Skip to content

Instantly share code, notes, and snippets.

@ProGamerGov

ProGamerGov/-image_size_2432_-tv_weight_0.0000005_log.txt Secret

Created October 24, 2017 00:09
Show Gist options
  • Save ProGamerGov/887307613788bde39567e287247bd209 to your computer and use it in GitHub Desktop.
Save ProGamerGov/887307613788bde39567e287247bd209 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
-image_size_2432_-tv_weight_0.0000005_log.txt
-image_size 2432 & -tv_weight 0.0000005
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:537] Reading dangerously large protocol message. If the message turns out to be larger than 1073741824 bytes, parsing will be halted for security reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 538683157
Successfully loaded models/VGG16_SOD_finetune.caffemodel
conv1_1: 64 3 3 3
conv1_2: 64 64 3 3
conv2_1: 128 64 3 3
conv2_2: 128 128 3 3
conv3_1: 256 128 3 3
conv3_2: 256 256 3 3
conv3_3: 256 256 3 3
conv4_1: 512 256 3 3
conv4_2: 512 512 3 3
conv4_3: 512 512 3 3
conv5_1: 512 512 3 3
conv5_2: 512 512 3 3
conv5_3: 512 512 3 3
fc6: 1 1 25088 4096
fc7: 1 1 4096 4096
fc8-SOD100: 1 1 4096 100
Setting up style layer 2 : relu1_1
Setting up style layer 7 : relu2_1
Setting up style layer 12 : relu3_1
Setting up style layer 19 : relu4_1
Setting up content layer 21 : relu4_2
Setting up style layer 26 : relu5_1
Capturing content targets
nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> output]
(1): nn.GPU(1) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> output]
(1): nn.TVLoss
(2): cudnn.SpatialConvolution(3 -> 64, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
}
(2): nn.GPU(2) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> output]
(1): nn.StyleLoss
(2): cudnn.SpatialConvolution(64 -> 64, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
}
(3): nn.GPU(3) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> output]
(1): cudnn.SpatialMaxPooling(2x2, 2,2)
(2): cudnn.SpatialConvolution(64 -> 128, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
(4): nn.StyleLoss
(5): cudnn.SpatialConvolution(128 -> 128, 3x3, 1,1, 1,1)
(6): cudnn.ReLU
}
(4): nn.GPU(4) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> output]
(1): cudnn.SpatialMaxPooling(2x2, 2,2)
(2): cudnn.SpatialConvolution(128 -> 256, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
}
(5): nn.GPU(5) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> output]
(1): nn.StyleLoss
(2): cudnn.SpatialConvolution(256 -> 256, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
(4): cudnn.SpatialConvolution(256 -> 256, 3x3, 1,1, 1,1)
(5): cudnn.ReLU
}
(6): nn.GPU(6) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> output]
(1): cudnn.SpatialMaxPooling(2x2, 2,2)
(2): cudnn.SpatialConvolution(256 -> 512, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
(4): nn.StyleLoss
(5): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1)
(6): cudnn.ReLU
}
(7): nn.GPU(7) @ nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> output]
(1): nn.ContentLoss
(2): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1)
(3): cudnn.ReLU
(4): cudnn.SpatialMaxPooling(2x2, 2,2)
(5): cudnn.SpatialConvolution(512 -> 512, 3x3, 1,1, 1,1)
}
(8): nn.GPU(8) @ nn.Sequential {
[input -> (1) -> (2) -> output]
(1): cudnn.ReLU
(2): nn.StyleLoss
}
}
Capturing style target 1
3.8834133148193
125.94509124756
122.21520233154
23.665088653564
4.5750517845154
y value: 41.496166229248
dy value: 0
Running optimization with ADAM
---
x1 value: -7.1936044692993
feval(x) grad value: -5.4058352083863e-16
---
StyleLoss:updateOutput self.G 1: 1278823680
StyleLoss:updateOutput self.G 2: 3.6386742591858
StyleLoss:updateGradInput self.gradInput 1: -2.1727835086693e-09
StyleLoss:updateGradInput self.gradInput 2: -1.3036697964708e-05
dG 1: -0.00011950141924899
dG 2: -3.400208445966e-13
---
StyleLoss:updateOutput self.G 1: 20267821056
StyleLoss:updateOutput self.G 2: 115.33726501465
StyleLoss:updateGradInput self.gradInput 1: -4.7330814822999e-09
StyleLoss:updateGradInput self.gradInput 2: -4.0275226638187e-05
dG 1: -0.001294901361689
dG 2: -7.3688399132577e-12
---
StyleLoss:updateOutput self.G 1: 10460779520
StyleLoss:updateOutput self.G 2: 118.95206451416
StyleLoss:updateGradInput self.gradInput 1: -8.5812879024871e-10
StyleLoss:updateGradInput self.gradInput 2: -2.9808131785103e-06
dG 1: -9.958243026631e-05
dG 2: -1.1323762023549e-12
---
StyleLoss:updateOutput self.G 1: 918054848
StyleLoss:updateOutput self.G 2: 20.841968536377
StyleLoss:updateGradInput self.gradInput 1: -1.1896679197321e-08
StyleLoss:updateGradInput self.gradInput 2: -7.4847244832199e-05
dG 1: -2.1538742657867e-05
dG 2: -4.8897913712889e-13
---
StyleLoss:updateOutput self.G 1: 40656444
StyleLoss:updateOutput self.G 2: 3.6789810657501
StyleLoss:updateGradInput self.gradInput 1: -7.1434293147377e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00042860573739745
dG 1: -6.8364793150977e-06
dG 2: -6.1862955079775e-13
---
Iteration 1 / 2500
Content 1 loss: 1994813.281250
Style 1 loss: 2699.189365
Style 2 loss: 2853272.277832
Style 3 loss: 10104018.310547
Style 4 loss: 662611.404419
Style 5 loss: 25619.004250
Total loss: 15643033.467662
---
x1 value: -7.1467981338501
feval(x) grad value: 1.2719613189254e-16
---
StyleLoss:updateOutput self.G 1: 1206750720
StyleLoss:updateOutput self.G 2: 3.4336030483246
StyleLoss:updateGradInput self.gradInput 1: -2.7389350787388e-09
StyleLoss:updateGradInput self.gradInput 2: -1.6433616110589e-05
dG 1: -0.00021963387553114
dG 2: -6.2493066277369e-13
---
StyleLoss:updateOutput self.G 1: 18687930368
StyleLoss:updateOutput self.G 2: 106.34661865234
StyleLoss:updateGradInput self.gradInput 1: -5.4425308704253e-09
StyleLoss:updateGradInput self.gradInput 2: -4.731443914352e-05
dG 1: -0.0023923912085593
dG 2: -1.361428157709e-11
---
StyleLoss:updateOutput self.G 1: 10190614528
StyleLoss:updateOutput self.G 2: 115.87995147705
StyleLoss:updateGradInput self.gradInput 1: -1.1233610708317e-09
StyleLoss:updateGradInput self.gradInput 2: -3.905042376573e-06
dG 1: -0.00019333629461471
dG 2: -2.1984746922249e-12
---
StyleLoss:updateOutput self.G 1: 848677632
StyleLoss:updateOutput self.G 2: 19.266941070557
StyleLoss:updateGradInput self.gradInput 1: -1.4315402196985e-08
StyleLoss:updateGradInput self.gradInput 2: -9.0013003500644e-05
dG 1: -3.3555243135197e-05
dG 2: -7.6178137149024e-13
---
StyleLoss:updateOutput self.G 1: 36033176
StyleLoss:updateOutput self.G 2: 3.2606241703033
StyleLoss:updateGradInput self.gradInput 1: -8.2274240753577e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00049364555161446
dG 1: -1.0028291399067e-05
dG 2: -9.0745488380561e-13
---
Iteration 2 / 2500
Content 1 loss: 1836153.125000
Style 1 loss: 4946.664691
Style 2 loss: 5943945.556641
Style 3 loss: 14918696.777344
Style 4 loss: 957293.609619
Style 5 loss: 35902.750969
Total loss: 23696938.484263
---
x1 value: -7.0969209671021
feval(x) grad value: -7.4374400266066e-16
---
StyleLoss:updateOutput self.G 1: 1149958016
StyleLoss:updateOutput self.G 2: 3.2720093727112
StyleLoss:updateGradInput self.gradInput 1: -2.80233436456e-09
StyleLoss:updateGradInput self.gradInput 2: -1.6814003174659e-05
dG 1: -0.0002985370811075
dG 2: -8.4943624399994e-13
---
StyleLoss:updateOutput self.G 1: 17448140800
StyleLoss:updateOutput self.G 2: 99.291412353516
StyleLoss:updateGradInput self.gradInput 1: -5.5571653945208e-09
