss = 0.322794
I0606 00:42:18.477744 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325287 (* 1 = 0.325287 loss)
I0606 00:42:18.477756 54715 sgd_solver.cpp:106] Iteration 1884, lr = 0.00969741
I0606 00:42:27.850847 54715 solver.cpp:237] Iteration 1887, loss = 0.326382
I0606 00:42:27.850896 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.361306 (* 1 = 0.361306 loss)
I0606 00:42:27.850908 54715 sgd_solver.cpp:106] Iteration 1887, lr = 0.00969692
I0606 00:42:34.209528 54715 solver.cpp:341] Iteration 1890, Testing net (#0)
I0606 00:42:35.492900 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.833569
I0606 00:42:35.492944 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893913
I0606 00:42:35.492951 54715 solver.cpp:409] Test net output #2: class_Acc = 0.688266
I0606 00:42:35.492960 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.369075 (* 1 = 0.369075 loss)
I0606 00:42:38.508271 54715 solver.cpp:237] Iteration 1890, loss = 0.324936
I0606 00:42:38.508302 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.401477 (* 1 = 0.401477 loss)
I0606 00:42:38.508312 54715 sgd_solver.cpp:106] Iteration 1890, lr = 0.00969644
I0606 00:42:47.878150 54715 solver.cpp:237] Iteration 1893, loss = 0.326961
I0606 00:42:47.878185 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367466 (* 1 = 0.367466 loss)
I0606 00:42:47.878195 54715 sgd_solver.cpp:106] Iteration 1893, lr = 0.00969596
I0606 00:42:54.729928 54715 softmax_loss_layer.cu:194] weight loss 0 =0.264138 weight loss 1 =1 weight loss 2 =0
I0606 00:42:57.253639 54715 solver.cpp:237] Iteration 1896, loss = 0.327571
I0606 00:42:57.253691 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327662 (* 1 = 0.327662 loss)
I0606 00:42:57.253702 54715 sgd_solver.cpp:106] Iteration 1896, lr = 0.00969547
I0606 00:43:06.630636 54715 solver.cpp:237] Iteration 1899, loss = 0.329008
I0606 00:43:06.630772 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.301887 (* 1 = 0.301887 loss)
I0606 00:43:06.630785 54715 sgd_solver.cpp:106] Iteration 1899, lr = 0.00969499
I0606 00:43:06.740018 54715 solver.cpp:341] Iteration 1900, Testing net (#0)
I0606 00:43:08.022629 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.723309
I0606 00:43:08.022673 54715 solver.cpp:409] Test net output #1: class_Acc = 0.697685
I0606 00:43:08.022680 54715 solver.cpp:409] Test net output #2: class_Acc = 0.781894
I0606 00:43:08.022691 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.578137 (* 1 = 0.578137 loss)
I0606 00:43:17.288161 54715 solver.cpp:237] Iteration 1902, loss = 0.328928
I0606 00:43:17.288213 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.298024 (* 1 = 0.298024 loss)
I0606 00:43:17.288223 54715 sgd_solver.cpp:106] Iteration 1902, lr = 0.0096945
I0606 00:43:26.664136 54715 solver.cpp:237] Iteration 1905, loss = 0.327592
I0606 00:43:26.664206 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.301228 (* 1 = 0.301228 loss)
I0606 00:43:26.665020 54715 sgd_solver.cpp:106] Iteration 1905, lr = 0.00969402
I0606 00:43:36.036968 54715 solver.cpp:237] Iteration 1908, loss = 0.324248
I0606 00:43:36.037019 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.308406 (* 1 = 0.308406 loss)
I0606 00:43:36.037029 54715 sgd_solver.cpp:106] Iteration 1908, lr = 0.00969354
I0606 00:43:39.272313 54715 solver.cpp:341] Iteration 1910, Testing net (#0)
I0606 00:43:40.555156 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.837386
I0606 00:43:40.555203 54715 solver.cpp:409] Test net output #1: class_Acc = 0.95008
I0606 00:43:40.555210 54715 solver.cpp:409] Test net output #2: class_Acc = 0.545047
I0606 00:43:40.555220 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.350723 (* 1 = 0.350723 loss)
I0606 00:43:46.693532 54715 solver.cpp:237] Iteration 1911, loss = 0.323253
I0606 00:43:46.693584 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.335301 (* 1 = 0.335301 loss)
I0606 00:43:46.693595 54715 sgd_solver.cpp:106] Iteration 1911, lr = 0.00969305
I0606 00:43:56.070637 54715 solver.cpp:237] Iteration 1914, loss = 0.322907
I0606 00:43:56.070690 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359268 (* 1 = 0.359268 loss)
I0606 00:43:56.070703 54715 sgd_solver.cpp:106] Iteration 1914, lr = 0.00969257
I0606 00:44:05.449362 54715 solver.cpp:237] Iteration 1917, loss = 0.321853
I0606 00:44:05.449411 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.324726 (* 1 = 0.324726 loss)
I0606 00:44:05.449424 54715 sgd_solver.cpp:106] Iteration 1917, lr = 0.00969209
I0606 00:44:11.808276 54715 solver.cpp:341] Iteration 1920, Testing net (#0)
I0606 00:44:13.093080 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.860842
I0606 00:44:13.093127 54715 solver.cpp:409] Test net output #1: class_Acc = 0.887045
I0606 00:44:13.093134 54715 solver.cpp:409] Test net output #2: class_Acc = 0.797345
I0606 00:44:13.093144 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.318572 (* 1 = 0.318572 loss)
I0606 00:44:16.108572 54715 solver.cpp:237] Iteration 1920, loss = 0.324709
I0606 00:44:16.108621 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.352297 (* 1 = 0.352297 loss)
I0606 00:44:16.108633 54715 sgd_solver.cpp:106] Iteration 1920, lr = 0.0096916
I0606 00:44:25.481838 54715 solver.cpp:237] Iteration 1923, loss = 0.326492
I0606 00:44:25.481889 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.352993 (* 1 = 0.352993 loss)
I0606 00:44:25.481899 54715 sgd_solver.cpp:106] Iteration 1923, lr = 0.00969112
I0606 00:44:34.855810 54715 solver.cpp:237] Iteration 1926, loss = 0.327727
I0606 00:44:34.855859 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.283226 (* 1 = 0.283226 loss)
I0606 00:44:34.855867 54715 sgd_solver.cpp:106] Iteration 1926, lr = 0.00969063
I0606 00:44:44.230419 54715 solver.cpp:237] Iteration 1929, loss = 0.328706
I0606 00:44:44.230522 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.307368 (* 1 = 0.307368 loss)
I0606 00:44:44.230540 54715 sgd_solver.cpp:106] Iteration 1929, lr = 0.00969015
I0606 00:44:44.339855 54715 solver.cpp:341] Iteration 1930, Testing net (#0)
I0606 00:44:45.623492 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.858526
I0606 00:44:45.623538 54715 solver.cpp:409] Test net output #1: class_Acc = 0.920242
I0606 00:44:45.623545 54715 solver.cpp:409] Test net output #2: class_Acc = 0.701623
I0606 00:44:45.623554 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.318138 (* 1 = 0.318138 loss)
I0606 00:44:47.670320 54715 softmax_loss_layer.cu:194] weight loss 0 =0.230343 weight loss 1 =1 weight loss 2 =0
I0606 00:44:54.884722 54715 solver.cpp:237] Iteration 1932, loss = 0.330506
I0606 00:44:54.884773 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.271719 (* 1 = 0.271719 loss)
I0606 00:44:54.884784 54715 sgd_solver.cpp:106] Iteration 1932, lr = 0.00968967
I0606 00:45:04.258631 54715 solver.cpp:237] Iteration 1935, loss = 0.330241
I0606 00:45:04.258682 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.272349 (* 1 = 0.272349 loss)
I0606 00:45:04.258692 54715 sgd_solver.cpp:106] Iteration 1935, lr = 0.00968918
I0606 00:45:13.630697 54715 solver.cpp:237] Iteration 1938, loss = 0.331632
I0606 00:45:13.630745 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.297664 (* 1 = 0.297664 loss)
I0606 00:45:13.630755 54715 sgd_solver.cpp:106] Iteration 1938, lr = 0.0096887
I0606 00:45:16.864517 54715 solver.cpp:341] Iteration 1940, Testing net (#0)
I0606 00:45:18.148149 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.854653
I0606 00:45:18.148195 54715 solver.cpp:409] Test net output #1: class_Acc = 0.886475
I0606 00:45:18.148202 54715 solver.cpp:409] Test net output #2: class_Acc = 0.773056
I0606 00:45:18.148214 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.327834 (* 1 = 0.327834 loss)
I0606 00:45:24.285811 54715 solver.cpp:237] Iteration 1941, loss = 0.33034
I0606 00:45:24.285861 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.373197 (* 1 = 0.373197 loss)
I0606 00:45:24.285872 54715 sgd_solver.cpp:106] Iteration 1941, lr = 0.00968821
I0606 00:45:33.661206 54715 solver.cpp:237] Iteration 1944, loss = 0.326644
I0606 00:45:33.661257 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348539 (* 1 = 0.348539 loss)
I0606 00:45:33.661268 54715 sgd_solver.cpp:106] Iteration 1944, lr = 0.00968773
I0606 00:45:43.035264 54715 solver.cpp:237] Iteration 1947, loss = 0.323498
I0606 00:45:43.035313 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.299682 (* 1 = 0.299682 loss)
I0606 00:45:43.035324 54715 sgd_solver.cpp:106] Iteration 1947, lr = 0.00968725
I0606 00:45:49.394094 54715 solver.cpp:341] Iteration 1950, Testing net (#0)
I0606 00:45:50.678774 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.842351
I0606 00:45:50.678818 54715 solver.cpp:409] Test net output #1: class_Acc = 0.859109
I0606 00:45:50.678825 54715 solver.cpp:409] Test net output #2: class_Acc = 0.798529
I0606 00:45:50.678834 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.353594 (* 1 = 0.353594 loss)
I0606 00:45:53.692852 54715 solver.cpp:237] Iteration 1950, loss = 0.321104
I0606 00:45:53.692899 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.341345 (* 1 = 0.341345 loss)
I0606 00:45:53.692909 54715 sgd_solver.cpp:106] Iteration 1950, lr = 0.00968676
I0606 00:46:03.066165 54715 solver.cpp:237] Iteration 1953, loss = 0.320789
I0606 00:46:03.066216 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.308139 (* 1 = 0.308139 loss)
I0606 00:46:03.066227 54715 sgd_solver.cpp:106] Iteration 1953, lr = 0.00968628
I0606 00:46:09.917589 54715 softmax_loss_layer.cu:194] weight loss 0 =0.319969 weight loss 1 =1 weight loss 2 =0
I0606 00:46:12.442001 54715 solver.cpp:237] Iteration 1956, loss = 0.320042
I0606 00:46:12.442054 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.304884 (* 1 = 0.304884 loss)
I0606 00:46:12.442075 54715 sgd_solver.cpp:106] Iteration 1956, lr = 0.0096858
I0606 00:46:21.819183 54715 solver.cpp:237] Iteration 1959, loss = 0.320055
I0606 00:46:21.819326 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.289458 (* 1 = 0.289458 loss)
I0606 00:46:21.819340 54715 sgd_solver.cpp:106] Iteration 1959, lr = 0.00968531
I0606 00:46:21.928735 54715 solver.cpp:341] Iteration 1960, Testing net (#0)
I0606 00:46:23.213613 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.843793
I0606 00:46:23.213660 54715 solver.cpp:409] Test net output #1: class_Acc = 0.847665
I0606 00:46:23.213666 54715 solver.cpp:409] Test net output #2: class_Acc = 0.828759
I0606 00:46:23.213677 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.351884 (* 1 = 0.351884 loss)
I0606 00:46:32.476194 54715 solver.cpp:237] Iteration 1962, loss = 0.318573
I0606 00:46:32.476249 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318233 (* 1 = 0.318233 loss)
I0606 00:46:32.476261 54715 sgd_solver.cpp:106] Iteration 1962, lr = 0.00968483
I0606 00:46:41.853718 54715 solver.cpp:237] Iteration 1965, loss = 0.318107
I0606 00:46:41.853770 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.26994 (* 1 = 0.26994 loss)
I0606 00:46:41.853781 54715 sgd_solver.cpp:106] Iteration 1965, lr = 0.00968434
I0606 00:46:44.787596 54715 softmax_loss_layer.cu:194] weight loss 0 =0.419285 weight loss 1 =1 weight loss 2 =0
I0606 00:46:51.226243 54715 solver.cpp:237] Iteration 1968, loss = 0.314139
I0606 00:46:51.226294 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.367462 (* 1 = 0.367462 loss)
I0606 00:46:51.226305 54715 sgd_solver.cpp:106] Iteration 1968, lr = 0.00968386
I0606 00:46:54.459883 54715 solver.cpp:341] Iteration 1970, Testing net (#0)
I0606 00:46:55.742238 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.832394
I0606 00:46:55.742281 54715 solver.cpp:409] Test net output #1: class_Acc = 0.960472
I0606 00:46:55.742288 54715 solver.cpp:409] Test net output #2: class_Acc = 0.504016
I0606 00:46:55.742300 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.370496 (* 1 = 0.370496 loss)
I0606 00:47:01.880620 54715 solver.cpp:237] Iteration 1971, loss = 0.313873
I0606 00:47:01.880671 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35896 (* 1 = 0.35896 loss)
I0606 00:47:01.880681 54715 sgd_solver.cpp:106] Iteration 1971, lr = 0.00968338
I0606 00:47:11.262207 54715 solver.cpp:237] Iteration 1974, loss = 0.316648
I0606 00:47:11.262264 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.278308 (* 1 = 0.278308 loss)
I0606 00:47:11.262275 54715 sgd_solver.cpp:106] Iteration 1974, lr = 0.00968289
I0606 00:47:20.639542 54715 solver.cpp:237] Iteration 1977, loss = 0.318513
I0606 00:47:20.639596 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337069 (* 1 = 0.337069 loss)
I0606 00:47:20.639607 54715 sgd_solver.cpp:106] Iteration 1977, lr = 0.00968241
I0606 00:47:26.999146 54715 solver.cpp:341] Iteration 1980, Testing net (#0)
I0606 00:47:28.284063 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848851
I0606 00:47:28.284109 54715 solver.cpp:409] Test net output #1: class_Acc = 0.871564
I0606 00:47:28.284116 54715 solver.cpp:409] Test net output #2: class_Acc = 0.786148
I0606 00:47:28.284126 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.338188 (* 1 = 0.338188 loss)
I0606 00:47:31.297343 54715 solver.cpp:237] Iteration 1980, loss = 0.321304
I0606 00:47:31.297397 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.377069 (* 1 = 0.377069 loss)
I0606 00:47:31.297408 54715 sgd_solver.cpp:106] Iteration 1980, lr = 0.00968193
I0606 00:47:40.671965 54715 solver.cpp:237] Iteration 1983, loss = 0.324392
I0606 00:47:40.672020 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340365 (* 1 = 0.340365 loss)
I0606 00:47:40.672031 54715 sgd_solver.cpp:106] Iteration 1983, lr = 0.00968144
I0606 00:47:50.047394 54715 solver.cpp:237] Iteration 1986, loss = 0.324802
I0606 00:47:50.047456 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310142 (* 1 = 0.310142 loss)
I0606 00:47:50.047467 54715 sgd_solver.cpp:106] Iteration 1986, lr = 0.00968096
I0606 00:47:59.421150 54715 solver.cpp:237] Iteration 1989, loss = 0.321092
I0606 00:47:59.421259 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.291757 (* 1 = 0.291757 loss)
I0606 00:47:59.421272 54715 sgd_solver.cpp:106] Iteration 1989, lr = 0.00968047
I0606 00:47:59.530702 54715 solver.cpp:341] Iteration 1990, Testing net (#0)
I0606 00:48:00.815454 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.852022
I0606 00:48:00.815497 54715 solver.cpp:409] Test net output #1: class_Acc = 0.88259
I0606 00:48:00.815505 54715 solver.cpp:409] Test net output #2: class_Acc = 0.777632
I0606 00:48:00.815515 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.334142 (* 1 = 0.334142 loss)
I0606 00:48:10.080097 54715 solver.cpp:237] Iteration 1992, loss = 0.32136
I0606 00:48:10.080168 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.300622 (* 1 = 0.300622 loss)
I0606 00:48:10.080180 54715 sgd_solver.cpp:106] Iteration 1992, lr = 0.00967999
I0606 00:48:19.458839 54715 solver.cpp:237] Iteration 1995, loss = 0.319411
I0606 00:48:19.458890 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318333 (* 1 = 0.318333 loss)
I0606 00:48:19.458901 54715 sgd_solver.cpp:106] Iteration 1995, lr = 0.00967951
I0606 00:48:28.834358 54715 solver.cpp:237] Iteration 1998, loss = 0.317248
I0606 00:48:28.834408 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.260435 (* 1 = 0.260435 loss)
I0606 00:48:28.834419 54715 sgd_solver.cpp:106] Iteration 1998, lr = 0.00967902
I0606 00:48:32.068783 54715 solver.cpp:459] Snapshotting to binary proto file /home/ubuntu/membraneTraining_SEMTEM/5fm/trainedmodel/5fm_classifer_iter_2000.caffemodel
I0606 00:48:32.477761 54715 sgd_solver.cpp:269] Snapshotting solver state to binary proto file /home/ubuntu/membraneTraining_SEMTEM/5fm/trainedmodel/5fm_classifer_iter_2000.solverstate
I0606 00:48:32.657214 54715 solver.cpp:341] Iteration 2000, Testing net (#0)
I0606 00:48:33.940829 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.860462
I0606 00:48:33.940876 54715 solver.cpp:409] Test net output #1: class_Acc = 0.913281
I0606 00:48:33.940883 54715 solver.cpp:409] Test net output #2: class_Acc = 0.736897
I0606 00:48:33.940892 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.318663 (* 1 = 0.318663 loss)
I0606 00:48:40.081758 54715 solver.cpp:237] Iteration 2001, loss = 0.317028
I0606 00:48:40.081809 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.287076 (* 1 = 0.287076 loss)
I0606 00:48:40.081820 54715 sgd_solver.cpp:106] Iteration 2001, lr = 0.00967854
I0606 00:48:49.456655 54715 solver.cpp:237] Iteration 2004, loss = 0.315281
I0606 00:48:49.456707 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.284058 (* 1 = 0.284058 loss)
I0606 00:48:49.456717 54715 sgd_solver.cpp:106] Iteration 2004, lr = 0.00967805
I0606 00:48:58.834661 54715 solver.cpp:237] Iteration 2007, loss = 0.317547
I0606 00:48:58.834712 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.294496 (* 1 = 0.294496 loss)
I0606 00:48:58.834722 54715 sgd_solver.cpp:106] Iteration 2007, lr = 0.00967757
I0606 00:49:05.194046 54715 solver.cpp:341] Iteration 2010, Testing net (#0)
I0606 00:49:06.478106 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.854303
I0606 00:49:06.478148 54715 solver.cpp:409] Test net output #1: class_Acc = 0.90153
I0606 00:49:06.478157 54715 solver.cpp:409] Test net output #2: class_Acc = 0.735467
I0606 00:49:06.478166 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.332829 (* 1 = 0.332829 loss)
I0606 00:49:09.493122 54715 solver.cpp:237] Iteration 2010, loss = 0.32089
I0606 00:49:09.493172 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.263595 (* 1 = 0.263595 loss)
I0606 00:49:09.493183 54715 sgd_solver.cpp:106] Iteration 2010, lr = 0.00967709
I0606 00:49:18.870620 54715 solver.cpp:237] Iteration 2013, loss = 0.320534
I0606 00:49:18.870672 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.404411 (* 1 = 0.404411 loss)
I0606 00:49:18.870682 54715 sgd_solver.cpp:106] Iteration 2013, lr = 0.0096766
I0606 00:49:28.247454 54715 solver.cpp:237] Iteration 2016, loss = 0.320697
I0606 00:49:28.247503 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.256204 (* 1 = 0.256204 loss)
I0606 00:49:28.247514 54715 sgd_solver.cpp:106] Iteration 2016, lr = 0.00967612
I0606 00:49:30.015897 54715 softmax_loss_layer.cu:194] weight loss 0 =0.194094 weight loss 1 =1 weight loss 2 =0
I0606 00:49:37.625211 54715 solver.cpp:237] Iteration 2019, loss = 0.323616
I0606 00:49:37.625366 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.289135 (* 1 = 0.289135 loss)
I0606 00:49:37.625381 54715 sgd_solver.cpp:106] Iteration 2019, lr = 0.00967563
I0606 00:49:37.734719 54715 solver.cpp:341] Iteration 2020, Testing net (#0)
I0606 00:49:39.018810 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.85155
I0606 00:49:39.018853 54715 solver.cpp:409] Test net output #1: class_Acc = 0.884616
I0606 00:49:39.018860 54715 solver.cpp:409] Test net output #2: class_Acc = 0.771217
I0606 00:49:39.018870 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.336382 (* 1 = 0.336382 loss)
I0606 00:49:48.283807 54715 solver.cpp:237] Iteration 2022, loss = 0.325757
I0606 00:49:48.283860 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325652 (* 1 = 0.325652 loss)
I0606 00:49:48.283871 54715 sgd_solver.cpp:106] Iteration 2022, lr = 0.00967515
I0606 00:49:57.656903 54715 solver.cpp:237] Iteration 2025, loss = 0.326917
I0606 00:49:57.656953 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347874 (* 1 = 0.347874 loss)
I0606 00:49:57.656965 54715 sgd_solver.cpp:106] Iteration 2025, lr = 0.00967467
I0606 00:50:07.030951 54715 solver.cpp:237] Iteration 2028, loss = 0.327444
I0606 00:50:07.031002 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310329 (* 1 = 0.310329 loss)
I0606 00:50:07.031013 54715 sgd_solver.cpp:106] Iteration 2028, lr = 0.00967418
I0606 00:50:10.266852 54715 solver.cpp:341] Iteration 2030, Testing net (#0)
I0606 00:50:11.551429 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.856534
I0606 00:50:11.551473 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893479
I0606 00:50:11.551481 54715 solver.cpp:409] Test net output #2: class_Acc = 0.760653
I0606 00:50:11.551492 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.32609 (* 1 = 0.32609 loss)
I0606 00:50:17.692422 54715 solver.cpp:237] Iteration 2031, loss = 0.32699
I0606 00:50:17.692472 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.273475 (* 1 = 0.273475 loss)
I0606 00:50:17.692482 54715 sgd_solver.cpp:106] Iteration 2031, lr = 0.0096737
I0606 00:50:27.069769 54715 solver.cpp:237] Iteration 2034, loss = 0.322895
I0606 00:50:27.069825 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368518 (* 1 = 0.368518 loss)
I0606 00:50:27.069836 54715 sgd_solver.cpp:106] Iteration 2034, lr = 0.00967321
I0606 00:50:36.444758 54715 solver.cpp:237] Iteration 2037, loss = 0.323523
I0606 00:50:36.444808 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.419922 (* 1 = 0.419922 loss)
I0606 00:50:36.444818 54715 sgd_solver.cpp:106] Iteration 2037, lr = 0.00967273
I0606 00:50:42.803948 54715 solver.cpp:341] Iteration 2040, Testing net (#0)
I0606 00:50:44.088786 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.818657
I0606 00:50:44.088832 54715 solver.cpp:409] Test net output #1: class_Acc = 0.837323
I0606 00:50:44.088840 54715 solver.cpp:409] Test net output #2: class_Acc = 0.772823
I0606 00:50:44.088848 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.404724 (* 1 = 0.404724 loss)
I0606 00:50:47.103693 54715 solver.cpp:237] Iteration 2040, loss = 0.324804
I0606 00:50:47.103742 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366446 (* 1 = 0.366446 loss)
I0606 00:50:47.103754 54715 sgd_solver.cpp:106] Iteration 2040, lr = 0.00967225
I0606 00:50:56.482940 54715 solver.cpp:237] Iteration 2043, loss = 0.324681
I0606 00:50:56.482991 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.32397 (* 1 = 0.32397 loss)
I0606 00:50:56.483002 54715 sgd_solver.cpp:106] Iteration 2043, lr = 0.00967176
I0606 00:51:05.859421 54715 solver.cpp:237] Iteration 2046, loss = 0.327955
I0606 00:51:05.859473 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334556 (* 1 = 0.334556 loss)
I0606 00:51:05.859483 54715 sgd_solver.cpp:106] Iteration 2046, lr = 0.00967128
I0606 00:51:15.233654 54715 solver.cpp:237] Iteration 2049, loss = 0.331533
I0606 00:51:15.233750 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.394979 (* 1 = 0.394979 loss)
I0606 00:51:15.233763 54715 sgd_solver.cpp:106] Iteration 2049, lr = 0.00967079
I0606 00:51:15.343184 54715 solver.cpp:341] Iteration 2050, Testing net (#0)
I0606 00:51:16.626770 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.850703
I0606 00:51:16.626814 54715 solver.cpp:409] Test net output #1: class_Acc = 0.93975
I0606 00:51:16.626821 54715 solver.cpp:409] Test net output #2: class_Acc = 0.636331
I0606 00:51:16.626832 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.336529 (* 1 = 0.336529 loss)
I0606 00:51:25.892371 54715 solver.cpp:237] Iteration 2052, loss = 0.334024
I0606 00:51:25.892419 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359892 (* 1 = 0.359892 loss)
I0606 00:51:25.892431 54715 sgd_solver.cpp:106] Iteration 2052, lr = 0.00967031
I0606 00:51:35.270402 54715 solver.cpp:237] Iteration 2055, loss = 0.331463
I0606 00:51:35.270458 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.347336 (* 1 = 0.347336 loss)
I0606 00:51:35.270469 54715 sgd_solver.cpp:106] Iteration 2055, lr = 0.00966983
I0606 00:51:38.610002 54715 softmax_loss_layer.cu:194] weight loss 0 =0.391335 weight loss 1 =1 weight loss 2 =0
I0606 00:51:44.648975 54715 solver.cpp:237] Iteration 2058, loss = 0.331589
I0606 00:51:44.649022 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321489 (* 1 = 0.321489 loss)
I0606 00:51:44.649034 54715 sgd_solver.cpp:106] Iteration 2058, lr = 0.00966934
I0606 00:51:47.883833 54715 solver.cpp:341] Iteration 2060, Testing net (#0)
I0606 00:51:49.168653 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.847758
I0606 00:51:49.168697 54715 solver.cpp:409] Test net output #1: class_Acc = 0.878916
I0606 00:51:49.168704 54715 solver.cpp:409] Test net output #2: class_Acc = 0.770027
I0606 00:51:49.168714 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.341505 (* 1 = 0.341505 loss)
I0606 00:51:55.309288 54715 solver.cpp:237] Iteration 2061, loss = 0.331969
I0606 00:51:55.309339 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.306952 (* 1 = 0.306952 loss)
I0606 00:51:55.309350 54715 sgd_solver.cpp:106] Iteration 2061, lr = 0.00966886
I0606 00:52:04.686245 54715 solver.cpp:237] Iteration 2064, loss = 0.323834
I0606 00:52:04.686302 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.354826 (* 1 = 0.354826 loss)
I0606 00:52:04.686313 54715 sgd_solver.cpp:106] Iteration 2064, lr = 0.00966837
I0606 00:52:06.454960 54715 softmax_loss_layer.cu:194] weight loss 0 =0.437794 weight loss 1 =1 weight loss 2 =0
I0606 00:52:14.061655 54715 solver.cpp:237] Iteration 2067, loss = 0.319751
I0606 00:52:14.061707 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.382432 (* 1 = 0.382432 loss)
I0606 00:52:14.061718 54715 sgd_solver.cpp:106] Iteration 2067, lr = 0.00966789
I0606 00:52:20.422466 54715 solver.cpp:341] Iteration 2070, Testing net (#0)
I0606 00:52:21.705922 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.832403
I0606 00:52:21.705971 54715 solver.cpp:409] Test net output #1: class_Acc = 0.851081
I0606 00:52:21.705991 54715 solver.cpp:409] Test net output #2: class_Acc = 0.794159
I0606 00:52:21.706001 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.374557 (* 1 = 0.374557 loss)
I0606 00:52:24.720271 54715 solver.cpp:237] Iteration 2070, loss = 0.318127
I0606 00:52:24.720322 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286352 (* 1 = 0.286352 loss)
I0606 00:52:24.720335 54715 sgd_solver.cpp:106] Iteration 2070, lr = 0.0096674
I0606 00:52:34.095634 54715 solver.cpp:237] Iteration 2073, loss = 0.31813
I0606 00:52:34.095687 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366472 (* 1 = 0.366472 loss)
I0606 00:52:34.095698 54715 sgd_solver.cpp:106] Iteration 2073, lr = 0.00966692
I0606 00:52:43.471458 54715 solver.cpp:237] Iteration 2076, loss = 0.317547
I0606 00:52:43.471513 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.294387 (* 1 = 0.294387 loss)
I0606 00:52:43.471523 54715 sgd_solver.cpp:106] Iteration 2076, lr = 0.00966644
I0606 00:52:52.846923 54715 solver.cpp:237] Iteration 2079, loss = 0.317978
I0606 00:52:52.847074 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.279779 (* 1 = 0.279779 loss)
I0606 00:52:52.847087 54715 sgd_solver.cpp:106] Iteration 2079, lr = 0.00966595
I0606 00:52:52.956435 54715 solver.cpp:341] Iteration 2080, Testing net (#0)
I0606 00:52:54.241564 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.858307
I0606 00:52:54.241611 54715 solver.cpp:409] Test net output #1: class_Acc = 0.874212
I0606 00:52:54.241618 54715 solver.cpp:409] Test net output #2: class_Acc = 0.812053
I0606 00:52:54.241628 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.321909 (* 1 = 0.321909 loss)
I0606 00:53:03.502957 54715 solver.cpp:237] Iteration 2082, loss = 0.31934
I0606 00:53:03.503011 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.282921 (* 1 = 0.282921 loss)
I0606 00:53:03.503022 54715 sgd_solver.cpp:106] Iteration 2082, lr = 0.00966547
I0606 00:53:12.877986 54715 solver.cpp:237] Iteration 2085, loss = 0.320315
I0606 00:53:12.878041 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310777 (* 1 = 0.310777 loss)
I0606 00:53:12.878051 54715 sgd_solver.cpp:106] Iteration 2085, lr = 0.00966498
I0606 00:53:22.252502 54715 solver.cpp:237] Iteration 2088, loss = 0.320576
I0606 00:53:22.252555 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.356816 (* 1 = 0.356816 loss)
I0606 00:53:22.252566 54715 sgd_solver.cpp:106] Iteration 2088, lr = 0.0096645
I0606 00:53:25.488639 54715 solver.cpp:341] Iteration 2090, Testing net (#0)
I0606 00:53:26.772456 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.861948
I0606 00:53:26.772503 54715 solver.cpp:409] Test net output #1: class_Acc = 0.931059
I0606 00:53:26.772511 54715 solver.cpp:409] Test net output #2: class_Acc = 0.694651
I0606 00:53:26.772521 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.316368 (* 1 = 0.316368 loss)
I0606 00:53:32.911504 54715 solver.cpp:237] Iteration 2091, loss = 0.317225
I0606 00:53:32.911557 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.308737 (* 1 = 0.308737 loss)
I0606 00:53:32.911568 54715 sgd_solver.cpp:106] Iteration 2091, lr = 0.00966402
I0606 00:53:42.284723 54715 solver.cpp:237] Iteration 2094, loss = 0.317599
I0606 00:53:42.284777 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.304791 (* 1 = 0.304791 loss)
I0606 00:53:42.284788 54715 sgd_solver.cpp:106] Iteration 2094, lr = 0.00966353
I0606 00:53:51.659804 54715 solver.cpp:237] Iteration 2097, loss = 0.318157
I0606 00:53:51.659859 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31384 (* 1 = 0.31384 loss)
I0606 00:53:51.659870 54715 sgd_solver.cpp:106] Iteration 2097, lr = 0.00966305
I0606 00:53:58.019668 54715 solver.cpp:341] Iteration 2100, Testing net (#0)
I0606 00:53:59.305022 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.846094
I0606 00:53:59.305070 54715 solver.cpp:409] Test net output #1: class_Acc = 0.890229
I0606 00:53:59.305088 54715 solver.cpp:409] Test net output #2: class_Acc = 0.733891
I0606 00:53:59.305097 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.349654 (* 1 = 0.349654 loss)
I0606 00:54:02.321107 54715 solver.cpp:237] Iteration 2100, loss = 0.318837
I0606 00:54:02.321157 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.340205 (* 1 = 0.340205 loss)
I0606 00:54:02.321168 54715 sgd_solver.cpp:106] Iteration 2100, lr = 0.00966256
I0606 00:54:11.693186 54715 solver.cpp:237] Iteration 2103, loss = 0.320082
I0606 00:54:11.693233 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.381745 (* 1 = 0.381745 loss)
I0606 00:54:11.693244 54715 sgd_solver.cpp:106] Iteration 2103, lr = 0.00966208
I0606 00:54:21.069039 54715 solver.cpp:237] Iteration 2106, loss = 0.32341
I0606 00:54:21.069093 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.37487 (* 1 = 0.37487 loss)
I0606 00:54:21.069104 54715 sgd_solver.cpp:106] Iteration 2106, lr = 0.0096616
I0606 00:54:30.442136 54715 solver.cpp:237] Iteration 2109, loss = 0.32518
I0606 00:54:30.442204 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.273487 (* 1 = 0.273487 loss)
I0606 00:54:30.442215 54715 sgd_solver.cpp:106] Iteration 2109, lr = 0.00966111
I0606 00:54:30.551789 54715 solver.cpp:341] Iteration 2110, Testing net (#0)
I0606 00:54:31.836169 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.833173
I0606 00:54:31.836218 54715 solver.cpp:409] Test net output #1: class_Acc = 0.909285
I0606 00:54:31.836225 54715 solver.cpp:409] Test net output #2: class_Acc = 0.632337
I0606 00:54:31.836236 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.389342 (* 1 = 0.389342 loss)
I0606 00:54:41.106057 54715 solver.cpp:237] Iteration 2112, loss = 0.322417
I0606 00:54:41.106117 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.295391 (* 1 = 0.295391 loss)
I0606 00:54:41.106127 54715 sgd_solver.cpp:106] Iteration 2112, lr = 0.00966063
I0606 00:54:50.482913 54715 solver.cpp:237] Iteration 2115, loss = 0.323032
I0606 00:54:50.482960 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.341673 (* 1 = 0.341673 loss)
I0606 00:54:50.482971 54715 sgd_solver.cpp:106] Iteration 2115, lr = 0.00966014
I0606 00:54:59.858716 54715 solver.cpp:237] Iteration 2118, loss = 0.317901
I0606 00:54:59.858763 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.430506 (* 1 = 0.430506 loss)
I0606 00:54:59.858774 54715 sgd_solver.cpp:106] Iteration 2118, lr = 0.00965966
I0606 00:55:03.092447 54715 solver.cpp:341] Iteration 2120, Testing net (#0)
I0606 00:55:04.377048 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.833366
I0606 00:55:04.377094 54715 solver.cpp:409] Test net output #1: class_Acc = 0.85283
I0606 00:55:04.377101 54715 solver.cpp:409] Test net output #2: class_Acc = 0.78509
I0606 00:55:04.377111 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.375968 (* 1 = 0.375968 loss)
I0606 00:55:10.518210 54715 solver.cpp:237] Iteration 2121, loss = 0.31957
I0606 00:55:10.518265 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.302913 (* 1 = 0.302913 loss)
I0606 00:55:10.518275 54715 sgd_solver.cpp:106] Iteration 2121, lr = 0.00965917
I0606 00:55:19.895522 54715 solver.cpp:237] Iteration 2124, loss = 0.316274
I0606 00:55:19.895572 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.277411 (* 1 = 0.277411 loss)
I0606 00:55:19.895584 54715 sgd_solver.cpp:106] Iteration 2124, lr = 0.00965869
I0606 00:55:29.271749 54715 solver.cpp:237] Iteration 2127, loss = 0.318492
I0606 00:55:29.271800 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327665 (* 1 = 0.327665 loss)
I0606 00:55:29.271811 54715 sgd_solver.cpp:106] Iteration 2127, lr = 0.00965821
I0606 00:55:35.634887 54715 solver.cpp:341] Iteration 2130, Testing net (#0)
I0606 00:55:36.918893 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.847948
I0606 00:55:36.918932 54715 solver.cpp:409] Test net output #1: class_Acc = 0.933351
I0606 00:55:36.918946 54715 solver.cpp:409] Test net output #2: class_Acc = 0.636315
I0606 00:55:36.918957 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.340779 (* 1 = 0.340779 loss)
I0606 00:55:39.934118 54715 solver.cpp:237] Iteration 2130, loss = 0.31763
I0606 00:55:39.934170 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.420632 (* 1 = 0.420632 loss)
I0606 00:55:39.934180 54715 sgd_solver.cpp:106] Iteration 2130, lr = 0.00965772
I0606 00:55:49.308126 54715 solver.cpp:237] Iteration 2133, loss = 0.322833
I0606 00:55:49.308192 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.349791 (* 1 = 0.349791 loss)
I0606 00:55:49.308203 54715 sgd_solver.cpp:106] Iteration 2133, lr = 0.00965724
I0606 00:55:58.681949 54715 solver.cpp:237] Iteration 2136, loss = 0.321586
I0606 00:55:58.682003 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.271297 (* 1 = 0.271297 loss)
I0606 00:55:58.682014 54715 sgd_solver.cpp:106] Iteration 2136, lr = 0.00965675
I0606 00:56:08.058042 54715 solver.cpp:237] Iteration 2139, loss = 0.31987
I0606 00:56:08.058161 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.375931 (* 1 = 0.375931 loss)
I0606 00:56:08.058173 54715 sgd_solver.cpp:106] Iteration 2139, lr = 0.00965627
I0606 00:56:08.167601 54715 solver.cpp:341] Iteration 2140, Testing net (#0)
I0606 00:56:09.452262 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.849799
I0606 00:56:09.452307 54715 solver.cpp:409] Test net output #1: class_Acc = 0.889771