StyleLoss:updateGradInput self.gradInput 2: -4.8180998419411e-05
dG 1: -0.0032536243088543
dG 2: -1.851526224006e-11
---
StyleLoss:updateOutput self.G 1: 9847486464
StyleLoss:updateOutput self.G 2: 111.97816467285
StyleLoss:updateGradInput self.gradInput 1: -1.728834408965e-09
StyleLoss:updateGradInput self.gradInput 2: -7.7461863838835e-06
dG 1: -0.00031240910175256
dG 2: -3.552480358493e-12
---
StyleLoss:updateOutput self.G 1: 792051584
StyleLoss:updateOutput self.G 2: 17.981395721436
StyleLoss:updateGradInput self.gradInput 1: -1.5619729509808e-08
StyleLoss:updateGradInput self.gradInput 2: -9.841605060501e-05
dG 1: -4.3363157601561e-05
dG 2: -9.8444386323338e-13
---
StyleLoss:updateOutput self.G 1: 32482132
StyleLoss:updateOutput self.G 2: 2.9392919540405
StyleLoss:updateGradInput self.gradInput 1: -8.6073562499678e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00051644124323502
dG 1: -1.2479858924053e-05
dG 2: -1.1292959839829e-12
---
Iteration 3 / 2500
Content 1 loss: 1712206.250000
Style 1 loss: 7596.604586
Style 2 loss: 9342404.296875
Style 3 loss: 19629184.570312
Style 4 loss: 1247745.300293
Style 5 loss: 46477.229118
Total loss: 31985614.251184
---
x1 value: -7.0450959205627
feval(x) grad value: 3.886548143622e-17
---
StyleLoss:updateOutput self.G 1: 1102386176
StyleLoss:updateOutput self.G 2: 3.136650800705
StyleLoss:updateGradInput self.gradInput 1: -2.8237752136562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.6942651200225e-05
dG 1: -0.00036462990101427
dG 2: -1.0374921408096e-12
---
StyleLoss:updateOutput self.G 1: 16412239872
StyleLoss:updateOutput self.G 2: 93.396453857422
StyleLoss:updateGradInput self.gradInput 1: -5.5836606449589e-09
StyleLoss:updateGradInput self.gradInput 2: -4.7892241127556e-05
dG 1: -0.0039732223376632
dG 2: -2.2610252212174e-11
---
StyleLoss:updateOutput self.G 1: 9472453632
StyleLoss:updateOutput self.G 2: 107.71360015869
StyleLoss:updateGradInput self.gradInput 1: -2.506162832816e-09
StyleLoss:updateGradInput self.gradInput 2: -1.2939052794536e-05
dG 1: -0.00044255357352085
dG 2: -5.0323850989131e-12
---
StyleLoss:updateOutput self.G 1: 742949696
StyleLoss:updateOutput self.G 2: 16.866670608521
StyleLoss:updateGradInput self.gradInput 1: -1.6470332653284e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00010403496708022
dG 1: -5.1867857109755e-05
dG 2: -1.1775199955724e-12
---
StyleLoss:updateOutput self.G 1: 29534870
StyleLoss:updateOutput self.G 2: 2.672595500946
StyleLoss:updateGradInput self.gradInput 1: -8.7867228160121e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00052720337407663
dG 1: -1.4514591384795e-05
dG 2: -1.31341801584e-12
---
Iteration 4 / 2500
Content 1 loss: 1606906.347656
Style 1 loss: 10405.622005
Style 2 loss: 12803192.871094
Style 3 loss: 23790433.593750
Style 4 loss: 1529300.170898
Style 5 loss: 56922.489166
Total loss: 39797161.094570
---
x1 value: -6.9919424057007
feval(x) grad value: 4.2222048674807e-16
---
StyleLoss:updateOutput self.G 1: 1061940224
StyleLoss:updateOutput self.G 2: 3.0215694904327
StyleLoss:updateGradInput self.gradInput 1: -2.8325848333566e-09
StyleLoss:updateGradInput self.gradInput 2: -1.6995509213302e-05
dG 1: -0.00042082217987627
dG 2: -1.1973778088828e-12
---
StyleLoss:updateOutput self.G 1: 15533731840
StyleLoss:updateOutput self.G 2: 88.397148132324
StyleLoss:updateGradInput self.gradInput 1: -5.5969193724081e-09
StyleLoss:updateGradInput self.gradInput 2: -4.737549170386e-05
dG 1: -0.0045834886841476
dG 2: -2.6083064527671e-11
---
StyleLoss:updateOutput self.G 1: 9084126208
StyleLoss:updateOutput self.G 2: 103.29782867432
StyleLoss:updateGradInput self.gradInput 1: -3.3877800564852e-09
StyleLoss:updateGradInput self.gradInput 2: -1.8904625903815e-05
dG 1: -0.00057731237029657
dG 2: -6.5647608876729e-12
---
StyleLoss:updateOutput self.G 1: 700456448
StyleLoss:updateOutput self.G 2: 15.901976585388
StyleLoss:updateGradInput self.gradInput 1: -1.701035756696e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00010767654021038
dG 1: -5.9227877500234e-05
dG 2: -1.3446098618211e-12
---
StyleLoss:updateOutput self.G 1: 27040744
StyleLoss:updateOutput self.G 2: 2.4469029903412
StyleLoss:updateGradInput self.gradInput 1: -8.884092039807e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00053304550237954
dG 1: -1.6236488590948e-05
dG 2: -1.4692314205533e-12
---
Iteration 5 / 2500
Content 1 loss: 1516414.062500
Style 1 loss: 13214.175224
Style 2 loss: 16159595.214844
Style 3 loss: 27307517.578125
Style 4 loss: 1796307.495117
Style 5 loss: 66935.050964
Total loss: 46859983.576775
---
x1 value: -6.9378447532654
feval(x) grad value: 1.5369531941937e-16
---
StyleLoss:updateOutput self.G 1: 1026969472
StyleLoss:updateOutput self.G 2: 2.9220662117004
StyleLoss:updateGradInput self.gradInput 1: -2.8360112036552e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7016067431541e-05
dG 1: -0.00046940770698711
dG 2: -1.3356195489866e-12
---
StyleLoss:updateOutput self.G 1: 14770340864
StyleLoss:updateOutput self.G 2: 84.052955627441
StyleLoss:updateGradInput self.gradInput 1: -5.6067381848379e-09
StyleLoss:updateGradInput self.gradInput 2: -4.7002522478579e-05
dG 1: -0.0051137851551175
dG 2: -2.9100799894821e-11
---
StyleLoss:updateOutput self.G 1: 8700471296
StyleLoss:updateOutput self.G 2: 98.935195922852
StyleLoss:updateGradInput self.gradInput 1: -4.2450927217885e-09
StyleLoss:updateGradInput self.gradInput 2: -2.4773749828455e-05
dG 1: -0.00071044964715838
dG 2: -8.0786974332447e-12
---
StyleLoss:updateOutput self.G 1: 662480064
StyleLoss:updateOutput self.G 2: 15.039823532104
StyleLoss:updateGradInput self.gradInput 1: -1.7367508320376e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011005861597368
dG 1: -6.5805594203994e-05
dG 2: -1.4939384365004e-12
---
StyleLoss:updateOutput self.G 1: 24862280
StyleLoss:updateOutput self.G 2: 2.2497744560242
StyleLoss:updateGradInput self.gradInput 1: -8.9402824698936e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00053641694830731
dG 1: -1.7740456314641e-05
dG 2: -1.605324597212e-12
---
Iteration 6 / 2500
Content 1 loss: 1435329.003906
Style 1 loss: 15952.959538
Style 2 loss: 19403862.304688
Style 3 loss: 30468416.015625
Style 4 loss: 2056525.634766
Style 5 loss: 76599.214554
Total loss: 53456685.133076
---
x1 value: -6.8831324577332
feval(x) grad value: -1.5192869985898e-16
---
StyleLoss:updateOutput self.G 1: 996364224
StyleLoss:updateOutput self.G 2: 2.8349840641022
StyleLoss:updateGradInput self.gradInput 1: -2.8382369787749e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7029416994774e-05
dG 1: -0.00051192817045376
dG 2: -1.456604043111e-12
---
StyleLoss:updateOutput self.G 1: 14100199424
StyleLoss:updateOutput self.G 2: 80.23942565918
StyleLoss:updateGradInput self.gradInput 1: -5.6142197557563e-09
StyleLoss:updateGradInput self.gradInput 2: -4.6783006837359e-05
dG 1: -0.0055793058127165
dG 2: -3.1749918666391e-11
---
StyleLoss:updateOutput self.G 1: 8335134720
StyleLoss:updateOutput self.G 2: 94.780853271484
StyleLoss:updateGradInput self.gradInput 1: -5.0201367507441e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0148326914059e-05
dG 1: -0.00083722989074886
dG 2: -9.5203471842109e-12
---
StyleLoss:updateOutput self.G 1: 628675712
StyleLoss:updateOutput self.G 2: 14.272391319275
StyleLoss:updateGradInput self.gradInput 1: -1.7607098001804e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011166401236551