I0606 00:56:09.452316 54715 solver.cpp:409] Test net output #2: class_Acc = 0.750136
I0606 00:56:09.452325 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.335627 (* 1 = 0.335627 loss)
I0606 00:56:18.714774 54715 solver.cpp:237] Iteration 2142, loss = 0.320883
I0606 00:56:18.714826 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.300963 (* 1 = 0.300963 loss)
I0606 00:56:18.714838 54715 sgd_solver.cpp:106] Iteration 2142, lr = 0.00965579
I0606 00:56:28.088608 54715 solver.cpp:237] Iteration 2145, loss = 0.321738
I0606 00:56:28.088661 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.254056 (* 1 = 0.254056 loss)
I0606 00:56:28.088673 54715 sgd_solver.cpp:106] Iteration 2145, lr = 0.0096553
I0606 00:56:37.464741 54715 solver.cpp:237] Iteration 2148, loss = 0.319091
I0606 00:56:37.464795 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.306972 (* 1 = 0.306972 loss)
I0606 00:56:37.464807 54715 sgd_solver.cpp:106] Iteration 2148, lr = 0.00965482
I0606 00:56:40.698479 54715 solver.cpp:341] Iteration 2150, Testing net (#0)
I0606 00:56:41.983180 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.845784
I0606 00:56:41.983227 54715 solver.cpp:409] Test net output #1: class_Acc = 0.88498
I0606 00:56:41.983234 54715 solver.cpp:409] Test net output #2: class_Acc = 0.753671
I0606 00:56:41.983244 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.347934 (* 1 = 0.347934 loss)
I0606 00:56:48.124416 54715 solver.cpp:237] Iteration 2151, loss = 0.320389
I0606 00:56:48.124469 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.356471 (* 1 = 0.356471 loss)
I0606 00:56:48.124480 54715 sgd_solver.cpp:106] Iteration 2151, lr = 0.00965433
I0606 00:56:57.500617 54715 solver.cpp:237] Iteration 2154, loss = 0.32016
I0606 00:56:57.500669 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.284198 (* 1 = 0.284198 loss)
I0606 00:56:57.500681 54715 sgd_solver.cpp:106] Iteration 2154, lr = 0.00965385
I0606 00:57:06.875023 54715 solver.cpp:237] Iteration 2157, loss = 0.317967
I0606 00:57:06.875072 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.287755 (* 1 = 0.287755 loss)
I0606 00:57:06.875083 54715 sgd_solver.cpp:106] Iteration 2157, lr = 0.00965336
I0606 00:57:13.234530 54715 solver.cpp:341] Iteration 2160, Testing net (#0)
I0606 00:57:14.518987 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.808444
I0606 00:57:14.519033 54715 solver.cpp:409] Test net output #1: class_Acc = 0.815544
I0606 00:57:14.519042 54715 solver.cpp:409] Test net output #2: class_Acc = 0.789702
I0606 00:57:14.519052 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.431406 (* 1 = 0.431406 loss)
I0606 00:57:17.534420 54715 solver.cpp:237] Iteration 2160, loss = 0.317865
I0606 00:57:17.534466 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.344048 (* 1 = 0.344048 loss)
I0606 00:57:17.534477 54715 sgd_solver.cpp:106] Iteration 2160, lr = 0.00965288
I0606 00:57:26.913561 54715 solver.cpp:237] Iteration 2163, loss = 0.31757
I0606 00:57:26.913612 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.293698 (* 1 = 0.293698 loss)
I0606 00:57:26.913625 54715 sgd_solver.cpp:106] Iteration 2163, lr = 0.0096524
I0606 00:57:36.290009 54715 solver.cpp:237] Iteration 2166, loss = 0.310844
I0606 00:57:36.290060 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.359447 (* 1 = 0.359447 loss)
I0606 00:57:36.290069 54715 sgd_solver.cpp:106] Iteration 2166, lr = 0.00965191
I0606 00:57:45.665383 54715 solver.cpp:237] Iteration 2169, loss = 0.311816
I0606 00:57:45.665506 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.253057 (* 1 = 0.253057 loss)
I0606 00:57:45.665518 54715 sgd_solver.cpp:106] Iteration 2169, lr = 0.00965143
I0606 00:57:45.775009 54715 solver.cpp:341] Iteration 2170, Testing net (#0)
I0606 00:57:47.059813 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.844053
I0606 00:57:47.059859 54715 solver.cpp:409] Test net output #1: class_Acc = 0.884252
I0606 00:57:47.059867 54715 solver.cpp:409] Test net output #2: class_Acc = 0.753209
I0606 00:57:47.059877 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.349492 (* 1 = 0.349492 loss)
I0606 00:57:56.324450 54715 solver.cpp:237] Iteration 2172, loss = 0.311981
I0606 00:57:56.324498 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348975 (* 1 = 0.348975 loss)
I0606 00:57:56.324510 54715 sgd_solver.cpp:106] Iteration 2172, lr = 0.00965094
I0606 00:58:05.698876 54715 solver.cpp:237] Iteration 2175, loss = 0.31078
I0606 00:58:05.698925 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351558 (* 1 = 0.351558 loss)
I0606 00:58:05.698935 54715 sgd_solver.cpp:106] Iteration 2175, lr = 0.00965046
I0606 00:58:15.072357 54715 solver.cpp:237] Iteration 2178, loss = 0.309925
I0606 00:58:15.072409 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.251673 (* 1 = 0.251673 loss)
I0606 00:58:15.072419 54715 sgd_solver.cpp:106] Iteration 2178, lr = 0.00964997
I0606 00:58:18.307467 54715 solver.cpp:341] Iteration 2180, Testing net (#0)
I0606 00:58:19.591964 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.856886
I0606 00:58:19.592010 54715 solver.cpp:409] Test net output #1: class_Acc = 0.89394
I0606 00:58:19.592015 54715 solver.cpp:409] Test net output #2: class_Acc = 0.770951
I0606 00:58:19.592025 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.328835 (* 1 = 0.328835 loss)
I0606 00:58:25.731129 54715 solver.cpp:237] Iteration 2181, loss = 0.312443
I0606 00:58:25.731184 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31473 (* 1 = 0.31473 loss)
I0606 00:58:25.731195 54715 sgd_solver.cpp:106] Iteration 2181, lr = 0.00964949
I0606 00:58:35.111131 54715 solver.cpp:237] Iteration 2184, loss = 0.311428
I0606 00:58:35.111182 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.339793 (* 1 = 0.339793 loss)
I0606 00:58:35.111193 54715 sgd_solver.cpp:106] Iteration 2184, lr = 0.00964901
I0606 00:58:44.486963 54715 solver.cpp:237] Iteration 2187, loss = 0.314318
I0606 00:58:44.487015 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.283992 (* 1 = 0.283992 loss)
I0606 00:58:44.487025 54715 sgd_solver.cpp:106] Iteration 2187, lr = 0.00964852
I0606 00:58:45.477671 54715 softmax_loss_layer.cu:194] weight loss 0 =0.25441 weight loss 1 =1 weight loss 2 =0
I0606 00:58:49.770017 54715 softmax_loss_layer.cu:194] weight loss 0 =0.350385 weight loss 1 =1 weight loss 2 =0
I0606 00:58:50.846758 54715 solver.cpp:341] Iteration 2190, Testing net (#0)
I0606 00:58:52.130450 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848467
I0606 00:58:52.130494 54715 solver.cpp:409] Test net output #1: class_Acc = 0.90218
I0606 00:58:52.130501 54715 solver.cpp:409] Test net output #2: class_Acc = 0.716516
I0606 00:58:52.130511 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.336599 (* 1 = 0.336599 loss)
I0606 00:58:55.145411 54715 solver.cpp:237] Iteration 2190, loss = 0.315115
I0606 00:58:55.145459 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.345763 (* 1 = 0.345763 loss)
I0606 00:58:55.145470 54715 sgd_solver.cpp:106] Iteration 2190, lr = 0.00964804
I0606 00:59:01.612179 54715 softmax_loss_layer.cu:194] weight loss 0 =0.213825 weight loss 1 =1 weight loss 2 =0
I0606 00:59:04.524015 54715 solver.cpp:237] Iteration 2193, loss = 0.318362
I0606 00:59:04.524068 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311584 (* 1 = 0.311584 loss)
I0606 00:59:04.524080 54715 sgd_solver.cpp:106] Iteration 2193, lr = 0.00964755
I0606 00:59:13.899894 54715 solver.cpp:237] Iteration 2196, loss = 0.315642
I0606 00:59:13.899950 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.365479 (* 1 = 0.365479 loss)
I0606 00:59:13.899960 54715 sgd_solver.cpp:106] Iteration 2196, lr = 0.00964707
I0606 00:59:23.277225 54715 solver.cpp:237] Iteration 2199, loss = 0.315381
I0606 00:59:23.277298 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327892 (* 1 = 0.327892 loss)
I0606 00:59:23.277310 54715 sgd_solver.cpp:106] Iteration 2199, lr = 0.00964658
I0606 00:59:23.386735 54715 solver.cpp:341] Iteration 2200, Testing net (#0)
I0606 00:59:24.671636 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.846334
I0606 00:59:24.671681 54715 solver.cpp:409] Test net output #1: class_Acc = 0.865698
I0606 00:59:24.671689 54715 solver.cpp:409] Test net output #2: class_Acc = 0.794996
I0606 00:59:24.671699 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.348517 (* 1 = 0.348517 loss)
I0606 00:59:33.932986 54715 solver.cpp:237] Iteration 2202, loss = 0.31386
I0606 00:59:33.933043 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.307083 (* 1 = 0.307083 loss)
I0606 00:59:33.933054 54715 sgd_solver.cpp:106] Iteration 2202, lr = 0.0096461
I0606 00:59:43.308904 54715 solver.cpp:237] Iteration 2205, loss = 0.314861
I0606 00:59:43.308957 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.285297 (* 1 = 0.285297 loss)
I0606 00:59:43.308969 54715 sgd_solver.cpp:106] Iteration 2205, lr = 0.00964562
I0606 00:59:52.683759 54715 solver.cpp:237] Iteration 2208, loss = 0.314004
I0606 00:59:52.683810 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.290498 (* 1 = 0.290498 loss)
I0606 00:59:52.683822 54715 sgd_solver.cpp:106] Iteration 2208, lr = 0.00964513
I0606 00:59:55.920157 54715 solver.cpp:341] Iteration 2210, Testing net (#0)
I0606 00:59:57.205029 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.861945
I0606 00:59:57.205075 54715 solver.cpp:409] Test net output #1: class_Acc = 0.916105
I0606 00:59:57.205082 54715 solver.cpp:409] Test net output #2: class_Acc = 0.723557
I0606 00:59:57.205092 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.310937 (* 1 = 0.310937 loss)
I0606 01:00:03.343405 54715 solver.cpp:237] Iteration 2211, loss = 0.315299
I0606 01:00:03.343458 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.312142 (* 1 = 0.312142 loss)
I0606 01:00:03.343469 54715 sgd_solver.cpp:106] Iteration 2211, lr = 0.00964465
I0606 01:00:12.720062 54715 solver.cpp:237] Iteration 2214, loss = 0.314698
I0606 01:00:12.720116 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.324942 (* 1 = 0.324942 loss)
I0606 01:00:12.720127 54715 sgd_solver.cpp:106] Iteration 2214, lr = 0.00964416
I0606 01:00:22.094837 54715 solver.cpp:237] Iteration 2217, loss = 0.317947
I0606 01:00:22.094905 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.253595 (* 1 = 0.253595 loss)
I0606 01:00:22.094918 54715 sgd_solver.cpp:106] Iteration 2217, lr = 0.00964368
I0606 01:00:28.452504 54715 solver.cpp:341] Iteration 2220, Testing net (#0)
I0606 01:00:29.738073 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848641
I0606 01:00:29.738117 54715 solver.cpp:409] Test net output #1: class_Acc = 0.870729
I0606 01:00:29.738126 54715 solver.cpp:409] Test net output #2: class_Acc = 0.788261
I0606 01:00:29.738134 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.341776 (* 1 = 0.341776 loss)
I0606 01:00:31.396318 54715 softmax_loss_layer.cu:194] weight loss 0 =0.243452 weight loss 1 =1 weight loss 2 =0
I0606 01:00:32.753670 54715 solver.cpp:237] Iteration 2220, loss = 0.319363
I0606 01:00:32.753721 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.269753 (* 1 = 0.269753 loss)
I0606 01:00:32.753731 54715 sgd_solver.cpp:106] Iteration 2220, lr = 0.00964319
I0606 01:00:42.130342 54715 solver.cpp:237] Iteration 2223, loss = 0.320021
I0606 01:00:42.130393 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.370416 (* 1 = 0.370416 loss)
I0606 01:00:42.130403 54715 sgd_solver.cpp:106] Iteration 2223, lr = 0.00964271
I0606 01:00:51.504531 54715 solver.cpp:237] Iteration 2226, loss = 0.314193
I0606 01:00:51.504585 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.29549 (* 1 = 0.29549 loss)
I0606 01:00:51.504597 54715 sgd_solver.cpp:106] Iteration 2226, lr = 0.00964222
I0606 01:01:00.879772 54715 solver.cpp:237] Iteration 2229, loss = 0.317312
I0606 01:01:00.879845 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.320744 (* 1 = 0.320744 loss)
I0606 01:01:00.879856 54715 sgd_solver.cpp:106] Iteration 2229, lr = 0.00964174
I0606 01:01:00.989359 54715 solver.cpp:341] Iteration 2230, Testing net (#0)
I0606 01:01:02.275159 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.849505
I0606 01:01:02.275207 54715 solver.cpp:409] Test net output #1: class_Acc = 0.867075
I0606 01:01:02.275213 54715 solver.cpp:409] Test net output #2: class_Acc = 0.801654
I0606 01:01:02.275224 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.337208 (* 1 = 0.337208 loss)
I0606 01:01:11.539360 54715 solver.cpp:237] Iteration 2232, loss = 0.314721
I0606 01:01:11.539407 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334417 (* 1 = 0.334417 loss)
I0606 01:01:11.539417 54715 sgd_solver.cpp:106] Iteration 2232, lr = 0.00964126
I0606 01:01:20.721884 54715 softmax_loss_layer.cu:194] weight loss 0 =0.337331 weight loss 1 =1 weight loss 2 =0
I0606 01:01:20.911371 54715 solver.cpp:237] Iteration 2235, loss = 0.31337
I0606 01:01:20.911417 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.27719 (* 1 = 0.27719 loss)
I0606 01:01:20.911427 54715 sgd_solver.cpp:106] Iteration 2235, lr = 0.00964077
I0606 01:01:30.284870 54715 solver.cpp:237] Iteration 2238, loss = 0.31004
I0606 01:01:30.284925 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.258733 (* 1 = 0.258733 loss)
I0606 01:01:30.284936 54715 sgd_solver.cpp:106] Iteration 2238, lr = 0.00964029
I0606 01:01:33.518860 54715 solver.cpp:341] Iteration 2240, Testing net (#0)
I0606 01:01:34.803395 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.856853
I0606 01:01:34.803441 54715 solver.cpp:409] Test net output #1: class_Acc = 0.887462
I0606 01:01:34.803447 54715 solver.cpp:409] Test net output #2: class_Acc = 0.784053
I0606 01:01:34.803457 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.326834 (* 1 = 0.326834 loss)
I0606 01:01:40.941215 54715 solver.cpp:237] Iteration 2241, loss = 0.313042
I0606 01:01:40.941267 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.346334 (* 1 = 0.346334 loss)
I0606 01:01:40.941277 54715 sgd_solver.cpp:106] Iteration 2241, lr = 0.0096398
I0606 01:01:50.317219 54715 solver.cpp:237] Iteration 2244, loss = 0.312608
I0606 01:01:50.317281 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.220478 (* 1 = 0.220478 loss)
I0606 01:01:50.317291 54715 sgd_solver.cpp:106] Iteration 2244, lr = 0.00963932
I0606 01:01:59.692525 54715 solver.cpp:237] Iteration 2247, loss = 0.314851
I0606 01:01:59.692577 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337417 (* 1 = 0.337417 loss)
I0606 01:01:59.692587 54715 sgd_solver.cpp:106] Iteration 2247, lr = 0.00963883
I0606 01:02:06.053298 54715 solver.cpp:341] Iteration 2250, Testing net (#0)
I0606 01:02:07.338940 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.859419
I0606 01:02:07.338987 54715 solver.cpp:409] Test net output #1: class_Acc = 0.866578
I0606 01:02:07.338995 54715 solver.cpp:409] Test net output #2: class_Acc = 0.838372
I0606 01:02:07.339005 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.319421 (* 1 = 0.319421 loss)
I0606 01:02:10.352170 54715 solver.cpp:237] Iteration 2250, loss = 0.315656
I0606 01:02:10.352221 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.33365 (* 1 = 0.33365 loss)
I0606 01:02:10.352231 54715 sgd_solver.cpp:106] Iteration 2250, lr = 0.00963835
I0606 01:02:19.725417 54715 solver.cpp:237] Iteration 2253, loss = 0.31598
I0606 01:02:19.725468 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.302807 (* 1 = 0.302807 loss)
I0606 01:02:19.725481 54715 sgd_solver.cpp:106] Iteration 2253, lr = 0.00963787
I0606 01:02:29.099092 54715 solver.cpp:237] Iteration 2256, loss = 0.320257
I0606 01:02:29.099141 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.390972 (* 1 = 0.390972 loss)
I0606 01:02:29.099153 54715 sgd_solver.cpp:106] Iteration 2256, lr = 0.00963738
I0606 01:02:38.471894 54715 solver.cpp:237] Iteration 2259, loss = 0.32005
I0606 01:02:38.471963 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.30648 (* 1 = 0.30648 loss)
I0606 01:02:38.471974 54715 sgd_solver.cpp:106] Iteration 2259, lr = 0.0096369
I0606 01:02:38.581441 54715 solver.cpp:341] Iteration 2260, Testing net (#0)
I0606 01:02:39.866309 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.838285
I0606 01:02:39.866356 54715 solver.cpp:409] Test net output #1: class_Acc = 0.882284
I0606 01:02:39.866364 54715 solver.cpp:409] Test net output #2: class_Acc = 0.729568
I0606 01:02:39.866374 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.360343 (* 1 = 0.360343 loss)
I0606 01:02:49.130110 54715 solver.cpp:237] Iteration 2262, loss = 0.318246
I0606 01:02:49.130161 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.28732 (* 1 = 0.28732 loss)
I0606 01:02:49.130172 54715 sgd_solver.cpp:106] Iteration 2262, lr = 0.00963641
I0606 01:02:58.503571 54715 solver.cpp:237] Iteration 2265, loss = 0.316183
I0606 01:02:58.503623 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.335339 (* 1 = 0.335339 loss)
I0606 01:02:58.503634 54715 sgd_solver.cpp:106] Iteration 2265, lr = 0.00963593
I0606 01:03:07.876391 54715 solver.cpp:237] Iteration 2268, loss = 0.318005
I0606 01:03:07.876444 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.377821 (* 1 = 0.377821 loss)
I0606 01:03:07.876456 54715 sgd_solver.cpp:106] Iteration 2268, lr = 0.00963544
I0606 01:03:11.112097 54715 solver.cpp:341] Iteration 2270, Testing net (#0)
I0606 01:03:12.397307 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.84778
I0606 01:03:12.397354 54715 solver.cpp:409] Test net output #1: class_Acc = 0.868979
I0606 01:03:12.397361 54715 solver.cpp:409] Test net output #2: class_Acc = 0.794451
I0606 01:03:12.397372 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.343996 (* 1 = 0.343996 loss)
I0606 01:03:18.537600 54715 solver.cpp:237] Iteration 2271, loss = 0.315225
I0606 01:03:18.537645 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326938 (* 1 = 0.326938 loss)
I0606 01:03:18.537657 54715 sgd_solver.cpp:106] Iteration 2271, lr = 0.00963496
I0606 01:03:27.912170 54715 solver.cpp:237] Iteration 2274, loss = 0.31473
I0606 01:03:27.912221 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.372182 (* 1 = 0.372182 loss)
I0606 01:03:27.912231 54715 sgd_solver.cpp:106] Iteration 2274, lr = 0.00963447
I0606 01:03:35.540701 54715 softmax_loss_layer.cu:194] weight loss 0 =0.382428 weight loss 1 =1 weight loss 2 =0
I0606 01:03:37.285719 54715 solver.cpp:237] Iteration 2277, loss = 0.318324
I0606 01:03:37.285773 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.261611 (* 1 = 0.261611 loss)
I0606 01:03:37.285784 54715 sgd_solver.cpp:106] Iteration 2277, lr = 0.00963399
I0606 01:03:43.647006 54715 solver.cpp:341] Iteration 2280, Testing net (#0)
I0606 01:03:44.932281 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.86383
I0606 01:03:44.932327 54715 solver.cpp:409] Test net output #1: class_Acc = 0.9099
I0606 01:03:44.932333 54715 solver.cpp:409] Test net output #2: class_Acc = 0.752915
I0606 01:03:44.932343 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.309966 (* 1 = 0.309966 loss)
I0606 01:03:47.947285 54715 solver.cpp:237] Iteration 2280, loss = 0.320628
I0606 01:03:47.947338 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.323716 (* 1 = 0.323716 loss)
I0606 01:03:47.947350 54715 sgd_solver.cpp:106] Iteration 2280, lr = 0.0096335
I0606 01:03:56.359499 54715 softmax_loss_layer.cu:194] weight loss 0 =0.248129 weight loss 1 =1 weight loss 2 =0
I0606 01:03:57.327339 54715 solver.cpp:237] Iteration 2283, loss = 0.316144
I0606 01:03:57.327390 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.331619 (* 1 = 0.331619 loss)
I0606 01:03:57.327402 54715 sgd_solver.cpp:106] Iteration 2283, lr = 0.00963302
I0606 01:04:06.703534 54715 solver.cpp:237] Iteration 2286, loss = 0.318523
I0606 01:04:06.703588 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.278436 (* 1 = 0.278436 loss)
I0606 01:04:06.703600 54715 sgd_solver.cpp:106] Iteration 2286, lr = 0.00963254
I0606 01:04:16.080700 54715 solver.cpp:237] Iteration 2289, loss = 0.320691
I0606 01:04:16.080765 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.280997 (* 1 = 0.280997 loss)
I0606 01:04:16.080777 54715 sgd_solver.cpp:106] Iteration 2289, lr = 0.00963205
I0606 01:04:16.190193 54715 solver.cpp:341] Iteration 2290, Testing net (#0)
I0606 01:04:17.474601 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.812478
I0606 01:04:17.474647 54715 solver.cpp:409] Test net output #1: class_Acc = 0.788736
I0606 01:04:17.474655 54715 solver.cpp:409] Test net output #2: class_Acc = 0.857376
I0606 01:04:17.474665 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.408795 (* 1 = 0.408795 loss)
I0606 01:04:26.738823 54715 solver.cpp:237] Iteration 2292, loss = 0.316934
I0606 01:04:26.738873 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.279667 (* 1 = 0.279667 loss)
I0606 01:04:26.738886 54715 sgd_solver.cpp:106] Iteration 2292, lr = 0.00963157
I0606 01:04:36.114651 54715 solver.cpp:237] Iteration 2295, loss = 0.315697
I0606 01:04:36.114709 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.328846 (* 1 = 0.328846 loss)
I0606 01:04:36.114720 54715 sgd_solver.cpp:106] Iteration 2295, lr = 0.00963108
I0606 01:04:45.487085 54715 solver.cpp:237] Iteration 2298, loss = 0.315663
I0606 01:04:45.487130 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31071 (* 1 = 0.31071 loss)
I0606 01:04:45.487141 54715 sgd_solver.cpp:106] Iteration 2298, lr = 0.0096306
I0606 01:04:48.722326 54715 solver.cpp:341] Iteration 2300, Testing net (#0)
I0606 01:04:50.006418 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.843575
I0606 01:04:50.006465 54715 solver.cpp:409] Test net output #1: class_Acc = 0.919919
I0606 01:04:50.006471 54715 solver.cpp:409] Test net output #2: class_Acc = 0.642264
I0606 01:04:50.006482 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.349641 (* 1 = 0.349641 loss)
I0606 01:04:56.146618 54715 solver.cpp:237] Iteration 2301, loss = 0.315328
I0606 01:04:56.146678 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.295061 (* 1 = 0.295061 loss)
I0606 01:04:56.146690 54715 sgd_solver.cpp:106] Iteration 2301, lr = 0.00963011
I0606 01:05:04.946100 54715 softmax_loss_layer.cu:194] weight loss 0 =0.150239 weight loss 1 =1 weight loss 2 =0
I0606 01:05:05.524772 54715 solver.cpp:237] Iteration 2304, loss = 0.317679
I0606 01:05:05.524817 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.298621 (* 1 = 0.298621 loss)
I0606 01:05:05.524828 54715 sgd_solver.cpp:106] Iteration 2304, lr = 0.00962963
I0606 01:05:14.901258 54715 solver.cpp:237] Iteration 2307, loss = 0.314822
I0606 01:05:14.901311 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.290178 (* 1 = 0.290178 loss)
I0606 01:05:14.901324 54715 sgd_solver.cpp:106] Iteration 2307, lr = 0.00962914
I0606 01:05:21.260372 54715 solver.cpp:341] Iteration 2310, Testing net (#0)
I0606 01:05:22.545409 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848948
I0606 01:05:22.545456 54715 solver.cpp:409] Test net output #1: class_Acc = 0.853808
I0606 01:05:22.545464 54715 solver.cpp:409] Test net output #2: class_Acc = 0.834233
I0606 01:05:22.545473 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.33907 (* 1 = 0.33907 loss)
I0606 01:05:25.559420 54715 solver.cpp:237] Iteration 2310, loss = 0.314648
I0606 01:05:25.559470 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.291006 (* 1 = 0.291006 loss)
I0606 01:05:25.559482 54715 sgd_solver.cpp:106] Iteration 2310, lr = 0.00962866
I0606 01:05:34.935703 54715 solver.cpp:237] Iteration 2313, loss = 0.315818
I0606 01:05:34.935753 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.281429 (* 1 = 0.281429 loss)
I0606 01:05:34.935765 54715 sgd_solver.cpp:106] Iteration 2313, lr = 0.00962817
I0606 01:05:44.311683 54715 solver.cpp:237] Iteration 2316, loss = 0.315986
I0606 01:05:44.311735 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326605 (* 1 = 0.326605 loss)
I0606 01:05:44.311748 54715 sgd_solver.cpp:106] Iteration 2316, lr = 0.00962769
I0606 01:05:53.499416 54715 softmax_loss_layer.cu:194] weight loss 0 =0.348128 weight loss 1 =1 weight loss 2 =0
I0606 01:05:53.688961 54715 solver.cpp:237] Iteration 2319, loss = 0.312864
I0606 01:05:53.689010 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.255736 (* 1 = 0.255736 loss)
I0606 01:05:53.689020 54715 sgd_solver.cpp:106] Iteration 2319, lr = 0.00962721
I0606 01:05:53.798512 54715 solver.cpp:341] Iteration 2320, Testing net (#0)
I0606 01:05:55.082793 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.853942
I0606 01:05:55.082835 54715 solver.cpp:409] Test net output #1: class_Acc = 0.892859
I0606 01:05:55.082841 54715 solver.cpp:409] Test net output #2: class_Acc = 0.761248
I0606 01:05:55.082852 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.327856 (* 1 = 0.327856 loss)
I0606 01:06:04.350240 54715 solver.cpp:237] Iteration 2322, loss = 0.312637
I0606 01:06:04.350293 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.316057 (* 1 = 0.316057 loss)
I0606 01:06:04.350304 54715 sgd_solver.cpp:106] Iteration 2322, lr = 0.00962672
I0606 01:06:13.725958 54715 solver.cpp:237] Iteration 2325, loss = 0.314129
I0606 01:06:13.726011 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.322522 (* 1 = 0.322522 loss)
I0606 01:06:13.726022 54715 sgd_solver.cpp:106] Iteration 2325, lr = 0.00962624
I0606 01:06:23.097607 54715 solver.cpp:237] Iteration 2328, loss = 0.315069
I0606 01:06:23.097659 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.344623 (* 1 = 0.344623 loss)
I0606 01:06:23.097671 54715 sgd_solver.cpp:106] Iteration 2328, lr = 0.00962575
I0606 01:06:26.334681 54715 solver.cpp:341] Iteration 2330, Testing net (#0)
I0606 01:06:27.620106 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.862863
I0606 01:06:27.620169 54715 solver.cpp:409] Test net output #1: class_Acc = 0.880178
I0606 01:06:27.620189 54715 solver.cpp:409] Test net output #2: class_Acc = 0.815898
I0606 01:06:27.620200 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.308196 (* 1 = 0.308196 loss)
I0606 01:06:33.762025 54715 solver.cpp:237] Iteration 2331, loss = 0.317109
I0606 01:06:33.762078 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.298683 (* 1 = 0.298683 loss)
I0606 01:06:33.762089 54715 sgd_solver.cpp:106] Iteration 2331, lr = 0.00962527
I0606 01:06:43.136232 54715 solver.cpp:237] Iteration 2334, loss = 0.318761
I0606 01:06:43.136281 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327043 (* 1 = 0.327043 loss)
I0606 01:06:43.136293 54715 sgd_solver.cpp:106] Iteration 2334, lr = 0.00962478
I0606 01:06:52.510471 54715 solver.cpp:237] Iteration 2337, loss = 0.321146
I0606 01:06:52.510522 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3243 (* 1 = 0.3243 loss)
I0606 01:06:52.510532 54715 sgd_solver.cpp:106] Iteration 2337, lr = 0.0096243
I0606 01:06:58.571815 54715 softmax_loss_layer.cu:194] weight loss 0 =0.331814 weight loss 1 =1 weight loss 2 =0
I0606 01:06:58.871053 54715 solver.cpp:341] Iteration 2340, Testing net (#0)
I0606 01:07:00.155712 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.852969
I0606 01:07:00.155757 54715 solver.cpp:409] Test net output #1: class_Acc = 0.912541
I0606 01:07:00.155766 54715 solver.cpp:409] Test net output #2: class_Acc = 0.698524
I0606 01:07:00.155776 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.327145 (* 1 = 0.327145 loss)
I0606 01:07:03.168671 54715 solver.cpp:237] Iteration 2340, loss = 0.320889
I0606 01:07:03.168725 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.293562 (* 1 = 0.293562 loss)
I0606 01:07:03.168736 54715 sgd_solver.cpp:106] Iteration 2340, lr = 0.00962381
I0606 01:07:12.544836 54715 solver.cpp:237] Iteration 2343, loss = 0.319999
I0606 01:07:12.544896 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.307312 (* 1 = 0.307312 loss)
I0606 01:07:12.545686 54715 sgd_solver.cpp:106] Iteration 2343, lr = 0.00962333
I0606 01:07:21.928216 54715 solver.cpp:237] Iteration 2346, loss = 0.317812
I0606 01:07:21.928261 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321756 (* 1 = 0.321756 loss)
I0606 01:07:21.928270 54715 sgd_solver.cpp:106] Iteration 2346, lr = 0.00962284
I0606 01:07:31.301594 54715 solver.cpp:237] Iteration 2349, loss = 0.315404
I0606 01:07:31.301661 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.285959 (* 1 = 0.285959 loss)
I0606 01:07:31.301673 54715 sgd_solver.cpp:106] Iteration 2349, lr = 0.00962236
I0606 01:07:31.411041 54715 solver.cpp:341] Iteration 2350, Testing net (#0)
I0606 01:07:32.696466 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.855279
I0606 01:07:32.696511 54715 solver.cpp:409] Test net output #1: class_Acc = 0.876306
I0606 01:07:32.696518 54715 solver.cpp:409] Test net output #2: class_Acc = 0.804919
I0606 01:07:32.696528 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.321411 (* 1 = 0.321411 loss)
I0606 01:07:41.960801 54715 solver.cpp:237] Iteration 2352, loss = 0.311744
I0606 01:07:41.960856 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.354832 (* 1 = 0.354832 loss)
I0606 01:07:41.960867 54715 sgd_solver.cpp:106] Iteration 2352, lr = 0.00962188
I0606 01:07:51.334811 54715 solver.cpp:237] Iteration 2355, loss = 0.311944
I0606 01:07:51.334861 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.281533 (* 1 = 0.281533 loss)
I0606 01:07:51.334872 54715 sgd_solver.cpp:106] Iteration 2355, lr = 0.00962139
I0606 01:08:00.708734 54715 solver.cpp:237] Iteration 2358, loss = 0.309421
I0606 01:08:00.708786 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.301608 (* 1 = 0.301608 loss)
I0606 01:08:00.708796 54715 sgd_solver.cpp:106] Iteration 2358, lr = 0.00962091
I0606 01:08:03.944526 54715 solver.cpp:341] Iteration 2360, Testing net (#0)
I0606 01:08:05.229666 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.860395
I0606 01:08:05.229713 54715 solver.cpp:409] Test net output #1: class_Acc = 0.867179
I0606 01:08:05.229719 54715 solver.cpp:409] Test net output #2: class_Acc = 0.8343
I0606 01:08:05.229729 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.31465 (* 1 = 0.31465 loss)
I0606 01:08:11.367797 54715 solver.cpp:237] Iteration 2361, loss = 0.304046
I0606 01:08:11.367851 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305083 (* 1 = 0.305083 loss)
I0606 01:08:11.367862 54715 sgd_solver.cpp:106] Iteration 2361, lr = 0.00962042
I0606 01:08:20.742954 54715 solver.cpp:237] Iteration 2364, loss = 0.305683
I0606 01:08:20.743011 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.299948 (* 1 = 0.299948 loss)
I0606 01:08:20.743022 54715 sgd_solver.cpp:106] Iteration 2364, lr = 0.00961994
I0606 01:08:30.118635 54715 solver.cpp:237] Iteration 2367, loss = 0.306068
I0606 01:08:30.118690 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.319999 (* 1 = 0.319999 loss)
I0606 01:08:30.118700 54715 sgd_solver.cpp:106] Iteration 2367, lr = 0.00961945
I0606 01:08:36.477282 54715 solver.cpp:341] Iteration 2370, Testing net (#0)
I0606 01:08:37.760951 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.857113
I0606 01:08:37.760996 54715 solver.cpp:409] Test net output #1: class_Acc = 0.889025
I0606 01:08:37.761003 54715 solver.cpp:409] Test net output #2: class_Acc = 0.772616
I0606 01:08:37.761013 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.318898 (* 1 = 0.318898 loss)
I0606 01:08:40.778996 54715 solver.cpp:237] Iteration 2370, loss = 0.302858
I0606 01:08:40.779047 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31242 (* 1 = 0.31242 loss)
I0606 01:08:40.779058 54715 sgd_solver.cpp:106] Iteration 2370, lr = 0.00961897
I0606 01:08:50.154937 54715 solver.cpp:237] Iteration 2373, loss = 0.306219
I0606 01:08:50.154992 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.273475 (* 1 = 0.273475 loss)
I0606 01:08:50.155004 54715 sgd_solver.cpp:106] Iteration 2373, lr = 0.00961848
I0606 01:08:59.532351 54715 solver.cpp:237] Iteration 2376, loss = 0.308809
I0606 01:08:59.532403 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368646 (* 1 = 0.368646 loss)
I0606 01:08:59.532413 54715 sgd_solver.cpp:106] Iteration 2376, lr = 0.009618
I0606 01:09:08.904651 54715 solver.cpp:237] Iteration 2379, loss = 0.307733
I0606 01:09:08.904753 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292241 (* 1 = 0.292241 loss)
I0606 01:09:08.904764 54715 sgd_solver.cpp:106] Iteration 2379, lr = 0.00961751
I0606 01:09:09.014199 54715 solver.cpp:341] Iteration 2380, Testing net (#0)
I0606 01:09:10.297974 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.856281
I0606 01:09:10.298020 54715 solver.cpp:409] Test net output #1: class_Acc = 0.860832
I0606 01:09:10.298027 54715 solver.cpp:409] Test net output #2: class_Acc = 0.838882
I0606 01:09:10.298036 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.322617 (* 1 = 0.322617 loss)
I0606 01:09:19.558293 54715 solver.cpp:237] Iteration 2382, loss = 0.309655
I0606 01:09:19.558342 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.332277 (* 1 = 0.332277 loss)
I0606 01:09:19.558352 54715 sgd_solver.cpp:106] Iteration 2382, lr = 0.00961703
I0606 01:09:28.931279 54715 solver.cpp:237] Iteration 2385, loss = 0.311908
I0606 01:09:28.931334 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.306128 (* 1 = 0.306128 loss)
I0606 01:09:28.931346 54715 sgd_solver.cpp:106] Iteration 2385, lr = 0.00961654
I0606 01:09:38.305027 54715 solver.cpp:237] Iteration 2388, loss = 0.308329
I0606 01:09:38.305068 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.237839 (* 1 = 0.237839 loss)
I0606 01:09:38.305078 54715 sgd_solver.cpp:106] Iteration 2388, lr = 0.00961606
I0606 01:09:41.539918 54715 solver.cpp:341] Iteration 2390, Testing net (#0)
I0606 01:09:42.825037 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.854291
I0606 01:09:42.825083 54715 solver.cpp:409] Test net output #1: class_Acc = 0.881046
I0606 01:09:42.825089 54715 solver.cpp:409] Test net output #2: class_Acc = 0.782788
I0606 01:09:42.825099 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.326266 (* 1 = 0.326266 loss)
I0606 01:09:48.966786 54715 solver.cpp:237] Iteration 2391, loss = 0.308612
I0606 01:09:48.966836 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310534 (* 1 = 0.310534 loss)
I0606 01:09:48.966847 54715 sgd_solver.cpp:106] Iteration 2391, lr = 0.00961557
I0606 01:09:58.339264 54715 solver.cpp:237] Iteration 2394, loss = 0.30853
I0606 01:09:58.339313 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318778 (* 1 = 0.318778 loss)
I0606 01:09:58.339323 54715 sgd_solver.cpp:106] Iteration 2394, lr = 0.00961509
I0606 01:10:07.716188 54715 solver.cpp:237] Iteration 2397, loss = 0.309048
I0606 01:10:07.716238 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.268767 (* 1 = 0.268767 loss)