dG 1: -7.1660666435491e-05
dG 2: -1.6268624902088e-12
---
StyleLoss:updateOutput self.G 1: 22960524
StyleLoss:updateOutput self.G 2: 2.0776858329773
StyleLoss:updateGradInput self.gradInput 1: -8.9735053165896e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00053841032786295
dG 1: -1.9053390133195e-05
dG 2: -1.7241314712729e-12
---
Iteration 7 / 2500
Content 1 loss: 1362586.621094
Style 1 loss: 18586.707115
Style 2 loss: 22502178.222656
Style 3 loss: 33375020.507812
Style 4 loss: 2304691.040039
Style 5 loss: 85755.580902
Total loss: 59648818.679619
---
x1 value: -6.8280878067017
feval(x) grad value: -2.2082661125155e-16
---
StyleLoss:updateOutput self.G 1: 969341376
StyleLoss:updateOutput self.G 2: 2.7580952644348
StyleLoss:updateGradInput self.gradInput 1: -2.8397442175532e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7038461010088e-05
dG 1: -0.00054947170428932
dG 2: -1.5634275558202e-12
---
StyleLoss:updateOutput self.G 1: 13508595712
StyleLoss:updateOutput self.G 2: 76.87279510498
StyleLoss:updateGradInput self.gradInput 1: -5.620059972955e-09
StyleLoss:updateGradInput self.gradInput 2: -4.6611410652986e-05
dG 1: -0.0059902695938945
dG 2: -3.4088572242741e-11
---
StyleLoss:updateOutput self.G 1: 7994427392
StyleLoss:updateOutput self.G 2: 90.906593322754
StyleLoss:updateGradInput self.gradInput 1: -5.69768499048e-09
StyleLoss:updateGradInput self.gradInput 2: -3.4864842746174e-05
dG 1: -0.00095546245574951
dG 2: -1.0864796909371e-11
---
StyleLoss:updateOutput self.G 1: 598558976
StyleLoss:updateOutput self.G 2: 13.588671684265
StyleLoss:updateGradInput self.gradInput 1: -1.777423719318e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011283426283626
dG 1: -7.687701145187e-05
dG 2: -1.7452853398603e-12
---
StyleLoss:updateOutput self.G 1: 21308344
StyleLoss:updateOutput self.G 2: 1.9281812906265
StyleLoss:updateGradInput self.gradInput 1: -8.9933358538019e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00053960020886734
dG 1: -2.0194020180497e-05
dG 2: -1.8273462170509e-12
---
Iteration 8 / 2500
Content 1 loss: 1297584.277344
Style 1 loss: 21098.050117
Style 2 loss: 25427961.914062
Style 3 loss: 36071830.078125
Style 4 loss: 2537404.541016
Style 5 loss: 94260.807037
Total loss: 65450139.667702
---
x1 value: -6.7729783058167
feval(x) grad value: -1.0069693113082e-16
---
StyleLoss:updateOutput self.G 1: 945304064
StyleLoss:updateOutput self.G 2: 2.6897013187408
StyleLoss:updateGradInput self.gradInput 1: -2.8407118879414e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7044270862243e-05
dG 1: -0.00058286712737754
dG 2: -1.6584487689403e-12
---
StyleLoss:updateOutput self.G 1: 12982495232
StyleLoss:updateOutput self.G 2: 73.878952026367
StyleLoss:updateGradInput self.gradInput 1: -5.6246189927833e-09
StyleLoss:updateGradInput self.gradInput 2: -4.6458033466479e-05
dG 1: -0.0063557312823832
dG 2: -3.6168287115279e-11
---
StyleLoss:updateOutput self.G 1: 7679200768
StyleLoss:updateOutput self.G 2: 87.322090148926
StyleLoss:updateGradInput self.gradInput 1: -6.2812612888763e-09
StyleLoss:updateGradInput self.gradInput 2: -3.8946061977185e-05
dG 1: -0.0010648533934727
dG 2: -1.2108709868119e-11
---
StyleLoss:updateOutput self.G 1: 571504128
StyleLoss:updateOutput self.G 2: 12.97446346283
StyleLoss:updateGradInput self.gradInput 1: -1.7901676585552e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011369063577149
dG 1: -8.1563048297539e-05
dG 2: -1.8516692085885e-12
---
StyleLoss:updateOutput self.G 1: 19849584
StyleLoss:updateOutput self.G 2: 1.796178817749
StyleLoss:updateGradInput self.gradInput 1: -9.0048139611554e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054028892191127
dG 1: -2.1201120034675e-05
dG 2: -1.9184786138188e-12
---
Iteration 9 / 2500
Content 1 loss: 1239320.507812
Style 1 loss: 23480.419636
Style 2 loss: 28179823.242188
Style 3 loss: 38604585.937500
Style 4 loss: 2753712.158203
Style 5 loss: 102224.716187
Total loss: 70903146.981525
---
x1 value: -6.7180557250977
feval(x) grad value: -1.5899515163079e-16
---
StyleLoss:updateOutput self.G 1: 923772480
StyleLoss:updateOutput self.G 2: 2.6284363269806
StyleLoss:updateGradInput self.gradInput 1: -2.8413535968497e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7048119843821e-05
dG 1: -0.00061278167413548
dG 2: -1.7435654699541e-12
---
StyleLoss:updateOutput self.G 1: 12511812608
StyleLoss:updateOutput self.G 2: 71.20044708252
StyleLoss:updateGradInput self.gradInput 1: -5.628158827875e-09
StyleLoss:updateGradInput self.gradInput 2: -4.6278339141281e-05
dG 1: -0.006682694889605
dG 2: -3.802893069893e-11
---
StyleLoss:updateOutput self.G 1: 7388298752
StyleLoss:updateOutput self.G 2: 84.014129638672
StyleLoss:updateGradInput self.gradInput 1: -6.78309719504e-09
StyleLoss:updateGradInput self.gradInput 2: -4.2444640712347e-05
dG 1: -0.0011658035218716
dG 2: -1.325663450541e-11
---
StyleLoss:updateOutput self.G 1: 547057920
StyleLoss:updateOutput self.G 2: 12.41947555542
StyleLoss:updateGradInput self.gradInput 1: -1.8005367863339e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011438125511631
dG 1: -8.5797255451325e-05
dG 2: -1.9477952237223e-12
---
StyleLoss:updateOutput self.G 1: 18551186
StyleLoss:updateOutput self.G 2: 1.6786873340607
StyleLoss:updateGradInput self.gradInput 1: -9.0115200634955e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005406912532635
dG 1: -2.2097510736785e-05
dG 2: -1.9995921151511e-12
---
Iteration 10 / 2500
Content 1 loss: 1187294.433594
Style 1 loss: 25735.945702
Style 2 loss: 30762506.835938
Style 3 loss: 41001043.945312
Style 4 loss: 2953463.195801
Style 5 loss: 109676.891327
Total loss: 76039721.247673
---
x1 value: -6.6635041236877
feval(x) grad value: 2.1376015947974e-16
---
StyleLoss:updateOutput self.G 1: 904378176
StyleLoss:updateOutput self.G 2: 2.5732533931732
StyleLoss:updateGradInput self.gradInput 1: -2.8418725150914e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7051237591659e-05
dG 1: -0.00063972646603361
dG 2: -1.8202323329164e-12
---
StyleLoss:updateOutput self.G 1: 12088676352
StyleLoss:updateOutput self.G 2: 68.792518615723
StyleLoss:updateGradInput self.gradInput 1: -5.6309032991919e-09
StyleLoss:updateGradInput self.gradInput 2: -4.6065619244473e-05
dG 1: -0.0069766324013472
dG 2: -3.97016274023e-11
---
StyleLoss:updateOutput self.G 1: 7119417344
StyleLoss:updateOutput self.G 2: 80.956634521484
StyleLoss:updateGradInput self.gradInput 1: -7.2174564103022e-09
StyleLoss:updateGradInput self.gradInput 2: -4.5446049625752e-05
dG 1: -0.0012591111008078
dG 2: -1.4317660772256e-11
---
StyleLoss:updateOutput self.G 1: 524907008
StyleLoss:updateOutput self.G 2: 11.916599273682
StyleLoss:updateGradInput self.gradInput 1: -1.8094000964197e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011499268293846
dG 1: -8.9633904281072e-05
dG 2: -2.034896123132e-12
---
StyleLoss:updateOutput self.G 1: 17386442
StyleLoss:updateOutput self.G 2: 1.5732899904251
StyleLoss:updateGradInput self.gradInput 1: -9.0157257659484e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054094358347356
dG 1: -2.2901624106453e-05
dG 2: -2.0723561755531e-12
---
Iteration 11 / 2500
Content 1 loss: 1140776.562500
Style 1 loss: 27869.084358
Style 2 loss: 33182176.757812
Style 3 loss: 43272093.750000
Style 4 loss: 3136776.123047
Style 5 loss: 116632.564545
Total loss: 80876324.842262
---
x1 value: -6.6094737052917
feval(x) grad value: 7.7730962872441e-17
---
StyleLoss:updateOutput self.G 1: 886823488
StyleLoss:updateOutput self.G 2: 2.5233047008514
StyleLoss:updateGradInput self.gradInput 1: -2.8422975084652e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7053787814802e-05
dG 1: -0.00066411547595635
dG 2: -1.8896269098068e-12
---
StyleLoss:updateOutput self.G 1: 11706680320
StyleLoss:updateOutput self.G 2: 66.618713378906
StyleLoss:updateGradInput self.gradInput 1: -5.6330149433848e-09
StyleLoss:updateGradInput self.gradInput 2: -4.5810033043381e-05
dG 1: -0.0072419894859195
dG 2: -4.1211686840903e-11
---
StyleLoss:updateOutput self.G 1: 6870191104
StyleLoss:updateOutput self.G 2: 78.122611999512
StyleLoss:updateGradInput self.gradInput 1: -7.5964932122474e-09
StyleLoss:updateGradInput self.gradInput 2: -4.8050798795884e-05
dG 1: -0.0013455982552841
dG 2: -1.5301130154577e-11
---
StyleLoss:updateOutput self.G 1: 504722720
StyleLoss:updateOutput self.G 2: 11.458371162415
StyleLoss:updateGradInput self.gradInput 1: -1.8175038363211e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001155166173703
dG 1: -9.3129914603196e-05
dG 2: -2.1142631916049e-12
---
StyleLoss:updateOutput self.G 1: 16341784
StyleLoss:updateOutput self.G 2: 1.4787596464157
StyleLoss:updateGradInput self.gradInput 1: -9.0185267254128e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054111157078296
dG 1: -2.3622838853044e-05
dG 2: -2.1376184242833e-12
---
Iteration 12 / 2500
Content 1 loss: 1098976.171875
Style 1 loss: 29885.725021
Style 2 loss: 35446807.617188
Style 3 loss: 45423539.062500
Style 4 loss: 3304604.370117
Style 5 loss: 123096.805573
Total loss: 85426909.752274
---
x1 value: -6.5561037063599
feval(x) grad value: 2.6499192489918e-17
---
StyleLoss:updateOutput self.G 1: 870866560
StyleLoss:updateOutput self.G 2: 2.4779016971588
StyleLoss:updateGradInput self.gradInput 1: -2.8426418996474e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7055850548786e-05
dG 1: -0.00068628485314548
dG 2: -1.9527064427233e-12
---
StyleLoss:updateOutput self.G 1: 11360462848
StyleLoss:updateOutput self.G 2: 64.64852142334
StyleLoss:updateGradInput self.gradInput 1: -5.6346380894468e-09
StyleLoss:updateGradInput self.gradInput 2: -4.5523473090725e-05
dG 1: -0.0074824928306043
dG 2: -4.2580310805063e-11
---
StyleLoss:updateOutput self.G 1: 6638599168
StyleLoss:updateOutput self.G 2: 75.489143371582
StyleLoss:updateGradInput self.gradInput 1: -7.9298043687004e-09
StyleLoss:updateGradInput self.gradInput 2: -5.0318209105171e-05
dG 1: -0.0014259656891227
dG 2: -1.6215005033127e-11
---
StyleLoss:updateOutput self.G 1: 486304448
StyleLoss:updateOutput self.G 2: 11.040231704712
StyleLoss:updateGradInput self.gradInput 1: -1.8249945554771e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001160152387456
dG 1: -9.632004366722e-05
dG 2: -2.1866872462056e-12
---
StyleLoss:updateOutput self.G 1: 15394633
StyleLoss:updateOutput self.G 2: 1.3930524587631
StyleLoss:updateGradInput self.gradInput 1: -9.0207265657227e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054124381858855
dG 1: -2.4276727344841e-05
dG 2: -2.1967885410062e-12
---
Iteration 13 / 2500
Content 1 loss: 1061147.265625
Style 1 loss: 31790.943146
Style 2 loss: 37565865.234375
Style 3 loss: 47468531.250000
Style 4 loss: 3458041.992188
Style 5 loss: 129133.289337
Total loss: 89714509.974670
---
x1 value: -6.5035138130188
feval(x) grad value: 8.8330647147598e-18
---
StyleLoss:updateOutput self.G 1: 856299264
StyleLoss:updateOutput self.G 2: 2.4364531040192
StyleLoss:updateGradInput self.gradInput 1: -2.8429243403849e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7057544027921e-05
dG 1: -0.00070652354042977
dG 2: -2.0102916727105e-12
---
StyleLoss:updateOutput self.G 1: 11045510144
StyleLoss:updateOutput self.G 2: 62.856224060059
StyleLoss:updateGradInput self.gradInput 1: -5.6359530375971e-09
StyleLoss:updateGradInput self.gradInput 2: -4.5214019337436e-05
dG 1: -0.0077012781985104
dG 2: -4.3825335721559e-11
---
StyleLoss:updateOutput self.G 1: 6423248896
StyleLoss:updateOutput self.G 2: 73.040336608887
StyleLoss:updateGradInput self.gradInput 1: -8.2231927933663e-09
StyleLoss:updateGradInput self.gradInput 2: -5.2291303290986e-05
dG 1: -0.0015006976900622
dG 2: -1.7064802695921e-11
---
StyleLoss:updateOutput self.G 1: 469381856
StyleLoss:updateOutput self.G 2: 10.656049728394
StyleLoss:updateGradInput self.gradInput 1: -1.8323328632164e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011652325338218
dG 1: -9.9251119536348e-05
dG 2: -2.2532292871802e-12
---
StyleLoss:updateOutput self.G 1: 14537055
StyleLoss:updateOutput self.G 2: 1.315450668335
StyleLoss:updateGradInput self.gradInput 1: -9.0225768190066e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054135458776727
dG 1: -2.4868782929843e-05
dG 2: -2.2503637408383e-12
---
Iteration 14 / 2500
Content 1 loss: 1026697.558594
Style 1 loss: 33593.639374
Style 2 loss: 39548853.515625
Style 3 loss: 49419070.312500
Style 4 loss: 3598629.272461
Style 5 loss: 134744.922638
Total loss: 93761589.221191
---
x1 value: -6.4518103599548
feval(x) grad value: 7.9497575815393e-17
---
StyleLoss:updateOutput self.G 1: 842950720
StyleLoss:updateOutput self.G 2: 2.3984723091125
StyleLoss:updateGradInput self.gradInput 1: -2.843164814692e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7058988305507e-05
dG 1: -0.00072506879223511
dG 2: -2.0630593587645e-12
---
StyleLoss:updateOutput self.G 1: 10758091776
StyleLoss:updateOutput self.G 2: 61.220630645752
StyleLoss:updateGradInput self.gradInput 1: -5.6370668133354e-09
StyleLoss:updateGradInput self.gradInput 2: -4.4902375520905e-05
dG 1: -0.0079009355977178
dG 2: -4.4961520617726e-11
---
StyleLoss:updateOutput self.G 1: 6222419968
StyleLoss:updateOutput self.G 2: 70.756660461426
StyleLoss:updateGradInput self.gradInput 1: -8.482111901742e-09
StyleLoss:updateGradInput self.gradInput 2: -5.4003641707823e-05
dG 1: -0.0015703898388892
dG 2: -1.7857288564516e-11
---
StyleLoss:updateOutput self.G 1: 453718464
StyleLoss:updateOutput self.G 2: 10.300455093384
StyleLoss:updateGradInput self.gradInput 1: -1.839373631185e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011696787987603
dG 1: -0.00010196409857599
dG 2: -2.314819776833e-12
---
StyleLoss:updateOutput self.G 1: 13752453
StyleLoss:updateOutput self.G 2: 1.2444523572922
StyleLoss:updateGradInput self.gradInput 1: -9.0242636474613e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005414558108896
dG 1: -2.5410459784325e-05
dG 2: -2.2993790031733e-12
---
Iteration 15 / 2500
Content 1 loss: 995027.148438
Style 1 loss: 35301.195145
Style 2 loss: 41404995.117188
Style 3 loss: 51284742.187500
Style 4 loss: 3728646.972656
Style 5 loss: 140000.541687
Total loss: 97588713.162613
---
x1 value: -6.4010877609253
feval(x) grad value: -1.748946747348e-16
---
StyleLoss:updateOutput self.G 1: 830666368
StyleLoss:updateOutput self.G 2: 2.3635196685791
StyleLoss:updateGradInput self.gradInput 1: -2.8433779775128e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7060268874047e-05
dG 1: -0.00074213574407622
dG 2: -2.1116203403893e-12
---
StyleLoss:updateOutput self.G 1: 10494921728
StyleLoss:updateOutput self.G 2: 59.723014831543
StyleLoss:updateGradInput self.gradInput 1: -5.6380349278129e-09