I0606 01:10:07.716249 54715 sgd_solver.cpp:106] Iteration 2397, lr = 0.0096146
I0606 01:10:14.075803 54715 solver.cpp:341] Iteration 2400, Testing net (#0)
I0606 01:10:15.359985 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.864205
I0606 01:10:15.360035 54715 solver.cpp:409] Test net output #1: class_Acc = 0.890001
I0606 01:10:15.360043 54715 solver.cpp:409] Test net output #2: class_Acc = 0.799279
I0606 01:10:15.360052 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.309294 (* 1 = 0.309294 loss)
I0606 01:10:18.372762 54715 solver.cpp:237] Iteration 2400, loss = 0.306628
I0606 01:10:18.372809 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.276084 (* 1 = 0.276084 loss)
I0606 01:10:18.372819 54715 sgd_solver.cpp:106] Iteration 2400, lr = 0.00961412
I0606 01:10:22.099061 54715 softmax_loss_layer.cu:194] weight loss 0 =0.312841 weight loss 1 =1 weight loss 2 =0
I0606 01:10:27.745033 54715 solver.cpp:237] Iteration 2403, loss = 0.30898
I0606 01:10:27.745077 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.369755 (* 1 = 0.369755 loss)
I0606 01:10:27.745088 54715 sgd_solver.cpp:106] Iteration 2403, lr = 0.00961364
I0606 01:10:37.119241 54715 solver.cpp:237] Iteration 2406, loss = 0.313689
I0606 01:10:37.119292 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311747 (* 1 = 0.311747 loss)
I0606 01:10:37.119304 54715 sgd_solver.cpp:106] Iteration 2406, lr = 0.00961315
I0606 01:10:46.495630 54715 solver.cpp:237] Iteration 2409, loss = 0.314757
I0606 01:10:46.495731 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.285271 (* 1 = 0.285271 loss)
I0606 01:10:46.495743 54715 sgd_solver.cpp:106] Iteration 2409, lr = 0.00961267
I0606 01:10:46.605104 54715 solver.cpp:341] Iteration 2410, Testing net (#0)
I0606 01:10:47.890292 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.829677
I0606 01:10:47.890337 54715 solver.cpp:409] Test net output #1: class_Acc = 0.840097
I0606 01:10:47.890344 54715 solver.cpp:409] Test net output #2: class_Acc = 0.799332
I0606 01:10:47.890354 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.380361 (* 1 = 0.380361 loss)
I0606 01:10:57.154074 54715 solver.cpp:237] Iteration 2412, loss = 0.314002
I0606 01:10:57.154122 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.344556 (* 1 = 0.344556 loss)
I0606 01:10:57.154134 54715 sgd_solver.cpp:106] Iteration 2412, lr = 0.00961218
I0606 01:11:06.529965 54715 solver.cpp:237] Iteration 2415, loss = 0.314162
I0606 01:11:06.530017 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286539 (* 1 = 0.286539 loss)
I0606 01:11:06.530028 54715 sgd_solver.cpp:106] Iteration 2415, lr = 0.0096117
I0606 01:11:15.903707 54715 solver.cpp:237] Iteration 2418, loss = 0.316395
I0606 01:11:15.903754 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.304598 (* 1 = 0.304598 loss)
I0606 01:11:15.903774 54715 sgd_solver.cpp:106] Iteration 2418, lr = 0.00961121
I0606 01:11:19.137112 54715 solver.cpp:341] Iteration 2420, Testing net (#0)
I0606 01:11:20.420641 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.838754
I0606 01:11:20.420683 54715 solver.cpp:409] Test net output #1: class_Acc = 0.856958
I0606 01:11:20.420691 54715 solver.cpp:409] Test net output #2: class_Acc = 0.78841
I0606 01:11:20.420699 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.363193 (* 1 = 0.363193 loss)
I0606 01:11:26.560154 54715 solver.cpp:237] Iteration 2421, loss = 0.318088
I0606 01:11:26.560200 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.264338 (* 1 = 0.264338 loss)
I0606 01:11:26.560210 54715 sgd_solver.cpp:106] Iteration 2421, lr = 0.00961073
I0606 01:11:32.230530 54715 softmax_loss_layer.cu:194] weight loss 0 =0.389183 weight loss 1 =1 weight loss 2 =0
I0606 01:11:35.935636 54715 solver.cpp:237] Iteration 2424, loss = 0.314486
I0606 01:11:35.935684 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.35134 (* 1 = 0.35134 loss)
I0606 01:11:35.935695 54715 sgd_solver.cpp:106] Iteration 2424, lr = 0.00961024
I0606 01:11:45.310416 54715 solver.cpp:237] Iteration 2427, loss = 0.316069
I0606 01:11:45.310477 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.362456 (* 1 = 0.362456 loss)
I0606 01:11:45.310493 54715 sgd_solver.cpp:106] Iteration 2427, lr = 0.00960976
I0606 01:11:51.669625 54715 solver.cpp:341] Iteration 2430, Testing net (#0)
I0606 01:11:52.953459 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.854709
I0606 01:11:52.953502 54715 solver.cpp:409] Test net output #1: class_Acc = 0.92287
I0606 01:11:52.953510 54715 solver.cpp:409] Test net output #2: class_Acc = 0.684283
I0606 01:11:52.953519 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.326057 (* 1 = 0.326057 loss)
I0606 01:11:55.970336 54715 solver.cpp:237] Iteration 2430, loss = 0.317631
I0606 01:11:55.970383 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.318242 (* 1 = 0.318242 loss)
I0606 01:11:55.970396 54715 sgd_solver.cpp:106] Iteration 2430, lr = 0.00960927
I0606 01:12:05.346096 54715 solver.cpp:237] Iteration 2433, loss = 0.315531
I0606 01:12:05.346144 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.301092 (* 1 = 0.301092 loss)
I0606 01:12:05.346155 54715 sgd_solver.cpp:106] Iteration 2433, lr = 0.00960879
I0606 01:12:14.719314 54715 solver.cpp:237] Iteration 2436, loss = 0.311713
I0606 01:12:14.719362 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305543 (* 1 = 0.305543 loss)
I0606 01:12:14.719372 54715 sgd_solver.cpp:106] Iteration 2436, lr = 0.0096083
I0606 01:12:24.095114 54715 solver.cpp:237] Iteration 2439, loss = 0.311668
I0606 01:12:24.095223 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.3038 (* 1 = 0.3038 loss)
I0606 01:12:24.095235 54715 sgd_solver.cpp:106] Iteration 2439, lr = 0.00960782
I0606 01:12:24.204571 54715 solver.cpp:341] Iteration 2440, Testing net (#0)
I0606 01:12:25.488464 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.855758
I0606 01:12:25.488512 54715 solver.cpp:409] Test net output #1: class_Acc = 0.902394
I0606 01:12:25.488517 54715 solver.cpp:409] Test net output #2: class_Acc = 0.753784
I0606 01:12:25.488528 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.32808 (* 1 = 0.32808 loss)
I0606 01:12:34.754385 54715 solver.cpp:237] Iteration 2442, loss = 0.310113
I0606 01:12:34.754437 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.255211 (* 1 = 0.255211 loss)
I0606 01:12:34.754448 54715 sgd_solver.cpp:106] Iteration 2442, lr = 0.00960733
I0606 01:12:44.131868 54715 solver.cpp:237] Iteration 2445, loss = 0.307721
I0606 01:12:44.131911 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305136 (* 1 = 0.305136 loss)
I0606 01:12:44.131922 54715 sgd_solver.cpp:106] Iteration 2445, lr = 0.00960685
I0606 01:12:53.507688 54715 solver.cpp:237] Iteration 2448, loss = 0.304703
I0606 01:12:53.507750 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.247068 (* 1 = 0.247068 loss)
I0606 01:12:53.507762 54715 sgd_solver.cpp:106] Iteration 2448, lr = 0.00960636
I0606 01:12:56.741706 54715 solver.cpp:341] Iteration 2450, Testing net (#0)
I0606 01:12:58.025110 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.858173
I0606 01:12:58.025154 54715 solver.cpp:409] Test net output #1: class_Acc = 0.898783
I0606 01:12:58.025161 54715 solver.cpp:409] Test net output #2: class_Acc = 0.755971
I0606 01:12:58.025171 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.320687 (* 1 = 0.320687 loss)
I0606 01:13:04.166970 54715 solver.cpp:237] Iteration 2451, loss = 0.307392
I0606 01:13:04.167019 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.283144 (* 1 = 0.283144 loss)
I0606 01:13:04.167029 54715 sgd_solver.cpp:106] Iteration 2451, lr = 0.00960588
I0606 01:13:13.541616 54715 solver.cpp:237] Iteration 2454, loss = 0.304516
I0606 01:13:13.541661 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.262464 (* 1 = 0.262464 loss)
I0606 01:13:13.541671 54715 sgd_solver.cpp:106] Iteration 2454, lr = 0.00960539
I0606 01:13:21.947235 54715 softmax_loss_layer.cu:194] weight loss 0 =0.285508 weight loss 1 =1 weight loss 2 =0
I0606 01:13:22.914474 54715 solver.cpp:237] Iteration 2457, loss = 0.304132
I0606 01:13:22.914522 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.297825 (* 1 = 0.297825 loss)
I0606 01:13:22.914533 54715 sgd_solver.cpp:106] Iteration 2457, lr = 0.00960491
I0606 01:13:29.273759 54715 solver.cpp:341] Iteration 2460, Testing net (#0)
I0606 01:13:30.557615 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.853951
I0606 01:13:30.557653 54715 solver.cpp:409] Test net output #1: class_Acc = 0.925093
I0606 01:13:30.557660 54715 solver.cpp:409] Test net output #2: class_Acc = 0.688736
I0606 01:13:30.557670 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.324794 (* 1 = 0.324794 loss)
I0606 01:13:33.571491 54715 solver.cpp:237] Iteration 2460, loss = 0.303007
I0606 01:13:33.571534 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292457 (* 1 = 0.292457 loss)
I0606 01:13:33.571545 54715 sgd_solver.cpp:106] Iteration 2460, lr = 0.00960442
I0606 01:13:42.947216 54715 solver.cpp:237] Iteration 2463, loss = 0.307436
I0606 01:13:42.947263 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.331012 (* 1 = 0.331012 loss)
I0606 01:13:42.947273 54715 sgd_solver.cpp:106] Iteration 2463, lr = 0.00960394
I0606 01:13:52.324820 54715 solver.cpp:237] Iteration 2466, loss = 0.306909
I0606 01:13:52.324870 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.30314 (* 1 = 0.30314 loss)
I0606 01:13:52.324880 54715 sgd_solver.cpp:106] Iteration 2466, lr = 0.00960345
I0606 01:14:01.703831 54715 solver.cpp:237] Iteration 2469, loss = 0.305971
I0606 01:14:01.703896 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.265312 (* 1 = 0.265312 loss)
I0606 01:14:01.703908 54715 sgd_solver.cpp:106] Iteration 2469, lr = 0.00960297
I0606 01:14:01.813300 54715 solver.cpp:341] Iteration 2470, Testing net (#0)
I0606 01:14:03.097262 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.861779
I0606 01:14:03.097301 54715 solver.cpp:409] Test net output #1: class_Acc = 0.906337
I0606 01:14:03.097309 54715 solver.cpp:409] Test net output #2: class_Acc = 0.752188
I0606 01:14:03.097319 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.314112 (* 1 = 0.314112 loss)
I0606 01:14:12.361768 54715 solver.cpp:237] Iteration 2472, loss = 0.308016
I0606 01:14:12.361817 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.355549 (* 1 = 0.355549 loss)
I0606 01:14:12.361829 54715 sgd_solver.cpp:106] Iteration 2472, lr = 0.00960248
I0606 01:14:21.734773 54715 solver.cpp:237] Iteration 2475, loss = 0.313874
I0606 01:14:21.734825 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.27005 (* 1 = 0.27005 loss)
I0606 01:14:21.734846 54715 sgd_solver.cpp:106] Iteration 2475, lr = 0.009602
I0606 01:14:31.113035 54715 solver.cpp:237] Iteration 2478, loss = 0.312752
I0606 01:14:31.113088 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.242474 (* 1 = 0.242474 loss)
I0606 01:14:31.113099 54715 sgd_solver.cpp:106] Iteration 2478, lr = 0.00960151
I0606 01:14:34.349887 54715 solver.cpp:341] Iteration 2480, Testing net (#0)
I0606 01:14:35.634712 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.845994
I0606 01:14:35.634757 54715 solver.cpp:409] Test net output #1: class_Acc = 0.846251
I0606 01:14:35.634764 54715 solver.cpp:409] Test net output #2: class_Acc = 0.839988
I0606 01:14:35.634773 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.341122 (* 1 = 0.341122 loss)
I0606 01:14:41.772897 54715 solver.cpp:237] Iteration 2481, loss = 0.311392
I0606 01:14:41.772946 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.284178 (* 1 = 0.284178 loss)
I0606 01:14:41.772956 54715 sgd_solver.cpp:106] Iteration 2481, lr = 0.00960103
I0606 01:14:51.149014 54715 solver.cpp:237] Iteration 2484, loss = 0.312222
I0606 01:14:51.149062 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.309436 (* 1 = 0.309436 loss)
I0606 01:14:51.149072 54715 sgd_solver.cpp:106] Iteration 2484, lr = 0.00960055
I0606 01:15:00.522028 54715 solver.cpp:237] Iteration 2487, loss = 0.309721
I0606 01:15:00.522074 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.261108 (* 1 = 0.261108 loss)
I0606 01:15:00.522085 54715 sgd_solver.cpp:106] Iteration 2487, lr = 0.00960006
I0606 01:15:06.879303 54715 solver.cpp:341] Iteration 2490, Testing net (#0)
I0606 01:15:08.164069 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.865335
I0606 01:15:08.164114 54715 solver.cpp:409] Test net output #1: class_Acc = 0.876557
I0606 01:15:08.164121 54715 solver.cpp:409] Test net output #2: class_Acc = 0.83257
I0606 01:15:08.164131 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.308579 (* 1 = 0.308579 loss)
I0606 01:15:11.178308 54715 solver.cpp:237] Iteration 2490, loss = 0.309035
I0606 01:15:11.178359 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.240242 (* 1 = 0.240242 loss)
I0606 01:15:11.178371 54715 sgd_solver.cpp:106] Iteration 2490, lr = 0.00959957
I0606 01:15:20.551961 54715 solver.cpp:237] Iteration 2493, loss = 0.309115
I0606 01:15:20.552013 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.376572 (* 1 = 0.376572 loss)
I0606 01:15:20.552024 54715 sgd_solver.cpp:106] Iteration 2493, lr = 0.00959909
I0606 01:15:29.927774 54715 solver.cpp:237] Iteration 2496, loss = 0.310376
I0606 01:15:29.927825 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.27587 (* 1 = 0.27587 loss)
I0606 01:15:29.927835 54715 sgd_solver.cpp:106] Iteration 2496, lr = 0.00959861
I0606 01:15:39.302469 54715 solver.cpp:237] Iteration 2499, loss = 0.311008
I0606 01:15:39.302534 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.30021 (* 1 = 0.30021 loss)
I0606 01:15:39.302546 54715 sgd_solver.cpp:106] Iteration 2499, lr = 0.00959812
I0606 01:15:39.411911 54715 solver.cpp:341] Iteration 2500, Testing net (#0)
I0606 01:15:40.695842 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.831183
I0606 01:15:40.695888 54715 solver.cpp:409] Test net output #1: class_Acc = 0.829903
I0606 01:15:40.695895 54715 solver.cpp:409] Test net output #2: class_Acc = 0.830908
I0606 01:15:40.695904 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.382683 (* 1 = 0.382683 loss)
I0606 01:15:45.088641 54715 softmax_loss_layer.cu:194] weight loss 0 =0.249396 weight loss 1 =1 weight loss 2 =0
I0606 01:15:49.959116 54715 solver.cpp:237] Iteration 2502, loss = 0.312925
I0606 01:15:49.959163 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.338237 (* 1 = 0.338237 loss)
I0606 01:15:49.959174 54715 sgd_solver.cpp:106] Iteration 2502, lr = 0.00959763
I0606 01:15:59.332677 54715 solver.cpp:237] Iteration 2505, loss = 0.309379
I0606 01:15:59.332726 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.28989 (* 1 = 0.28989 loss)
I0606 01:15:59.332736 54715 sgd_solver.cpp:106] Iteration 2505, lr = 0.00959715
I0606 01:16:08.705319 54715 solver.cpp:237] Iteration 2508, loss = 0.309806
I0606 01:16:08.705370 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.271663 (* 1 = 0.271663 loss)
I0606 01:16:08.705381 54715 sgd_solver.cpp:106] Iteration 2508, lr = 0.00959667
I0606 01:16:11.939692 54715 solver.cpp:341] Iteration 2510, Testing net (#0)
I0606 01:16:13.224493 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.841325
I0606 01:16:13.224534 54715 solver.cpp:409] Test net output #1: class_Acc = 0.836969
I0606 01:16:13.224542 54715 solver.cpp:409] Test net output #2: class_Acc = 0.846811
I0606 01:16:13.224552 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.352708 (* 1 = 0.352708 loss)
I0606 01:16:19.365620 54715 solver.cpp:237] Iteration 2511, loss = 0.307265
I0606 01:16:19.365665 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321167 (* 1 = 0.321167 loss)
I0606 01:16:19.365676 54715 sgd_solver.cpp:106] Iteration 2511, lr = 0.00959618
I0606 01:16:26.996281 54715 softmax_loss_layer.cu:194] weight loss 0 =0.454079 weight loss 1 =1 weight loss 2 =0
I0606 01:16:28.742151 54715 solver.cpp:237] Iteration 2514, loss = 0.305717
I0606 01:16:28.742202 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.283087 (* 1 = 0.283087 loss)
I0606 01:16:28.742213 54715 sgd_solver.cpp:106] Iteration 2514, lr = 0.0095957
I0606 01:16:38.113119 54715 solver.cpp:237] Iteration 2517, loss = 0.304812
I0606 01:16:38.113171 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327276 (* 1 = 0.327276 loss)
I0606 01:16:38.113181 54715 sgd_solver.cpp:106] Iteration 2517, lr = 0.00959521
I0606 01:16:44.470857 54715 solver.cpp:341] Iteration 2520, Testing net (#0)
I0606 01:16:45.754542 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.840044
I0606 01:16:45.754587 54715 solver.cpp:409] Test net output #1: class_Acc = 0.864779
I0606 01:16:45.754595 54715 solver.cpp:409] Test net output #2: class_Acc = 0.77776
I0606 01:16:45.754604 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.360473 (* 1 = 0.360473 loss)
I0606 01:16:48.768997 54715 solver.cpp:237] Iteration 2520, loss = 0.301938
I0606 01:16:48.769052 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305934 (* 1 = 0.305934 loss)
I0606 01:16:48.769062 54715 sgd_solver.cpp:106] Iteration 2520, lr = 0.00959473
I0606 01:16:58.144659 54715 solver.cpp:237] Iteration 2523, loss = 0.300642
I0606 01:16:58.144711 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.272553 (* 1 = 0.272553 loss)
I0606 01:16:58.144721 54715 sgd_solver.cpp:106] Iteration 2523, lr = 0.00959424
I0606 01:17:04.202805 54715 softmax_loss_layer.cu:194] weight loss 0 =0.234142 weight loss 1 =1 weight loss 2 =0