StyleLoss:updateGradInput self.gradInput 2: -4.4593853090191e-05
dG 1: -0.0080837495625019
dG 2: -4.6001858572398e-11
---
StyleLoss:updateOutput self.G 1: 6034869248
StyleLoss:updateOutput self.G 2: 68.623970031738
StyleLoss:updateGradInput self.gradInput 1: -8.7110754165565e-09
StyleLoss:updateGradInput self.gradInput 2: -5.5516127758892e-05
dG 1: -0.001635474502109
dG 2: -1.8597380579966e-11
---
StyleLoss:updateOutput self.G 1: 439121600
StyleLoss:updateOutput self.G 2: 9.9690723419189
StyleLoss:updateGradInput self.gradInput 1: -1.8462429807187e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001174142525997
dG 1: -0.00010449234105181
dG 2: -2.3722167893231e-12
---
StyleLoss:updateOutput self.G 1: 13030011
StyleLoss:updateOutput self.G 2: 1.1790792942047
StyleLoss:updateGradInput self.gradInput 1: -9.0257977092278e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054154783720151
dG 1: -2.5909212126862e-05
dG 2: -2.3445121712096e-12
---
Iteration 16 / 2500
Content 1 loss: 965745.312500
Style 1 loss: 36921.426773
Style 2 loss: 43143770.507812
Style 3 loss: 53070949.218750
Style 4 loss: 3849214.965820
Style 5 loss: 144936.985016
Total loss: 101211538.416672
---
x1 value: -6.3514180183411
feval(x) grad value: -1.695948292885e-16
---
StyleLoss:updateOutput self.G 1: 819315776
StyleLoss:updateOutput self.G 2: 2.3312230110168
StyleLoss:updateGradInput self.gradInput 1: -2.8435729326759e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7061438484234e-05
dG 1: -0.00075790542177856
dG 2: -2.156490264138e-12
---
StyleLoss:updateOutput self.G 1: 10253016064
StyleLoss:updateOutput self.G 2: 58.346416473389
StyleLoss:updateGradInput self.gradInput 1: -5.6388862468282e-09
StyleLoss:updateGradInput self.gradInput 2: -4.4275893742451e-05
dG 1: -0.0082517908886075
dG 2: -4.6958117949636e-11
---
StyleLoss:updateOutput self.G 1: 5859446784
StyleLoss:updateOutput self.G 2: 66.629219055176
StyleLoss:updateGradInput self.gradInput 1: -8.914659233028e-09
StyleLoss:updateGradInput self.gradInput 2: -5.6830944231478e-05
dG 1: -0.0016963494708762
dG 2: -1.9289606370543e-11
---
StyleLoss:updateOutput self.G 1: 425377344
StyleLoss:updateOutput self.G 2: 9.6570463180542
StyleLoss:updateGradInput self.gradInput 1: -1.8534525025871e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011791846191045
dG 1: -0.00010687291069189
dG 2: -2.4262614486958e-12
---
StyleLoss:updateOutput self.G 1: 12353885
StyleLoss:updateOutput self.G 2: 1.117896437645
StyleLoss:updateGradInput self.gradInput 1: -9.0272621378062e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054163573076949
dG 1: -2.6375999368611e-05
dG 2: -2.3867507362857e-12
---
Iteration 17 / 2500
Content 1 loss: 938576.660156
Style 1 loss: 38463.214874
Style 2 loss: 44775679.687500
Style 3 loss: 54782296.875000
Style 4 loss: 3961156.860352
Style 5 loss: 149631.889343
Total loss: 104645805.187225
---
x1 value: -6.3028678894043
feval(x) grad value: -1.2012968012073e-16
---
StyleLoss:updateOutput self.G 1: 808788864
StyleLoss:updateOutput self.G 2: 2.3012704849243
StyleLoss:updateGradInput self.gradInput 1: -2.8437494581368e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7062500774045e-05
dG 1: -0.00077253056224436
dG 2: -2.1981038950819e-12
---
StyleLoss:updateOutput self.G 1: 10029786112
StyleLoss:updateOutput self.G 2: 57.076084136963
StyleLoss:updateGradInput self.gradInput 1: -5.6396438630202e-09
StyleLoss:updateGradInput self.gradInput 2: -4.3963471398456e-05
dG 1: -0.0084068616852164
dG 2: -4.7840568312418e-11
---
StyleLoss:updateOutput self.G 1: 5695091200
StyleLoss:updateOutput self.G 2: 64.760284423828
StyleLoss:updateGradInput self.gradInput 1: -9.0958032217259e-09
StyleLoss:updateGradInput self.gradInput 2: -5.7971250498667e-05
dG 1: -0.0017533849459141
dG 2: -1.993816917123e-11
---
StyleLoss:updateOutput self.G 1: 412414112
StyleLoss:updateOutput self.G 2: 9.3627500534058
StyleLoss:updateGradInput self.gradInput 1: -1.8605996743304e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011840245133499
dG 1: -0.00010911821300397
dG 2: -2.4772352138352e-12
---
StyleLoss:updateOutput self.G 1: 11723042
StyleLoss:updateOutput self.G 2: 1.0608117580414
StyleLoss:updateGradInput self.gradInput 1: -9.0286384590854e-08
StyleLoss:updateGradInput self.gradInput 2: -0.000541718211025
dG 1: -2.6811523639481e-05
dG 2: -2.4261610515747e-12
---
Iteration 18 / 2500
Content 1 loss: 913189.843750
Style 1 loss: 39932.756424
Style 2 loss: 46310583.984375
Style 3 loss: 56425822.265625
Style 4 loss: 4065719.604492
Style 5 loss: 154078.868866
Total loss: 107909327.323532
---
x1 value: -6.2554860115051
feval(x) grad value: 4.9465159093932e-17
---
StyleLoss:updateOutput self.G 1: 798983296
StyleLoss:updateOutput self.G 2: 2.2733702659607
StyleLoss:updateGradInput self.gradInput 1: -2.84391066252e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7063466657419e-05
dG 1: -0.00078615383245051
dG 2: -2.2368660743122e-12
---
StyleLoss:updateOutput self.G 1: 9823035392
StyleLoss:updateOutput self.G 2: 55.899532318115
StyleLoss:updateGradInput self.gradInput 1: -5.6403188786192e-09
StyleLoss:updateGradInput self.gradInput 2: -4.3654319597408e-05
dG 1: -0.0085504837334156
dG 2: -4.8657876339231e-11
---
StyleLoss:updateOutput self.G 1: 5541367296
StyleLoss:updateOutput self.G 2: 63.012252807617
StyleLoss:updateGradInput self.gradInput 1: -9.2553085195846e-09
StyleLoss:updateGradInput self.gradInput 2: -5.8982623158954e-05
dG 1: -0.0018067306373268
dG 2: -2.0544770745756e-11
---
StyleLoss:updateOutput self.G 1: 400235872
StyleLoss:updateOutput self.G 2: 9.0862770080566
StyleLoss:updateGradInput self.gradInput 1: -1.867218379914e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011885028652614
dG 1: -0.00011122751311632
dG 2: -2.5251218217087e-12
---
StyleLoss:updateOutput self.G 1: 11137034
StyleLoss:updateOutput self.G 2: 1.0077843666077
StyleLoss:updateGradInput self.gradInput 1: -9.0298215127405e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005417893989943
dG 1: -2.7216090529691e-05
dG 2: -2.4627702221308e-12
---
Iteration 19 / 2500
Content 1 loss: 889410.742188
Style 1 loss: 41336.531639
Style 2 loss: 47757228.515625
Style 3 loss: 58008439.453125
Style 4 loss: 4163928.955078
Style 5 loss: 158272.087097
Total loss: 111018616.284752
---
x1 value: -6.2093071937561
feval(x) grad value: 7.7730962872441e-17
---
StyleLoss:updateOutput self.G 1: 789817856
StyleLoss:updateOutput self.G 2: 2.2472915649414
StyleLoss:updateGradInput self.gradInput 1: -2.8440592103607e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7064356143237e-05
dG 1: -0.00079888757318258
dG 2: -2.2730979425123e-12
---
StyleLoss:updateOutput self.G 1: 9630915584
StyleLoss:updateOutput self.G 2: 54.806247711182
StyleLoss:updateGradInput self.gradInput 1: -5.6409228399446e-09
StyleLoss:updateGradInput self.gradInput 2: -4.3327971070539e-05
dG 1: -0.0086839413270354
dG 2: -4.9417338277014e-11
---
StyleLoss:updateOutput self.G 1: 5397215744
StyleLoss:updateOutput self.G 2: 61.373062133789
StyleLoss:updateGradInput self.gradInput 1: -9.3952481350357e-09
StyleLoss:updateGradInput self.gradInput 2: -5.9835394495167e-05
dG 1: -0.0018567546503618
dG 2: -2.1113607390211e-11
---
StyleLoss:updateOutput self.G 1: 388747424
StyleLoss:updateOutput self.G 2: 8.82546043396
StyleLoss:updateGradInput self.gradInput 1: -1.8734759521521e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011921222903766
dG 1: -0.00011321740748826
dG 2: -2.5702964062679e-12
---
StyleLoss:updateOutput self.G 1: 10594999
StyleLoss:updateOutput self.G 2: 0.95873618125916
StyleLoss:updateGradInput self.gradInput 1: -9.0307644029508e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054184574401006
dG 1: -2.7590296667768e-05
dG 2: -2.4966320243819e-12
---
Iteration 20 / 2500
Content 1 loss: 867157.128906
Style 1 loss: 42681.930542
Style 2 loss: 49123400.390625
Style 3 loss: 59536957.031250
Style 4 loss: 4256465.698242
Style 5 loss: 162216.693878
Total loss: 113988878.873444
---
x1 value: -6.1643576622009
feval(x) grad value: 1.2542951233214e-16
---
StyleLoss:updateOutput self.G 1: 781219136
StyleLoss:updateOutput self.G 2: 2.2228255271912
StyleLoss:updateGradInput self.gradInput 1: -2.8442024291309e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7065212887246e-05
dG 1: -0.00081083388067782
dG 2: -2.3070891985028e-12
---
StyleLoss:updateOutput self.G 1: 9451826176
StyleLoss:updateOutput self.G 2: 53.787109375
StyleLoss:updateGradInput self.gradInput 1: -5.6414650728698e-09
StyleLoss:updateGradInput self.gradInput 2: -4.2983221646864e-05
dG 1: -0.00880834646523
dG 2: -5.0125292805347e-11
---
StyleLoss:updateOutput self.G 1: 5261818880
StyleLoss:updateOutput self.G 2: 59.833427429199
StyleLoss:updateGradInput self.gradInput 1: -9.51751566447e-09
StyleLoss:updateGradInput self.gradInput 2: -6.0558319091797e-05
dG 1: -0.0019037403399125
dG 2: -2.1647900486088e-11
---
StyleLoss:updateOutput self.G 1: 377820224
StyleLoss:updateOutput self.G 2: 8.5773906707764
StyleLoss:updateGradInput self.gradInput 1: -1.8794160894231e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011955236550421
dG 1: -0.00011511002958287
dG 2: -2.6132637720444e-12
---
StyleLoss:updateOutput self.G 1: 10092200
StyleLoss:updateOutput self.G 2: 0.91323775053024
StyleLoss:updateGradInput self.gradInput 1: -9.0315076306524e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054189038928598
dG 1: -2.7937425329583e-05
dG 2: -2.5280426623614e-12
---
Iteration 21 / 2500
Content 1 loss: 846257.226562
Style 1 loss: 43974.987030
Style 2 loss: 50416242.187500
Style 3 loss: 61013255.859375
Style 4 loss: 4344143.554688
Style 5 loss: 165926.582336
Total loss: 116829800.397491
---
x1 value: -6.1206593513489
feval(x) grad value: 1.4486226132206e-16
---
StyleLoss:updateOutput self.G 1: 773130816
StyleLoss:updateOutput self.G 2: 2.1998119354248
StyleLoss:updateGradInput self.gradInput 1: -2.8443347677154e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7066005966626e-05
dG 1: -0.00082207098603249
dG 2: -2.3390625374098e-12
---
StyleLoss:updateOutput self.G 1: 9284355072
StyleLoss:updateOutput self.G 2: 52.834087371826
StyleLoss:updateGradInput self.gradInput 1: -5.6419509064654e-09
StyleLoss:updateGradInput self.gradInput 2: -4.2639676394174e-05
dG 1: -0.0089246826246381
dG 2: -5.0787311856038e-11
---
StyleLoss:updateOutput self.G 1: 5134301184
StyleLoss:updateOutput self.G 2: 58.383399963379
StyleLoss:updateGradInput self.gradInput 1: -9.6243688574305e-09
StyleLoss:updateGradInput self.gradInput 2: -6.1187238316052e-05
dG 1: -0.001947992364876
dG 2: -2.2151091724765e-11
---
StyleLoss:updateOutput self.G 1: 367402592
StyleLoss:updateOutput self.G 2: 8.3408870697021
StyleLoss:updateGradInput self.gradInput 1: -1.8849855010217e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001198613026645
dG 1: -0.00011691441613948
dG 2: -2.6542270985253e-12
---
StyleLoss:updateOutput self.G 1: 9624832
StyleLoss:updateOutput self.G 2: 0.8709459900856
StyleLoss:updateGradInput self.gradInput 1: -9.0320618539863e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054192362586036
dG 1: -2.8260084945941e-05
dG 2: -2.5572402268664e-12
---
Iteration 22 / 2500
Content 1 loss: 826661.816406
Style 1 loss: 45217.723846
Style 2 loss: 51642480.468750
Style 3 loss: 62440201.171875
Style 4 loss: 4427393.188477
Style 5 loss: 169417.613983
Total loss: 119551371.983337
---
x1 value: -6.0782251358032
feval(x) grad value: -9.0097253473105e-17
---
StyleLoss:updateOutput self.G 1: 765499584
StyleLoss:updateOutput self.G 2: 2.1780984401703
StyleLoss:updateGradInput self.gradInput 1: -2.8444575583819e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7066742657335e-05
dG 1: -0.00083267339505255
dG 2: -2.3692298123379e-12
---
StyleLoss:updateOutput self.G 1: 9127360512
StyleLoss:updateOutput self.G 2: 51.940696716309
StyleLoss:updateGradInput self.gradInput 1: -5.6423887784263e-09
StyleLoss:updateGradInput self.gradInput 2: -4.2283001675969e-05
dG 1: -0.009033739566803
dG 2: -5.1407926526803e-11
---
StyleLoss:updateOutput self.G 1: 5013900288
StyleLoss:updateOutput self.G 2: 57.014297485352
StyleLoss:updateGradInput self.gradInput 1: -9.7180743452441e-09
StyleLoss:updateGradInput self.gradInput 2: -6.1718921642751e-05
dG 1: -0.0019897737074643
dG 2: -2.2626199525089e-11
---
StyleLoss:updateOutput self.G 1: 357471648
StyleLoss:updateOutput self.G 2: 8.1154308319092
StyleLoss:updateGradInput self.gradInput 1: -1.890116685388e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001201649356517
dG 1: -0.00011863448889926
dG 2: -2.6932770250121e-12
---
StyleLoss:updateOutput self.G 1: 9189750
StyleLoss:updateOutput self.G 2: 0.83157581090927
StyleLoss:updateGradInput self.gradInput 1: -9.0324604684611e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054194766562432
dG 1: -2.8560454666149e-05
dG 2: -2.5844211753306e-12
---
Iteration 23 / 2500
Content 1 loss: 808283.593750
Style 1 loss: 46416.512489
Style 2 loss: 52807429.687500
Style 3 loss: 63822580.078125
Style 4 loss: 4506585.937500
Style 5 loss: 172708.145142
Total loss: 122164003.954506
---
x1 value: -6.0370650291443
feval(x) grad value: -6.7131291832174e-17
---
StyleLoss:updateOutput self.G 1: 758282880
StyleLoss:updateOutput self.G 2: 2.157564163208
StyleLoss:updateGradInput self.gradInput 1: -2.8445696909074e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7067421140382e-05
dG 1: -0.00084269978106022
dG 2: -2.3977582072621e-12
---
StyleLoss:updateOutput self.G 1: 8979834880
StyleLoss:updateOutput self.G 2: 51.101173400879
StyleLoss:updateGradInput self.gradInput 1: -5.6427835737338e-09
StyleLoss:updateGradInput self.gradInput 2: -4.1933133616112e-05
dG 1: -0.0091362204402685
dG 2: -5.1991105864957e-11
---
StyleLoss:updateOutput self.G 1: 4900245504
StyleLoss:updateOutput self.G 2: 55.721885681152
StyleLoss:updateGradInput self.gradInput 1: -9.8004218074266e-09
StyleLoss:updateGradInput self.gradInput 2: -6.2170402088668e-05
dG 1: -0.0020292149856687
dG 2: -2.3074700136738e-11
---
StyleLoss:updateOutput self.G 1: 348021152
StyleLoss:updateOutput self.G 2: 7.9008822441101
StyleLoss:updateGradInput self.gradInput 1: -1.8948012936448e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012044627510477
dG 1: -0.0001202713829116
dG 2: -2.7304374039527e-12
---
StyleLoss:updateOutput self.G 1: 8786960
StyleLoss:updateOutput self.G 2: 0.79512763023376
StyleLoss:updateGradInput self.gradInput 1: -9.0327318957861e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054196390556172
dG 1: -2.8838536309195e-05
dG 2: -2.6095842067114e-12
---
Iteration 24 / 2500
Content 1 loss: 791028.515625
Style 1 loss: 47572.594643
Style 2 loss: 53915882.812500
Style 3 loss: 65162894.531250
Style 4 loss: 4581937.866211
Style 5 loss: 175783.607483
Total loss: 124675099.927711