I0606 01:17:07.517005 54715 solver.cpp:237] Iteration 2526, loss = 0.3032
I0606 01:17:07.517057 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311125 (* 1 = 0.311125 loss)
I0606 01:17:07.517067 54715 sgd_solver.cpp:106] Iteration 2526, lr = 0.00959376
I0606 01:17:16.888943 54715 solver.cpp:237] Iteration 2529, loss = 0.305554
I0606 01:17:16.889057 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.366082 (* 1 = 0.366082 loss)
I0606 01:17:16.889070 54715 sgd_solver.cpp:106] Iteration 2529, lr = 0.00959327
I0606 01:17:16.998414 54715 solver.cpp:341] Iteration 2530, Testing net (#0)
I0606 01:17:18.282899 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.867858
I0606 01:17:18.282943 54715 solver.cpp:409] Test net output #1: class_Acc = 0.89633
I0606 01:17:18.282950 54715 solver.cpp:409] Test net output #2: class_Acc = 0.793266
I0606 01:17:18.282960 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.300346 (* 1 = 0.300346 loss)
I0606 01:17:27.547205 54715 solver.cpp:237] Iteration 2532, loss = 0.304793
I0606 01:17:27.547258 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.326365 (* 1 = 0.326365 loss)
I0606 01:17:27.547271 54715 sgd_solver.cpp:106] Iteration 2532, lr = 0.00959279
I0606 01:17:36.924690 54715 solver.cpp:237] Iteration 2535, loss = 0.306208
I0606 01:17:36.924738 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.317803 (* 1 = 0.317803 loss)
I0606 01:17:36.924751 54715 sgd_solver.cpp:106] Iteration 2535, lr = 0.0095923
I0606 01:17:42.983835 54715 softmax_loss_layer.cu:194] weight loss 0 =0.216441 weight loss 1 =1 weight loss 2 =0
I0606 01:17:46.297938 54715 solver.cpp:237] Iteration 2538, loss = 0.305827
I0606 01:17:46.297989 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.331967 (* 1 = 0.331967 loss)
I0606 01:17:46.297999 54715 sgd_solver.cpp:106] Iteration 2538, lr = 0.00959182
I0606 01:17:49.532845 54715 solver.cpp:341] Iteration 2540, Testing net (#0)
I0606 01:17:50.816802 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.85312
I0606 01:17:50.816845 54715 solver.cpp:409] Test net output #1: class_Acc = 0.869651
I0606 01:17:50.816854 54715 solver.cpp:409] Test net output #2: class_Acc = 0.807582
I0606 01:17:50.816864 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.329674 (* 1 = 0.329674 loss)
I0606 01:17:56.959940 54715 solver.cpp:237] Iteration 2541, loss = 0.305829
I0606 01:17:56.959990 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.242937 (* 1 = 0.242937 loss)
I0606 01:17:56.960000 54715 sgd_solver.cpp:106] Iteration 2541, lr = 0.00959133
I0606 01:18:06.333171 54715 solver.cpp:237] Iteration 2544, loss = 0.304483
I0606 01:18:06.333220 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.302961 (* 1 = 0.302961 loss)
I0606 01:18:06.333230 54715 sgd_solver.cpp:106] Iteration 2544, lr = 0.00959085
I0606 01:18:15.707348 54715 solver.cpp:237] Iteration 2547, loss = 0.306439
I0606 01:18:15.707396 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.28004 (* 1 = 0.28004 loss)
I0606 01:18:15.707406 54715 sgd_solver.cpp:106] Iteration 2547, lr = 0.00959036
I0606 01:18:22.065639 54715 solver.cpp:341] Iteration 2550, Testing net (#0)
I0606 01:18:23.350229 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.863341
I0606 01:18:23.350271 54715 solver.cpp:409] Test net output #1: class_Acc = 0.897825
I0606 01:18:23.350278 54715 solver.cpp:409] Test net output #2: class_Acc = 0.777975
I0606 01:18:23.350288 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.309545 (* 1 = 0.309545 loss)
I0606 01:18:24.230005 54715 softmax_loss_layer.cu:194] weight loss 0 =0.245421 weight loss 1 =1 weight loss 2 =0
I0606 01:18:26.366731 54715 solver.cpp:237] Iteration 2550, loss = 0.30347
I0606 01:18:26.366780 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.26126 (* 1 = 0.26126 loss)
I0606 01:18:26.366791 54715 sgd_solver.cpp:106] Iteration 2550, lr = 0.00958988
I0606 01:18:35.743734 54715 solver.cpp:237] Iteration 2553, loss = 0.301881
I0606 01:18:35.743782 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.275347 (* 1 = 0.275347 loss)
I0606 01:18:35.743793 54715 sgd_solver.cpp:106] Iteration 2553, lr = 0.00958939
I0606 01:18:45.117604 54715 solver.cpp:237] Iteration 2556, loss = 0.300459
I0606 01:18:45.117638 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.322175 (* 1 = 0.322175 loss)
I0606 01:18:45.117648 54715 sgd_solver.cpp:106] Iteration 2556, lr = 0.00958891
I0606 01:18:54.493470 54715 solver.cpp:237] Iteration 2559, loss = 0.303323
I0606 01:18:54.493536 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.277436 (* 1 = 0.277436 loss)
I0606 01:18:54.493548 54715 sgd_solver.cpp:106] Iteration 2559, lr = 0.00958842
I0606 01:18:54.602911 54715 solver.cpp:341] Iteration 2560, Testing net (#0)
I0606 01:18:55.887902 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.864467
I0606 01:18:55.887948 54715 solver.cpp:409] Test net output #1: class_Acc = 0.890061
I0606 01:18:55.887967 54715 solver.cpp:409] Test net output #2: class_Acc = 0.80854
I0606 01:18:55.887979 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.307737 (* 1 = 0.307737 loss)
I0606 01:19:05.151058 54715 solver.cpp:237] Iteration 2562, loss = 0.302066
I0606 01:19:05.151106 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.32232 (* 1 = 0.32232 loss)
I0606 01:19:05.151116 54715 sgd_solver.cpp:106] Iteration 2562, lr = 0.00958794
I0606 01:19:14.525990 54715 solver.cpp:237] Iteration 2565, loss = 0.301991
I0606 01:19:14.526036 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305615 (* 1 = 0.305615 loss)
I0606 01:19:14.526046 54715 sgd_solver.cpp:106] Iteration 2565, lr = 0.00958745
I0606 01:19:23.900383 54715 solver.cpp:237] Iteration 2568, loss = 0.305131
I0606 01:19:23.900439 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.290169 (* 1 = 0.290169 loss)
I0606 01:19:23.900449 54715 sgd_solver.cpp:106] Iteration 2568, lr = 0.00958696
I0606 01:19:27.135844 54715 solver.cpp:341] Iteration 2570, Testing net (#0)
I0606 01:19:28.420213 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.865869
I0606 01:19:28.420261 54715 solver.cpp:409] Test net output #1: class_Acc = 0.886965
I0606 01:19:28.420267 54715 solver.cpp:409] Test net output #2: class_Acc = 0.809595
I0606 01:19:28.420277 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.302113 (* 1 = 0.302113 loss)
I0606 01:19:34.558976 54715 solver.cpp:237] Iteration 2571, loss = 0.304883
I0606 01:19:34.559027 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.368775 (* 1 = 0.368775 loss)
I0606 01:19:34.559037 54715 sgd_solver.cpp:106] Iteration 2571, lr = 0.00958648
I0606 01:19:43.931107 54715 solver.cpp:237] Iteration 2574, loss = 0.306056
I0606 01:19:43.931156 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.302716 (* 1 = 0.302716 loss)
I0606 01:19:43.931167 54715 sgd_solver.cpp:106] Iteration 2574, lr = 0.00958599
I0606 01:19:53.305160 54715 solver.cpp:237] Iteration 2577, loss = 0.305493
I0606 01:19:53.305212 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310133 (* 1 = 0.310133 loss)
I0606 01:19:53.305224 54715 sgd_solver.cpp:106] Iteration 2577, lr = 0.00958551
I0606 01:19:59.662691 54715 solver.cpp:341] Iteration 2580, Testing net (#0)
I0606 01:20:00.947898 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.853454
I0606 01:20:00.947942 54715 solver.cpp:409] Test net output #1: class_Acc = 0.852935
I0606 01:20:00.947948 54715 solver.cpp:409] Test net output #2: class_Acc = 0.84693
I0606 01:20:00.947958 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.329916 (* 1 = 0.329916 loss)
I0606 01:20:03.960974 54715 solver.cpp:237] Iteration 2580, loss = 0.304953
I0606 01:20:03.961025 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.253964 (* 1 = 0.253964 loss)
I0606 01:20:03.961035 54715 sgd_solver.cpp:106] Iteration 2580, lr = 0.00958502
I0606 01:20:13.336865 54715 solver.cpp:237] Iteration 2583, loss = 0.304955
I0606 01:20:13.336920 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286087 (* 1 = 0.286087 loss)
I0606 01:20:13.336931 54715 sgd_solver.cpp:106] Iteration 2583, lr = 0.00958454
I0606 01:20:22.711542 54715 solver.cpp:237] Iteration 2586, loss = 0.305302
I0606 01:20:22.711591 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337772 (* 1 = 0.337772 loss)
I0606 01:20:22.711601 54715 sgd_solver.cpp:106] Iteration 2586, lr = 0.00958405
I0606 01:20:32.083487 54715 solver.cpp:237] Iteration 2589, loss = 0.305888
I0606 01:20:32.083551 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.301717 (* 1 = 0.301717 loss)
I0606 01:20:32.083562 54715 sgd_solver.cpp:106] Iteration 2589, lr = 0.00958357
I0606 01:20:32.192957 54715 solver.cpp:341] Iteration 2590, Testing net (#0)
I0606 01:20:33.479216 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.844967
I0606 01:20:33.479274 54715 solver.cpp:409] Test net output #1: class_Acc = 0.866372
I0606 01:20:33.479282 54715 solver.cpp:409] Test net output #2: class_Acc = 0.795837
I0606 01:20:33.479291 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.345003 (* 1 = 0.345003 loss)
I0606 01:20:42.742668 54715 solver.cpp:237] Iteration 2592, loss = 0.305634
I0606 01:20:42.742720 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.226774 (* 1 = 0.226774 loss)
I0606 01:20:42.742733 54715 sgd_solver.cpp:106] Iteration 2592, lr = 0.00958308
I0606 01:20:52.119362 54715 solver.cpp:237] Iteration 2595, loss = 0.306659
I0606 01:20:52.119408 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.283805 (* 1 = 0.283805 loss)
I0606 01:20:52.119419 54715 sgd_solver.cpp:106] Iteration 2595, lr = 0.0095826
I0606 01:21:01.492161 54715 solver.cpp:237] Iteration 2598, loss = 0.308059
I0606 01:21:01.492213 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.389562 (* 1 = 0.389562 loss)
I0606 01:21:01.492223 54715 sgd_solver.cpp:106] Iteration 2598, lr = 0.00958211
I0606 01:21:04.725917 54715 solver.cpp:341] Iteration 2600, Testing net (#0)
I0606 01:21:06.010272 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.848448
I0606 01:21:06.010314 54715 solver.cpp:409] Test net output #1: class_Acc = 0.85025
I0606 01:21:06.010321 54715 solver.cpp:409] Test net output #2: class_Acc = 0.841975
I0606 01:21:06.010331 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.337187 (* 1 = 0.337187 loss)
I0606 01:21:12.149961 54715 solver.cpp:237] Iteration 2601, loss = 0.306931
I0606 01:21:12.150013 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.289511 (* 1 = 0.289511 loss)
I0606 01:21:12.150024 54715 sgd_solver.cpp:106] Iteration 2601, lr = 0.00958163
I0606 01:21:21.526754 54715 solver.cpp:237] Iteration 2604, loss = 0.307428
I0606 01:21:21.526806 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334216 (* 1 = 0.334216 loss)
I0606 01:21:21.526818 54715 sgd_solver.cpp:106] Iteration 2604, lr = 0.00958114
I0606 01:21:30.903087 54715 solver.cpp:237] Iteration 2607, loss = 0.305445
I0606 01:21:30.903141 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.353842 (* 1 = 0.353842 loss)
I0606 01:21:30.903151 54715 sgd_solver.cpp:106] Iteration 2607, lr = 0.00958066
I0606 01:21:37.262943 54715 solver.cpp:341] Iteration 2610, Testing net (#0)
I0606 01:21:38.548635 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.845565
I0606 01:21:38.548681 54715 solver.cpp:409] Test net output #1: class_Acc = 0.851839
I0606 01:21:38.548689 54715 solver.cpp:409] Test net output #2: class_Acc = 0.830534
I0606 01:21:38.548698 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.340788 (* 1 = 0.340788 loss)
I0606 01:21:41.561961 54715 solver.cpp:237] Iteration 2610, loss = 0.305131
I0606 01:21:41.562013 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.272815 (* 1 = 0.272815 loss)
I0606 01:21:41.562024 54715 sgd_solver.cpp:106] Iteration 2610, lr = 0.00958017
I0606 01:21:50.934854 54715 solver.cpp:237] Iteration 2613, loss = 0.304124
I0606 01:21:50.934902 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.321288 (* 1 = 0.321288 loss)
I0606 01:21:50.934912 54715 sgd_solver.cpp:106] Iteration 2613, lr = 0.00957969
I0606 01:22:00.309566 54715 solver.cpp:237] Iteration 2616, loss = 0.301936
I0606 01:22:00.309622 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.304918 (* 1 = 0.304918 loss)
I0606 01:22:00.309633 54715 sgd_solver.cpp:106] Iteration 2616, lr = 0.0095792
I0606 01:22:09.683084 54715 solver.cpp:237] Iteration 2619, loss = 0.302029
I0606 01:22:09.683143 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311737 (* 1 = 0.311737 loss)
I0606 01:22:09.683156 54715 sgd_solver.cpp:106] Iteration 2619, lr = 0.00957872
I0606 01:22:09.792470 54715 solver.cpp:341] Iteration 2620, Testing net (#0)
I0606 01:22:11.077253 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.860355
I0606 01:22:11.077308 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893728
I0606 01:22:11.077316 54715 solver.cpp:409] Test net output #2: class_Acc = 0.787998
I0606 01:22:11.077327 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.317608 (* 1 = 0.317608 loss)
I0606 01:22:20.340363 54715 solver.cpp:237] Iteration 2622, loss = 0.299561
I0606 01:22:20.340412 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.309437 (* 1 = 0.309437 loss)
I0606 01:22:20.340422 54715 sgd_solver.cpp:106] Iteration 2622, lr = 0.00957823
I0606 01:22:25.235517 54715 softmax_loss_layer.cu:194] weight loss 0 =0.266941 weight loss 1 =1 weight loss 2 =0
I0606 01:22:29.714431 54715 solver.cpp:237] Iteration 2625, loss = 0.303552
I0606 01:22:29.714479 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.288603 (* 1 = 0.288603 loss)
I0606 01:22:29.714489 54715 sgd_solver.cpp:106] Iteration 2625, lr = 0.00957775
I0606 01:22:39.086556 54715 solver.cpp:237] Iteration 2628, loss = 0.302565
I0606 01:22:39.086608 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.352859 (* 1 = 0.352859 loss)
I0606 01:22:39.086621 54715 sgd_solver.cpp:106] Iteration 2628, lr = 0.00957726
I0606 01:22:39.689126 54715 softmax_loss_layer.cu:194] weight loss 0 =0.307677 weight loss 1 =1 weight loss 2 =0
I0606 01:22:42.322412 54715 solver.cpp:341] Iteration 2630, Testing net (#0)
I0606 01:22:43.607288 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.84304
I0606 01:22:43.607332 54715 solver.cpp:409] Test net output #1: class_Acc = 0.859167
I0606 01:22:43.607338 54715 solver.cpp:409] Test net output #2: class_Acc = 0.801448
I0606 01:22:43.607348 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.359941 (* 1 = 0.359941 loss)
I0606 01:22:48.000684 54715 softmax_loss_layer.cu:194] weight loss 0 =0.280246 weight loss 1 =1 weight loss 2 =0
I0606 01:22:49.745020 54715 solver.cpp:237] Iteration 2631, loss = 0.30257
I0606 01:22:49.745069 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.293991 (* 1 = 0.293991 loss)
I0606 01:22:49.745081 54715 sgd_solver.cpp:106] Iteration 2631, lr = 0.00957678
I0606 01:22:59.119096 54715 solver.cpp:237] Iteration 2634, loss = 0.302479
I0606 01:22:59.119145 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.264754 (* 1 = 0.264754 loss)
I0606 01:22:59.119156 54715 sgd_solver.cpp:106] Iteration 2634, lr = 0.00957629
I0606 01:23:08.493459 54715 solver.cpp:237] Iteration 2637, loss = 0.304693
I0606 01:23:08.493511 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.294741 (* 1 = 0.294741 loss)
I0606 01:23:08.493522 54715 sgd_solver.cpp:106] Iteration 2637, lr = 0.00957581
I0606 01:23:14.855983 54715 solver.cpp:341] Iteration 2640, Testing net (#0)
I0606 01:23:16.139611 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.839131
I0606 01:23:16.139654 54715 solver.cpp:409] Test net output #1: class_Acc = 0.83023
I0606 01:23:16.139662 54715 solver.cpp:409] Test net output #2: class_Acc = 0.857546
I0606 01:23:16.139672 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.358341 (* 1 = 0.358341 loss)
I0606 01:23:19.151948 54715 solver.cpp:237] Iteration 2640, loss = 0.302985
I0606 01:23:19.151999 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.277887 (* 1 = 0.277887 loss)
I0606 01:23:19.152010 54715 sgd_solver.cpp:106] Iteration 2640, lr = 0.00957532
I0606 01:23:28.523275 54715 solver.cpp:237] Iteration 2643, loss = 0.302319
I0606 01:23:28.523319 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.247748 (* 1 = 0.247748 loss)
I0606 01:23:28.523329 54715 sgd_solver.cpp:106] Iteration 2643, lr = 0.00957484
I0606 01:23:37.896266 54715 solver.cpp:237] Iteration 2646, loss = 0.301601
I0606 01:23:37.896319 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.278656 (* 1 = 0.278656 loss)
I0606 01:23:37.896332 54715 sgd_solver.cpp:106] Iteration 2646, lr = 0.00957435
I0606 01:23:45.524185 54715 softmax_loss_layer.cu:194] weight loss 0 =0.240884 weight loss 1 =1 weight loss 2 =0
I0606 01:23:47.269948 54715 solver.cpp:237] Iteration 2649, loss = 0.300651
I0606 01:23:47.269996 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.31433 (* 1 = 0.31433 loss)
I0606 01:23:47.270007 54715 sgd_solver.cpp:106] Iteration 2649, lr = 0.00957386
I0606 01:23:47.379410 54715 solver.cpp:341] Iteration 2650, Testing net (#0)
I0606 01:23:48.663103 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.841311
I0606 01:23:48.663141 54715 solver.cpp:409] Test net output #1: class_Acc = 0.840048
I0606 01:23:48.663147 54715 solver.cpp:409] Test net output #2: class_Acc = 0.837472
I0606 01:23:48.663157 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.35379 (* 1 = 0.35379 loss)
I0606 01:23:57.930402 54715 solver.cpp:237] Iteration 2652, loss = 0.301349
I0606 01:23:57.930452 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.333138 (* 1 = 0.333138 loss)
I0606 01:23:57.930464 54715 sgd_solver.cpp:106] Iteration 2652, lr = 0.00957338
I0606 01:24:07.308490 54715 solver.cpp:237] Iteration 2655, loss = 0.305579
I0606 01:24:07.308542 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.287106 (* 1 = 0.287106 loss)
I0606 01:24:07.308552 54715 sgd_solver.cpp:106] Iteration 2655, lr = 0.0095729
I0606 01:24:16.682723 54715 solver.cpp:237] Iteration 2658, loss = 0.306943
I0606 01:24:16.682791 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292313 (* 1 = 0.292313 loss)
I0606 01:24:16.682802 54715 sgd_solver.cpp:106] Iteration 2658, lr = 0.00957241
I0606 01:24:19.916801 54715 solver.cpp:341] Iteration 2660, Testing net (#0)
I0606 01:24:21.201458 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.859264
I0606 01:24:21.201503 54715 solver.cpp:409] Test net output #1: class_Acc = 0.873111
I0606 01:24:21.201509 54715 solver.cpp:409] Test net output #2: class_Acc = 0.824533
I0606 01:24:21.201519 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.320331 (* 1 = 0.320331 loss)
I0606 01:24:21.303047 54715 softmax_loss_layer.cu:194] weight loss 0 =0.285644 weight loss 1 =1 weight loss 2 =0
I0606 01:24:27.340514 54715 solver.cpp:237] Iteration 2661, loss = 0.312073
I0606 01:24:27.340546 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.350569 (* 1 = 0.350569 loss)
I0606 01:24:27.340555 54715 sgd_solver.cpp:106] Iteration 2661, lr = 0.00957192
I0606 01:24:36.717262 54715 solver.cpp:237] Iteration 2664, loss = 0.31666
I0606 01:24:36.717316 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.343876 (* 1 = 0.343876 loss)
I0606 01:24:36.717327 54715 sgd_solver.cpp:106] Iteration 2664, lr = 0.00957144
I0606 01:24:46.092244 54715 solver.cpp:237] Iteration 2667, loss = 0.316296
I0606 01:24:46.092293 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.262688 (* 1 = 0.262688 loss)
I0606 01:24:46.092304 54715 sgd_solver.cpp:106] Iteration 2667, lr = 0.00957095
I0606 01:24:52.452821 54715 solver.cpp:341] Iteration 2670, Testing net (#0)
I0606 01:24:53.737507 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.861963
I0606 01:24:53.737550 54715 solver.cpp:409] Test net output #1: class_Acc = 0.877564
I0606 01:24:53.737557 54715 solver.cpp:409] Test net output #2: class_Acc = 0.822508
I0606 01:24:53.737567 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.311233 (* 1 = 0.311233 loss)
I0606 01:24:56.753437 54715 solver.cpp:237] Iteration 2670, loss = 0.31342
I0606 01:24:56.753482 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.36369 (* 1 = 0.36369 loss)
I0606 01:24:56.753494 54715 sgd_solver.cpp:106] Iteration 2670, lr = 0.00957047
I0606 01:25:06.128391 54715 solver.cpp:237] Iteration 2673, loss = 0.313504
I0606 01:25:06.128423 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.348014 (* 1 = 0.348014 loss)
I0606 01:25:06.128433 54715 sgd_solver.cpp:106] Iteration 2673, lr = 0.00956998
I0606 01:25:15.504354 54715 solver.cpp:237] Iteration 2676, loss = 0.310896
I0606 01:25:15.504415 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.32139 (* 1 = 0.32139 loss)
I0606 01:25:15.504426 54715 sgd_solver.cpp:106] Iteration 2676, lr = 0.0095695
I0606 01:25:24.879715 54715 solver.cpp:237] Iteration 2679, loss = 0.305455
I0606 01:25:24.879813 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.274987 (* 1 = 0.274987 loss)
I0606 01:25:24.879827 54715 sgd_solver.cpp:106] Iteration 2679, lr = 0.00956901
I0606 01:25:24.989122 54715 solver.cpp:341] Iteration 2680, Testing net (#0)
I0606 01:25:26.274410 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.86799
I0606 01:25:26.274456 54715 solver.cpp:409] Test net output #1: class_Acc = 0.893679
I0606 01:25:26.274462 54715 solver.cpp:409] Test net output #2: class_Acc = 0.794373
I0606 01:25:26.274471 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.302598 (* 1 = 0.302598 loss)
I0606 01:25:35.540513 54715 solver.cpp:237] Iteration 2682, loss = 0.303033
I0606 01:25:35.540570 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310563 (* 1 = 0.310563 loss)
I0606 01:25:35.540581 54715 sgd_solver.cpp:106] Iteration 2682, lr = 0.00956853
I0606 01:25:44.916734 54715 solver.cpp:237] Iteration 2685, loss = 0.303071
I0606 01:25:44.916785 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351403 (* 1 = 0.351403 loss)
I0606 01:25:44.916796 54715 sgd_solver.cpp:106] Iteration 2685, lr = 0.00956804
I0606 01:25:54.289461 54715 solver.cpp:237] Iteration 2688, loss = 0.302626
I0606 01:25:54.289515 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.267227 (* 1 = 0.267227 loss)
I0606 01:25:54.289525 54715 sgd_solver.cpp:106] Iteration 2688, lr = 0.00956756
I0606 01:25:57.524513 54715 solver.cpp:341] Iteration 2690, Testing net (#0)
I0606 01:25:58.808482 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.86493
I0606 01:25:58.808526 54715 solver.cpp:409] Test net output #1: class_Acc = 0.907534
I0606 01:25:58.808532 54715 solver.cpp:409] Test net output #2: class_Acc = 0.765886
I0606 01:25:58.808542 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.306069 (* 1 = 0.306069 loss)
I0606 01:26:04.947643 54715 solver.cpp:237] Iteration 2691, loss = 0.301523
I0606 01:26:04.947695 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.252734 (* 1 = 0.252734 loss)
I0606 01:26:04.947706 54715 sgd_solver.cpp:106] Iteration 2691, lr = 0.00956707
I0606 01:26:14.319447 54715 solver.cpp:237] Iteration 2694, loss = 0.305136
I0606 01:26:14.319499 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.261433 (* 1 = 0.261433 loss)
I0606 01:26:14.319509 54715 sgd_solver.cpp:106] Iteration 2694, lr = 0.00956659
I0606 01:26:17.657733 54715 softmax_loss_layer.cu:194] weight loss 0 =0.256417 weight loss 1 =1 weight loss 2 =0
I0606 01:26:23.695427 54715 solver.cpp:237] Iteration 2697, loss = 0.308353
I0606 01:26:23.695477 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.273683 (* 1 = 0.273683 loss)
I0606 01:26:23.695488 54715 sgd_solver.cpp:106] Iteration 2697, lr = 0.0095661
I0606 01:26:30.055145 54715 solver.cpp:341] Iteration 2700, Testing net (#0)
I0606 01:26:31.339862 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.86553
I0606 01:26:31.339910 54715 solver.cpp:409] Test net output #1: class_Acc = 0.885912
I0606 01:26:31.339916 54715 solver.cpp:409] Test net output #2: class_Acc = 0.809532
I0606 01:26:31.339926 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.303819 (* 1 = 0.303819 loss)
I0606 01:26:34.354591 54715 solver.cpp:237] Iteration 2700, loss = 0.305942
I0606 01:26:34.354638 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.234556 (* 1 = 0.234556 loss)
I0606 01:26:34.354648 54715 sgd_solver.cpp:106] Iteration 2700, lr = 0.00956562
I0606 01:26:43.731020 54715 solver.cpp:237] Iteration 2703, loss = 0.307621
I0606 01:26:43.731075 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.288334 (* 1 = 0.288334 loss)
I0606 01:26:43.731097 54715 sgd_solver.cpp:106] Iteration 2703, lr = 0.00956513
I0606 01:26:53.105355 54715 solver.cpp:237] Iteration 2706, loss = 0.306475
I0606 01:26:53.105408 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.360717 (* 1 = 0.360717 loss)
I0606 01:26:53.105418 54715 sgd_solver.cpp:106] Iteration 2706, lr = 0.00956464
I0606 01:27:02.485086 54715 solver.cpp:237] Iteration 2709, loss = 0.305066
I0606 01:27:02.485183 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286605 (* 1 = 0.286605 loss)
I0606 01:27:02.485195 54715 sgd_solver.cpp:106] Iteration 2709, lr = 0.00956416
I0606 01:27:02.594539 54715 solver.cpp:341] Iteration 2710, Testing net (#0)
I0606 01:27:03.879228 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.870325
I0606 01:27:03.879274 54715 solver.cpp:409] Test net output #1: class_Acc = 0.912055
I0606 01:27:03.879281 54715 solver.cpp:409] Test net output #2: class_Acc = 0.76075
I0606 01:27:03.879292 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.293315 (* 1 = 0.293315 loss)
I0606 01:27:13.147106 54715 solver.cpp:237] Iteration 2712, loss = 0.306513
I0606 01:27:13.147159 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310688 (* 1 = 0.310688 loss)
I0606 01:27:13.147171 54715 sgd_solver.cpp:106] Iteration 2712, lr = 0.00956367
I0606 01:27:22.524773 54715 solver.cpp:237] Iteration 2715, loss = 0.305923
I0606 01:27:22.524821 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286464 (* 1 = 0.286464 loss)
I0606 01:27:22.524832 54715 sgd_solver.cpp:106] Iteration 2715, lr = 0.00956319
I0606 01:27:31.896490 54715 solver.cpp:237] Iteration 2718, loss = 0.303367
I0606 01:27:31.896536 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.273632 (* 1 = 0.273632 loss)
I0606 01:27:31.896548 54715 sgd_solver.cpp:106] Iteration 2718, lr = 0.0095627
I0606 01:27:35.130362 54715 solver.cpp:341] Iteration 2720, Testing net (#0)
I0606 01:27:36.414237 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.834924
I0606 01:27:36.414279 54715 solver.cpp:409] Test net output #1: class_Acc = 0.796872
I0606 01:27:36.414286 54715 solver.cpp:409] Test net output #2: class_Acc = 0.906359
I0606 01:27:36.414296 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.360421 (* 1 = 0.360421 loss)
I0606 01:27:42.554531 54715 solver.cpp:237] Iteration 2721, loss = 0.308324
I0606 01:27:42.554582 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337687 (* 1 = 0.337687 loss)
I0606 01:27:42.554594 54715 sgd_solver.cpp:106] Iteration 2721, lr = 0.00956222
I0606 01:27:51.928151 54715 solver.cpp:237] Iteration 2724, loss = 0.311461
I0606 01:27:51.928198 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.297651 (* 1 = 0.297651 loss)
I0606 01:27:51.928210 54715 sgd_solver.cpp:106] Iteration 2724, lr = 0.00956173
I0606 01:28:01.305855 54715 solver.cpp:237] Iteration 2727, loss = 0.311054
I0606 01:28:01.305907 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.344624 (* 1 = 0.344624 loss)
I0606 01:28:01.305918 54715 sgd_solver.cpp:106] Iteration 2727, lr = 0.00956125
I0606 01:28:07.668107 54715 solver.cpp:341] Iteration 2730, Testing net (#0)
I0606 01:28:08.952998 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.841014
I0606 01:28:08.953038 54715 solver.cpp:409] Test net output #1: class_Acc = 0.859326
I0606 01:28:08.953045 54715 solver.cpp:409] Test net output #2: class_Acc = 0.790473
I0606 01:28:08.953055 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.357662 (* 1 = 0.357662 loss)
I0606 01:28:11.966512 54715 solver.cpp:237] Iteration 2730, loss = 0.311481
I0606 01:28:11.966562 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.263828 (* 1 = 0.263828 loss)
I0606 01:28:11.966572 54715 sgd_solver.cpp:106] Iteration 2730, lr = 0.00956076
I0606 01:28:21.341538 54715 solver.cpp:237] Iteration 2733, loss = 0.312314
I0606 01:28:21.341585 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.322624 (* 1 = 0.322624 loss)
I0606 01:28:21.341608 54715 sgd_solver.cpp:106] Iteration 2733, lr = 0.00956028
I0606 01:28:30.715404 54715 solver.cpp:237] Iteration 2736, loss = 0.308877
I0606 01:28:30.715457 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.267159 (* 1 = 0.267159 loss)
I0606 01:28:30.715468 54715 sgd_solver.cpp:106] Iteration 2736, lr = 0.00955979
I0606 01:28:40.089607 54715 solver.cpp:237] Iteration 2739, loss = 0.309452
I0606 01:28:40.089700 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337097 (* 1 = 0.337097 loss)
I0606 01:28:40.089713 54715 sgd_solver.cpp:106] Iteration 2739, lr = 0.0095593
I0606 01:28:40.199075 54715 solver.cpp:341] Iteration 2740, Testing net (#0)
I0606 01:28:41.481472 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.688336
I0606 01:28:41.481518 54715 solver.cpp:409] Test net output #1: class_Acc = 0.643638
I0606 01:28:41.481525 54715 solver.cpp:409] Test net output #2: class_Acc = 0.790123
I0606 01:28:41.481536 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.591733 (* 1 = 0.591733 loss)
I0606 01:28:50.749819 54715 solver.cpp:237] Iteration 2742, loss = 0.30675
I0606 01:28:50.749867 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.272703 (* 1 = 0.272703 loss)
I0606 01:28:50.749879 54715 sgd_solver.cpp:106] Iteration 2742, lr = 0.00955882
I0606 01:29:00.124912 54715 solver.cpp:237] Iteration 2745, loss = 0.304287
I0606 01:29:00.124963 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.29335 (* 1 = 0.29335 loss)
I0606 01:29:00.124974 54715 sgd_solver.cpp:106] Iteration 2745, lr = 0.00955833
I0606 01:29:09.500825 54715 solver.cpp:237] Iteration 2748, loss = 0.304587
I0606 01:29:09.500876 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.336782 (* 1 = 0.336782 loss)
I0606 01:29:09.500887 54715 sgd_solver.cpp:106] Iteration 2748, lr = 0.00955785
I0606 01:29:12.736243 54715 solver.cpp:341] Iteration 2750, Testing net (#0)
I0606 01:29:14.020598 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.865442
I0606 01:29:14.020639 54715 solver.cpp:409] Test net output #1: class_Acc = 0.914506
I0606 01:29:14.020647 54715 solver.cpp:409] Test net output #2: class_Acc = 0.747096
I0606 01:29:14.020655 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.30133 (* 1 = 0.30133 loss)
I0606 01:29:20.161005 54715 solver.cpp:237] Iteration 2751, loss = 0.309249
I0606 01:29:20.161056 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.322377 (* 1 = 0.322377 loss)
I0606 01:29:20.161067 54715 sgd_solver.cpp:106] Iteration 2751, lr = 0.00955736
I0606 01:29:29.535570 54715 solver.cpp:237] Iteration 2754, loss = 0.306235
I0606 01:29:29.535615 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.246342 (* 1 = 0.246342 loss)
I0606 01:29:29.535625 54715 sgd_solver.cpp:106] Iteration 2754, lr = 0.00955688
I0606 01:29:38.909224 54715 solver.cpp:237] Iteration 2757, loss = 0.303703
I0606 01:29:38.909276 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.27343 (* 1 = 0.27343 loss)
I0606 01:29:38.909286 54715 sgd_solver.cpp:106] Iteration 2757, lr = 0.00955639
I0606 01:29:45.267918 54715 solver.cpp:341] Iteration 2760, Testing net (#0)
I0606 01:29:46.552377 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.863394
I0606 01:29:46.552422 54715 solver.cpp:409] Test net output #1: class_Acc = 0.87514
I0606 01:29:46.552429 54715 solver.cpp:409] Test net output #2: class_Acc = 0.828511
I0606 01:29:46.552439 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.30567 (* 1 = 0.30567 loss)
I0606 01:29:49.567376 54715 solver.cpp:237] Iteration 2760, loss = 0.305054
I0606 01:29:49.567428 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.302301 (* 1 = 0.302301 loss)
I0606 01:29:49.567440 54715 sgd_solver.cpp:106] Iteration 2760, lr = 0.00955591
I0606 01:29:58.939501 54715 solver.cpp:237] Iteration 2763, loss = 0.308938
I0606 01:29:58.939549 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.320645 (* 1 = 0.320645 loss)
I0606 01:29:58.939570 54715 sgd_solver.cpp:106] Iteration 2763, lr = 0.00955542
I0606 01:30:08.314208 54715 solver.cpp:237] Iteration 2766, loss = 0.306806
I0606 01:30:08.314263 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.334599 (* 1 = 0.334599 loss)
I0606 01:30:08.314273 54715 sgd_solver.cpp:106] Iteration 2766, lr = 0.00955494
I0606 01:30:17.690110 54715 solver.cpp:237] Iteration 2769, loss = 0.306774
I0606 01:30:17.690233 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.298711 (* 1 = 0.298711 loss)
I0606 01:30:17.690248 54715 sgd_solver.cpp:106] Iteration 2769, lr = 0.00955445
I0606 01:30:17.799629 54715 solver.cpp:341] Iteration 2770, Testing net (#0)
I0606 01:30:19.083333 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.855863
I0606 01:30:19.083376 54715 solver.cpp:409] Test net output #1: class_Acc = 0.921093
I0606 01:30:19.083384 54715 solver.cpp:409] Test net output #2: class_Acc = 0.713412
I0606 01:30:19.083392 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.317759 (* 1 = 0.317759 loss)
I0606 01:30:28.349138 54715 solver.cpp:237] Iteration 2772, loss = 0.30794
I0606 01:30:28.349190 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.365149 (* 1 = 0.365149 loss)
I0606 01:30:28.349202 54715 sgd_solver.cpp:106] Iteration 2772, lr = 0.00955396
I0606 01:30:37.721230 54715 solver.cpp:237] Iteration 2775, loss = 0.305948
I0606 01:30:37.721276 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.28784 (* 1 = 0.28784 loss)
I0606 01:30:37.721287 54715 sgd_solver.cpp:106] Iteration 2775, lr = 0.00955348
I0606 01:30:47.098197 54715 solver.cpp:237] Iteration 2778, loss = 0.302868
I0606 01:30:47.098245 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.337787 (* 1 = 0.337787 loss)
I0606 01:30:47.098255 54715 sgd_solver.cpp:106] Iteration 2778, lr = 0.00955299
I0606 01:30:50.332670 54715 solver.cpp:341] Iteration 2780, Testing net (#0)
I0606 01:30:51.615798 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.851198
I0606 01:30:51.615841 54715 solver.cpp:409] Test net output #1: class_Acc = 0.892578
I0606 01:30:51.615847 54715 solver.cpp:409] Test net output #2: class_Acc = 0.751002
I0606 01:30:51.615857 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.339298 (* 1 = 0.339298 loss)
I0606 01:30:57.754886 54715 solver.cpp:237] Iteration 2781, loss = 0.300255
I0606 01:30:57.754932 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.307714 (* 1 = 0.307714 loss)