---
x1 value: -5.9971776008606
feval(x) grad value: -1.1129660878853e-16
---
StyleLoss:updateOutput self.G 1: 751448128
StyleLoss:updateOutput self.G 2: 2.1381168365479
StyleLoss:updateGradInput self.gradInput 1: -2.8446729416487e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7068041415769e-05
dG 1: -0.00085219537140802
dG 2: -2.42477630856e-12
---
StyleLoss:updateOutput self.G 1: 8840943616
StyleLoss:updateOutput self.G 2: 50.310791015625
StyleLoss:updateGradInput self.gradInput 1: -5.6431428419046e-09
StyleLoss:updateGradInput self.gradInput 2: -4.1560735553503e-05
dG 1: -0.0092327017337084
dG 2: -5.2540152783997e-11
---
StyleLoss:updateOutput self.G 1: 4792698368
StyleLoss:updateOutput self.G 2: 54.498931884766
StyleLoss:updateGradInput self.gradInput 1: -9.8735011277995e-09
StyleLoss:updateGradInput self.gradInput 2: -6.2527433328796e-05
dG 1: -0.0020665361080319
dG 2: -2.3499088092072e-11
---
StyleLoss:updateOutput self.G 1: 339045984
StyleLoss:updateOutput self.G 2: 7.697126865387
StyleLoss:updateGradInput self.gradInput 1: -1.8990306216438e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012070584489265
dG 1: -0.00012182591308374
dG 2: -2.7657294857097e-12
---
StyleLoss:updateOutput self.G 1: 8411741
StyleLoss:updateOutput self.G 2: 0.76117414236069
StyleLoss:updateGradInput self.gradInput 1: -9.0329237423248e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054197548888624
dG 1: -2.9097578590154e-05
dG 2: -2.6330255250423e-12
---
Iteration 25 / 2500
Content 1 loss: 774765.576172
Style 1 loss: 48686.439514
Style 2 loss: 54971794.921875
Style 3 loss: 66463376.953125
Style 4 loss: 4653438.720703
Style 5 loss: 178667.587280
Total loss: 127090730.198669
---
x1 value: -5.9585447311401
feval(x) grad value: 1.9079418460392e-16
---
StyleLoss:updateOutput self.G 1: 744956544
StyleLoss:updateOutput self.G 2: 2.1196463108063
StyleLoss:updateGradInput self.gradInput 1: -2.8447697530964e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7068621673388e-05
dG 1: -0.00086121429922059
dG 2: -2.4504382897805e-12
---
StyleLoss:updateOutput self.G 1: 8709948416
StyleLoss:updateOutput self.G 2: 49.565338134766
StyleLoss:updateGradInput self.gradInput 1: -5.6434728001875e-09
StyleLoss:updateGradInput self.gradInput 2: -4.1193645301973e-05
dG 1: -0.0093236993998289
dG 2: -5.3057981619364e-11
---
StyleLoss:updateOutput self.G 1: 4690689536
StyleLoss:updateOutput self.G 2: 53.338973999023
StyleLoss:updateGradInput self.gradInput 1: -9.938709411017e-09
StyleLoss:updateGradInput self.gradInput 2: -6.2845043430571e-05
dG 1: -0.0021019352134317
dG 2: -2.3901618531608e-11
---
StyleLoss:updateOutput self.G 1: 330454816
StyleLoss:updateOutput self.G 2: 7.5020866394043
StyleLoss:updateGradInput self.gradInput 1: -1.9029020137395e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012091862299712
dG 1: -0.00012331394827925
dG 2: -2.799511057e-12
---
StyleLoss:updateOutput self.G 1: 8059456
StyleLoss:updateOutput self.G 2: 0.72929602861404
StyleLoss:updateGradInput self.gradInput 1: -9.0330708246711e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054198422003537
dG 1: -2.9340790206334e-05
dG 2: -2.6550330944203e-12
---
Iteration 26 / 2500
Content 1 loss: 759345.947266
Style 1 loss: 49766.046524
Style 2 loss: 55978623.046875
Style 3 loss: 67725263.671875
Style 4 loss: 4721594.604492
Style 5 loss: 181387.664795
Total loss: 129415980.981827
---
x1 value: -5.9211397171021
feval(x) grad value: -3.7098871801991e-17
---
StyleLoss:updateOutput self.G 1: 738778368
StyleLoss:updateOutput self.G 2: 2.1020674705505
StyleLoss:updateGradInput self.gradInput 1: -2.8448574607154e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7069147361326e-05
dG 1: -0.00086979765910655
dG 2: -2.4748605942371e-12
---
StyleLoss:updateOutput self.G 1: 8586222080
StyleLoss:updateOutput self.G 2: 48.861255645752
StyleLoss:updateGradInput self.gradInput 1: -5.6437801099207e-09
StyleLoss:updateGradInput self.gradInput 2: -4.0820410504239e-05
dG 1: -0.0094096483662724
dG 2: -5.3547090372863e-11
---
StyleLoss:updateOutput self.G 1: 4593895424
StyleLoss:updateOutput self.G 2: 52.238304138184
StyleLoss:updateGradInput self.gradInput 1: -9.9970467459798e-09
StyleLoss:updateGradInput self.gradInput 2: -6.3108382164501e-05
dG 1: -0.0021355249918997
dG 2: -2.4283578620166e-11
---
StyleLoss:updateOutput self.G 1: 322251520
StyleLoss:updateOutput self.G 2: 7.315854549408
StyleLoss:updateGradInput self.gradInput 1: -1.9063000067376e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012109698582208
dG 1: -0.00012473479728214
dG 2: -2.831767806355e-12
---
StyleLoss:updateOutput self.G 1: 7727339
StyleLoss:updateOutput self.G 2: 0.69924312829971
StyleLoss:updateGradInput self.gradInput 1: -9.0331532476284e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054198916768655
dG 1: -2.9570073820651e-05
dG 2: -2.6757808208738e-12
---
Iteration 27 / 2500
Content 1 loss: 744754.687500
Style 1 loss: 50812.500000
Style 2 loss: 56938992.187500
Style 3 loss: 68948320.312500
Style 4 loss: 4786710.937500
Style 5 loss: 183966.110229
Total loss: 131653556.735229
---
x1 value: -5.8849315643311
feval(x) grad value: 1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 732889408
StyleLoss:updateOutput self.G 2: 2.0853116512299
StyleLoss:updateGradInput self.gradInput 1: -2.8449367306393e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7069618479582e-05
dG 1: -0.00087797932792455
dG 2: -2.4981397159229e-12
---
StyleLoss:updateOutput self.G 1: 8469186048
StyleLoss:updateOutput self.G 2: 48.195243835449
StyleLoss:updateGradInput self.gradInput 1: -5.6440714324424e-09
StyleLoss:updateGradInput self.gradInput 2: -4.0444745536661e-05
dG 1: -0.0094909472391009
dG 2: -5.4009744593353e-11
---
StyleLoss:updateOutput self.G 1: 4501938688
StyleLoss:updateOutput self.G 2: 51.192630767822
StyleLoss:updateGradInput self.gradInput 1: -1.0049395982037e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3322557252832e-05
dG 1: -0.0021674367599189
dG 2: -2.4646449811594e-11
---
StyleLoss:updateOutput self.G 1: 314380896
StyleLoss:updateOutput self.G 2: 7.1371712684631
StyleLoss:updateGradInput self.gradInput 1: -1.9092183833891e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012124654313084
dG 1: -0.00012609803525265
dG 2: -2.8627167910494e-12
---
StyleLoss:updateOutput self.G 1: 7411979
StyleLoss:updateOutput self.G 2: 0.67070627212524
StyleLoss:updateGradInput self.gradInput 1: -9.0332250124447e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054199359146878
dG 1: -2.9787794119329e-05
dG 2: -2.6954818585501e-12
---
Iteration 28 / 2500
Content 1 loss: 730892.919922
Style 1 loss: 51829.319000
Style 2 loss: 57855603.515625
Style 3 loss: 70133296.875000
Style 4 loss: 4849341.064453
Style 5 loss: 186422.138214
Total loss: 133807385.832214
---
x1 value: -5.8498849868774
feval(x) grad value: 8.1264188758345e-17
---
StyleLoss:updateOutput self.G 1: 727271488
StyleLoss:updateOutput self.G 2: 2.0693266391754
StyleLoss:updateGradInput self.gradInput 1: -2.8450084510467e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707004958007e-05
dG 1: -0.00088578450959176
dG 2: -2.5203480795433e-12
---
StyleLoss:updateOutput self.G 1: 8358336512
StyleLoss:updateOutput self.G 2: 47.564430236816
StyleLoss:updateGradInput self.gradInput 1: -5.6443512086446e-09
StyleLoss:updateGradInput self.gradInput 2: -4.0056223951979e-05