I0606 01:30:57.754942 54715 sgd_solver.cpp:106] Iteration 2781, lr = 0.00955251
I0606 01:31:07.134775 54715 solver.cpp:237] Iteration 2784, loss = 0.3019
I0606 01:31:07.134829 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292051 (* 1 = 0.292051 loss)
I0606 01:31:07.134840 54715 sgd_solver.cpp:106] Iteration 2784, lr = 0.00955202
I0606 01:31:16.510417 54715 solver.cpp:237] Iteration 2787, loss = 0.300396
I0606 01:31:16.510468 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.346528 (* 1 = 0.346528 loss)
I0606 01:31:16.510478 54715 sgd_solver.cpp:106] Iteration 2787, lr = 0.00955154
I0606 01:31:22.871479 54715 solver.cpp:341] Iteration 2790, Testing net (#0)
I0606 01:31:24.155935 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.85362
I0606 01:31:24.155980 54715 solver.cpp:409] Test net output #1: class_Acc = 0.874218
I0606 01:31:24.155987 54715 solver.cpp:409] Test net output #2: class_Acc = 0.800925
I0606 01:31:24.155997 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.330244 (* 1 = 0.330244 loss)
I0606 01:31:27.168232 54715 solver.cpp:237] Iteration 2790, loss = 0.303034
I0606 01:31:27.168284 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.275992 (* 1 = 0.275992 loss)
I0606 01:31:27.168295 54715 sgd_solver.cpp:106] Iteration 2790, lr = 0.00955105
I0606 01:31:36.543550 54715 solver.cpp:237] Iteration 2793, loss = 0.305113
I0606 01:31:36.543609 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.325406 (* 1 = 0.325406 loss)
I0606 01:31:36.543620 54715 sgd_solver.cpp:106] Iteration 2793, lr = 0.00955057
I0606 01:31:45.917971 54715 solver.cpp:237] Iteration 2796, loss = 0.305622
I0606 01:31:45.918023 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.307034 (* 1 = 0.307034 loss)
I0606 01:31:45.918033 54715 sgd_solver.cpp:106] Iteration 2796, lr = 0.00955008
I0606 01:31:55.292338 54715 solver.cpp:237] Iteration 2799, loss = 0.302408
I0606 01:31:55.292448 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.256301 (* 1 = 0.256301 loss)
I0606 01:31:55.292460 54715 sgd_solver.cpp:106] Iteration 2799, lr = 0.00954959
I0606 01:31:55.401747 54715 solver.cpp:341] Iteration 2800, Testing net (#0)
I0606 01:31:56.686877 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.850375
I0606 01:31:56.686921 54715 solver.cpp:409] Test net output #1: class_Acc = 0.85446
I0606 01:31:56.686928 54715 solver.cpp:409] Test net output #2: class_Acc = 0.836718
I0606 01:31:56.686938 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.332635 (* 1 = 0.332635 loss)
I0606 01:32:05.955899 54715 solver.cpp:237] Iteration 2802, loss = 0.301601
I0606 01:32:05.955950 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.26876 (* 1 = 0.26876 loss)
I0606 01:32:05.955960 54715 sgd_solver.cpp:106] Iteration 2802, lr = 0.00954911
I0606 01:32:07.335021 54715 softmax_loss_layer.cu:194] weight loss 0 =0.195488 weight loss 1 =1 weight loss 2 =0
I0606 01:32:15.330513 54715 solver.cpp:237] Iteration 2805, loss = 0.301774
I0606 01:32:15.330560 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.327577 (* 1 = 0.327577 loss)
I0606 01:32:15.330571 54715 sgd_solver.cpp:106] Iteration 2805, lr = 0.00954862
I0606 01:32:24.703538 54715 solver.cpp:237] Iteration 2808, loss = 0.301728
I0606 01:32:24.703589 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.290685 (* 1 = 0.290685 loss)
I0606 01:32:24.703601 54715 sgd_solver.cpp:106] Iteration 2808, lr = 0.00954814
I0606 01:32:27.938848 54715 solver.cpp:341] Iteration 2810, Testing net (#0)
I0606 01:32:29.222937 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.866208
I0606 01:32:29.222982 54715 solver.cpp:409] Test net output #1: class_Acc = 0.901012
I0606 01:32:29.222990 54715 solver.cpp:409] Test net output #2: class_Acc = 0.7749
I0606 01:32:29.223000 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.304972 (* 1 = 0.304972 loss)
I0606 01:32:35.362464 54715 solver.cpp:237] Iteration 2811, loss = 0.301068
I0606 01:32:35.362514 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.294183 (* 1 = 0.294183 loss)
I0606 01:32:35.362525 54715 sgd_solver.cpp:106] Iteration 2811, lr = 0.00954765
I0606 01:32:44.738539 54715 solver.cpp:237] Iteration 2814, loss = 0.302048
I0606 01:32:44.738587 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.305622 (* 1 = 0.305622 loss)
I0606 01:32:44.738598 54715 sgd_solver.cpp:106] Iteration 2814, lr = 0.00954717
I0606 01:32:54.117595 54715 solver.cpp:237] Iteration 2817, loss = 0.302119
I0606 01:32:54.117637 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.335315 (* 1 = 0.335315 loss)
I0606 01:32:54.117647 54715 sgd_solver.cpp:106] Iteration 2817, lr = 0.00954668
I0606 01:33:00.476320 54715 solver.cpp:341] Iteration 2820, Testing net (#0)
I0606 01:33:01.760210 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.866276
I0606 01:33:01.760254 54715 solver.cpp:409] Test net output #1: class_Acc = 0.903959
I0606 01:33:01.760262 54715 solver.cpp:409] Test net output #2: class_Acc = 0.770811
I0606 01:33:01.760272 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.299943 (* 1 = 0.299943 loss)
I0606 01:33:04.775681 54715 solver.cpp:237] Iteration 2820, loss = 0.299123
I0606 01:33:04.775730 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.266519 (* 1 = 0.266519 loss)
I0606 01:33:04.775751 54715 sgd_solver.cpp:106] Iteration 2820, lr = 0.0095462
I0606 01:33:14.150816 54715 solver.cpp:237] Iteration 2823, loss = 0.304491
I0606 01:33:14.150866 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.364398 (* 1 = 0.364398 loss)
I0606 01:33:14.150877 54715 sgd_solver.cpp:106] Iteration 2823, lr = 0.00954571
I0606 01:33:23.525864 54715 solver.cpp:237] Iteration 2826, loss = 0.30342
I0606 01:33:23.525913 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.286816 (* 1 = 0.286816 loss)
I0606 01:33:23.525924 54715 sgd_solver.cpp:106] Iteration 2826, lr = 0.00954522
I0606 01:33:32.903811 54715 solver.cpp:237] Iteration 2829, loss = 0.305872
I0606 01:33:32.903951 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.288822 (* 1 = 0.288822 loss)
I0606 01:33:32.903964 54715 sgd_solver.cpp:106] Iteration 2829, lr = 0.00954474
I0606 01:33:33.013217 54715 solver.cpp:341] Iteration 2830, Testing net (#0)
I0606 01:33:34.297307 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.868746
I0606 01:33:34.297350 54715 solver.cpp:409] Test net output #1: class_Acc = 0.922749
I0606 01:33:34.297358 54715 solver.cpp:409] Test net output #2: class_Acc = 0.733502
I0606 01:33:34.297368 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.295809 (* 1 = 0.295809 loss)
I0606 01:33:35.176542 54715 softmax_loss_layer.cu:194] weight loss 0 =0.286953 weight loss 1 =1 weight loss 2 =0
I0606 01:33:43.561069 54715 solver.cpp:237] Iteration 2832, loss = 0.307286
I0606 01:33:43.561115 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.358386 (* 1 = 0.358386 loss)
I0606 01:33:43.561126 54715 sgd_solver.cpp:106] Iteration 2832, lr = 0.00954425
I0606 01:33:52.936398 54715 solver.cpp:237] Iteration 2835, loss = 0.307711
I0606 01:33:52.936448 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.289126 (* 1 = 0.289126 loss)
I0606 01:33:52.936460 54715 sgd_solver.cpp:106] Iteration 2835, lr = 0.00954377
I0606 01:34:02.308851 54715 solver.cpp:237] Iteration 2838, loss = 0.303108
I0606 01:34:02.308902 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.311788 (* 1 = 0.311788 loss)
I0606 01:34:02.308912 54715 sgd_solver.cpp:106] Iteration 2838, lr = 0.00954328
I0606 01:34:05.543134 54715 solver.cpp:341] Iteration 2840, Testing net (#0)
I0606 01:34:06.827013 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.862775
I0606 01:34:06.827055 54715 solver.cpp:409] Test net output #1: class_Acc = 0.920684
I0606 01:34:06.827061 54715 solver.cpp:409] Test net output #2: class_Acc = 0.713963
I0606 01:34:06.827071 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.309544 (* 1 = 0.309544 loss)
I0606 01:34:12.964864 54715 solver.cpp:237] Iteration 2841, loss = 0.301824
I0606 01:34:12.964918 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.320601 (* 1 = 0.320601 loss)
I0606 01:34:12.964929 54715 sgd_solver.cpp:106] Iteration 2841, lr = 0.0095428
I0606 01:34:22.344086 54715 solver.cpp:237] Iteration 2844, loss = 0.299533
I0606 01:34:22.344135 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.280063 (* 1 = 0.280063 loss)
I0606 01:34:22.344158 54715 sgd_solver.cpp:106] Iteration 2844, lr = 0.00954231
I0606 01:34:28.015126 54715 softmax_loss_layer.cu:194] weight loss 0 =0.270109 weight loss 1 =1 weight loss 2 =0
I0606 01:34:31.717399 54715 solver.cpp:237] Iteration 2847, loss = 0.300505
I0606 01:34:31.717452 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.329796 (* 1 = 0.329796 loss)
I0606 01:34:31.717463 54715 sgd_solver.cpp:106] Iteration 2847, lr = 0.00954182
I0606 01:34:38.073652 54715 solver.cpp:341] Iteration 2850, Testing net (#0)
I0606 01:34:39.358011 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.857052
I0606 01:34:39.358055 54715 solver.cpp:409] Test net output #1: class_Acc = 0.861567
I0606 01:34:39.358062 54715 solver.cpp:409] Test net output #2: class_Acc = 0.842729
I0606 01:34:39.358072 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.320663 (* 1 = 0.320663 loss)
I0606 01:34:42.372114 54715 solver.cpp:237] Iteration 2850, loss = 0.300315
I0606 01:34:42.372177 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.310197 (* 1 = 0.310197 loss)
I0606 01:34:42.372189 54715 sgd_solver.cpp:106] Iteration 2850, lr = 0.00954134
I0606 01:34:51.750180 54715 solver.cpp:237] Iteration 2853, loss = 0.300076
I0606 01:34:51.750229 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.265949 (* 1 = 0.265949 loss)
I0606 01:34:51.750241 54715 sgd_solver.cpp:106] Iteration 2853, lr = 0.00954085
I0606 01:35:01.121213 54715 solver.cpp:237] Iteration 2856, loss = 0.303107
I0606 01:35:01.121264 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.273004 (* 1 = 0.273004 loss)
I0606 01:35:01.121275 54715 sgd_solver.cpp:106] Iteration 2856, lr = 0.00954037
I0606 01:35:10.495893 54715 solver.cpp:237] Iteration 2859, loss = 0.300724
I0606 01:35:10.496027 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.284394 (* 1 = 0.284394 loss)
I0606 01:35:10.496039 54715 sgd_solver.cpp:106] Iteration 2859, lr = 0.00953988
I0606 01:35:10.605334 54715 solver.cpp:341] Iteration 2860, Testing net (#0)
I0606 01:35:11.888109 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.865212
I0606 01:35:11.888164 54715 solver.cpp:409] Test net output #1: class_Acc = 0.929775
I0606 01:35:11.888172 54715 solver.cpp:409] Test net output #2: class_Acc = 0.717653
I0606 01:35:11.888182 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.306168 (* 1 = 0.306168 loss)
I0606 01:35:19.406285 54715 softmax_loss_layer.cu:194] weight loss 0 =0.30755 weight loss 1 =1 weight loss 2 =0
I0606 01:35:21.152037 54715 solver.cpp:237] Iteration 2862, loss = 0.302163
I0606 01:35:21.152089 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.382405 (* 1 = 0.382405 loss)
I0606 01:35:21.152099 54715 sgd_solver.cpp:106] Iteration 2862, lr = 0.0095394
I0606 01:35:30.524722 54715 solver.cpp:237] Iteration 2865, loss = 0.300746
I0606 01:35:30.524773 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.374673 (* 1 = 0.374673 loss)
I0606 01:35:30.524785 54715 sgd_solver.cpp:106] Iteration 2865, lr = 0.00953891
I0606 01:35:39.898283 54715 solver.cpp:237] Iteration 2868, loss = 0.301626
I0606 01:35:39.898332 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.292431 (* 1 = 0.292431 loss)
I0606 01:35:39.898344 54715 sgd_solver.cpp:106] Iteration 2868, lr = 0.00953843
I0606 01:35:43.132673 54715 solver.cpp:341] Iteration 2870, Testing net (#0)
I0606 01:35:44.416687 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.865228
I0606 01:35:44.416731 54715 solver.cpp:409] Test net output #1: class_Acc = 0.896587
I0606 01:35:44.416738 54715 solver.cpp:409] Test net output #2: class_Acc = 0.792894
I0606 01:35:44.416749 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.30606 (* 1 = 0.30606 loss)
I0606 01:35:50.557076 54715 solver.cpp:237] Iteration 2871, loss = 0.301766
I0606 01:35:50.557128 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.278179 (* 1 = 0.278179 loss)
I0606 01:35:50.557139 54715 sgd_solver.cpp:106] Iteration 2871, lr = 0.00953794
I0606 01:35:59.933302 54715 solver.cpp:237] Iteration 2874, loss = 0.300666
I0606 01:35:59.933348 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.277937 (* 1 = 0.277937 loss)
I0606 01:35:59.933359 54715 sgd_solver.cpp:106] Iteration 2874, lr = 0.00953745
I0606 01:36:01.701508 54715 softmax_loss_layer.cu:194] weight loss 0 =0.341431 weight loss 1 =1 weight loss 2 =0
I0606 01:36:09.309731 54715 solver.cpp:237] Iteration 2877, loss = 0.301531
I0606 01:36:09.309783 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.277864 (* 1 = 0.277864 loss)
I0606 01:36:09.309795 54715 sgd_solver.cpp:106] Iteration 2877, lr = 0.00953697
I0606 01:36:15.668807 54715 solver.cpp:341] Iteration 2880, Testing net (#0)
I0606 01:36:16.953230 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.866459
I0606 01:36:16.953291 54715 solver.cpp:409] Test net output #1: class_Acc = 0.871624
I0606 01:36:16.953299 54715 solver.cpp:409] Test net output #2: class_Acc = 0.847803
I0606 01:36:16.953308 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.302692 (* 1 = 0.302692 loss)
I0606 01:36:19.965242 54715 solver.cpp:237] Iteration 2880, loss = 0.301661
I0606 01:36:19.965293 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.287804 (* 1 = 0.287804 loss)
I0606 01:36:19.965303 54715 sgd_solver.cpp:106] Iteration 2880, lr = 0.00953648
I0606 01:36:29.336172 54715 solver.cpp:237] Iteration 2883, loss = 0.299965
I0606 01:36:29.336221 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.281146 (* 1 = 0.281146 loss)
I0606 01:36:29.336232 54715 sgd_solver.cpp:106] Iteration 2883, lr = 0.009536
I0606 01:36:38.710129 54715 solver.cpp:237] Iteration 2886, loss = 0.296172
I0606 01:36:38.710181 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.209221 (* 1 = 0.209221 loss)
I0606 01:36:38.710192 54715 sgd_solver.cpp:106] Iteration 2886, lr = 0.00953551
I0606 01:36:48.083684 54715 solver.cpp:237] Iteration 2889, loss = 0.299468
I0606 01:36:48.083808 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.308847 (* 1 = 0.308847 loss)
I0606 01:36:48.083819 54715 sgd_solver.cpp:106] Iteration 2889, lr = 0.00953502
I0606 01:36:48.193159 54715 solver.cpp:341] Iteration 2890, Testing net (#0)
I0606 01:36:49.477597 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.849396
I0606 01:36:49.477640 54715 solver.cpp:409] Test net output #1: class_Acc = 0.843835
I0606 01:36:49.477648 54715 solver.cpp:409] Test net output #2: class_Acc = 0.861318
I0606 01:36:49.477656 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.340599 (* 1 = 0.340599 loss)
I0606 01:36:58.742826 54715 solver.cpp:237] Iteration 2892, loss = 0.298143
I0606 01:36:58.742880 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.248916 (* 1 = 0.248916 loss)
I0606 01:36:58.742892 54715 sgd_solver.cpp:106] Iteration 2892, lr = 0.00953454
I0606 01:37:08.116186 54715 solver.cpp:237] Iteration 2895, loss = 0.297263
I0606 01:37:08.116235 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.387184 (* 1 = 0.387184 loss)
I0606 01:37:08.116245 54715 sgd_solver.cpp:106] Iteration 2895, lr = 0.00953405
I0606 01:37:17.487309 54715 solver.cpp:237] Iteration 2898, loss = 0.296937
I0606 01:37:17.487362 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.255148 (* 1 = 0.255148 loss)
I0606 01:37:17.487375 54715 sgd_solver.cpp:106] Iteration 2898, lr = 0.00953357
I0606 01:37:20.722828 54715 solver.cpp:341] Iteration 2900, Testing net (#0)
I0606 01:37:22.006944 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.863659
I0606 01:37:22.006989 54715 solver.cpp:409] Test net output #1: class_Acc = 0.864293
I0606 01:37:22.006996 54715 solver.cpp:409] Test net output #2: class_Acc = 0.855039
I0606 01:37:22.007006 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.307112 (* 1 = 0.307112 loss)
I0606 01:37:28.143837 54715 solver.cpp:237] Iteration 2901, loss = 0.302186
I0606 01:37:28.143885 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.309123 (* 1 = 0.309123 loss)
I0606 01:37:28.143896 54715 sgd_solver.cpp:106] Iteration 2901, lr = 0.00953308
I0606 01:37:37.516094 54715 solver.cpp:237] Iteration 2904, loss = 0.302338
I0606 01:37:37.516155 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.293108 (* 1 = 0.293108 loss)
I0606 01:37:37.516170 54715 sgd_solver.cpp:106] Iteration 2904, lr = 0.0095326
I0606 01:37:46.887127 54715 solver.cpp:237] Iteration 2907, loss = 0.302293
I0606 01:37:46.887178 54715 solver.cpp:253] Train net output #0: loss_deconv_all = 0.351313 (* 1 = 0.351313 loss)
I0606 01:37:46.887188 54715 sgd_solver.cpp:106] Iteration 2907, lr = 0.00953211
I0606 01:37:53.244632 54715 solver.cpp:341] Iteration 2910, Testing net (#0)
I0606 01:37:54.529803 54715 solver.cpp:409] Test net output #0: accuracy_conv = 0.850765
I0606 01:37:54.529862 54715 solver.cpp:409] Test net output #1: class_Acc = 0.86804
I0606 01:37:54.529870 54715 solver.cpp:409] Test net output #2: class_Acc = 0.80421
I0606 01:37:54.529880 54715 solver.cpp:409] Test net output #3: loss_deconv_all = 0.335329 (* 1 = 0.3*