dG 1: -0.0095679527148604
dG 2: -5.4447939212832e-11
---
StyleLoss:updateOutput self.G 1: 4414414848
StyleLoss:updateOutput self.G 2: 50.19739151001
StyleLoss:updateGradInput self.gradInput 1: -1.0096455227426e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3487204897683e-05
dG 1: -0.0021978092845529
dG 2: -2.4991819377873e-11
---
StyleLoss:updateOutput self.G 1: 306847392
StyleLoss:updateOutput self.G 2: 6.9661436080933
StyleLoss:updateGradInput self.gradInput 1: -1.9117871730145e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012137300655013
dG 1: -0.00012740287638735
dG 2: -2.8923391459657e-12
---
StyleLoss:updateOutput self.G 1: 7113817
StyleLoss:updateOutput self.G 2: 0.64372551441193
StyleLoss:updateGradInput self.gradInput 1: -9.033272618808e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054199644364417
dG 1: -2.9993638236192e-05
dG 2: -2.7141091023947e-12
---
Iteration 29 / 2500
Content 1 loss: 717856.591797
Style 1 loss: 52817.350388
Style 2 loss: 58730876.953125
Style 3 loss: 71282320.312500
Style 4 loss: 4909262.695312
Style 5 loss: 188752.681732
Total loss: 135881886.584854
---
x1 value: -5.8159685134888
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 721908160
StyleLoss:updateOutput self.G 2: 2.0540664196014
StyleLoss:updateGradInput self.gradInput 1: -2.8450708455807e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7070422472898e-05
dG 1: -0.00089323578868061
dG 2: -2.5415498698667e-12
---
StyleLoss:updateOutput self.G 1: 8253205504
StyleLoss:updateOutput self.G 2: 46.966171264648
StyleLoss:updateGradInput self.gradInput 1: -5.6446216589734e-09
StyleLoss:updateGradInput self.gradInput 2: -3.9667826058576e-05
dG 1: -0.0096409814432263
dG 2: -5.4863523446524e-11
---
StyleLoss:updateOutput self.G 1: 4331024384
StyleLoss:updateOutput self.G 2: 49.249141693115
StyleLoss:updateGradInput self.gradInput 1: -1.0138895056855e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3614148530178e-05
dG 1: -0.0022267473395914
dG 2: -2.5320884278202e-11
---
StyleLoss:updateOutput self.G 1: 299658912
StyleLoss:updateOutput self.G 2: 6.802948474884
StyleLoss:updateGradInput self.gradInput 1: -1.9140731666312e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012148320820415
dG 1: -0.0001286479528062
dG 2: -2.9206053808045e-12
---
StyleLoss:updateOutput self.G 1: 6832740
StyleLoss:updateOutput self.G 2: 0.61829107999802
StyleLoss:updateGradInput self.gradInput 1: -9.0333280411414e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054199964506552
dG 1: -3.0187689844752e-05
dG 2: -2.7316686239398e-12
---
Iteration 30 / 2500
Content 1 loss: 705596.435547
Style 1 loss: 53774.208069
Style 2 loss: 59567267.578125
Style 3 loss: 72396398.437500
Style 4 loss: 4966305.175781
Style 5 loss: 190952.590942
Total loss: 137880294.425964
---
x1 value: -5.7831435203552
feval(x) grad value: 3.1799032973135e-17
---
StyleLoss:updateOutput self.G 1: 716777600
StyleLoss:updateOutput self.G 2: 2.0394680500031
StyleLoss:updateGradInput self.gradInput 1: -2.845126356732e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7070758985938e-05
dG 1: -0.00090036366600543
dG 2: -2.561831389386e-12
---
StyleLoss:updateOutput self.G 1: 8153418752
StyleLoss:updateOutput self.G 2: 46.398315429688
StyleLoss:updateGradInput self.gradInput 1: -5.6448836716072e-09
StyleLoss:updateGradInput self.gradInput 2: -3.9260357880266e-05
dG 1: -0.0097102988511324
dG 2: -5.5257989156621e-11
---
StyleLoss:updateOutput self.G 1: 4251462656
StyleLoss:updateOutput self.G 2: 48.344413757324
StyleLoss:updateGradInput self.gradInput 1: -1.0177303444436e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3708459492773e-05
dG 1: -0.0022543570958078
dG 2: -2.5634844941225e-11
---
StyleLoss:updateOutput self.G 1: 292753984
StyleLoss:updateOutput self.G 2: 6.6461915969849
StyleLoss:updateGradInput self.gradInput 1: -1.9163362452446e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012159724428784
dG 1: -0.00012984391651116
dG 2: -2.9477570558101e-12
---
StyleLoss:updateOutput self.G 1: 6568505.5
StyleLoss:updateOutput self.G 2: 0.59438067674637
StyleLoss:updateGradInput self.gradInput 1: -9.0333898583594e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054200348677114
dG 1: -3.0370114473044e-05
dG 2: -2.7481758188563e-12
---
Iteration 31 / 2500
Content 1 loss: 694072.216797
Style 1 loss: 54705.951691
Style 2 loss: 60366638.671875
Style 3 loss: 73475789.062500
Style 4 loss: 5020632.934570
Style 5 loss: 193026.901245
Total loss: 139804865.738678
---
x1 value: -5.7513709068298
feval(x) grad value: 1.766612942952e-17
---
StyleLoss:updateOutput self.G 1: 711871232
StyleLoss:updateOutput self.G 2: 2.0255079269409
StyleLoss:updateGradInput self.gradInput 1: -2.845174096322e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071044567274e-05
dG 1: -0.00090718036517501
dG 2: -2.5812262483688e-12
---
StyleLoss:updateOutput self.G 1: 8058665472
StyleLoss:updateOutput self.G 2: 45.859107971191
StyleLoss:updateGradInput self.gradInput 1: -5.6451416874381e-09
StyleLoss:updateGradInput self.gradInput 2: -3.8859860069351e-05
dG 1: -0.0097761200740933
dG 2: -5.5632557588448e-11
---
StyleLoss:updateOutput self.G 1: 4175616768
StyleLoss:updateOutput self.G 2: 47.481956481934
StyleLoss:updateGradInput self.gradInput 1: -1.0211890000278e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3771884015296e-05
dG 1: -0.0022806776687503
dG 2: -2.5934143721429e-11
---
StyleLoss:updateOutput self.G 1: 286147840
StyleLoss:updateOutput self.G 2: 6.4962167739868
StyleLoss:updateGradInput self.gradInput 1: -1.9183257649047e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012169834371889
dG 1: -0.00013098813360557
dG 2: -2.9737334556607e-12
---
StyleLoss:updateOutput self.G 1: 6319343.5
StyleLoss:updateOutput self.G 2: 0.57183420658112
StyleLoss:updateGradInput self.gradInput 1: -9.033498571398e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005420099478215
dG 1: -3.0542130843969e-05
dG 2: -2.7637419262871e-12
---
Iteration 32 / 2500
Content 1 loss: 683221.728516
Style 1 loss: 55609.434128
Style 2 loss: 61130373.046875
Style 3 loss: 74520035.156250
Style 4 loss: 5072547.729492
Style 5 loss: 194984.344482
Total loss: 141656771.439743
---
x1 value: -5.7206163406372
feval(x) grad value: -2.0316047189586e-17
---
StyleLoss:updateOutput self.G 1: 707172224
StyleLoss:updateOutput self.G 2: 2.0121378898621
StyleLoss:updateGradInput self.gradInput 1: -2.8452145084401e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071284673875e-05
dG 1: -0.00091370876180008
dG 2: -2.59980188419e-12
---
StyleLoss:updateOutput self.G 1: 7968616960
StyleLoss:updateOutput self.G 2: 45.346672058105
StyleLoss:updateGradInput self.gradInput 1: -5.645395262377e-09
StyleLoss:updateGradInput self.gradInput 2: -3.8454356399598e-05
dG 1: -0.00983867328614
dG 2: -5.5988529784612e-11
---
StyleLoss:updateOutput self.G 1: 4103207168
StyleLoss:updateOutput self.G 2: 46.658580780029
StyleLoss:updateGradInput self.gradInput 1: -1.0242978909503e-08
StyleLoss:updateGradInput self.gradInput 2: -6.380849663401e-05
dG 1: -0.0023058054503053
dG 2: -2.6219873494604e-11
---
StyleLoss:updateOutput self.G 1: 279825664
StyleLoss:updateOutput self.G 2: 6.352689743042
StyleLoss:updateGradInput self.gradInput 1: -1.9199710266093e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012175977462903
dG 1: -0.0001320831652265
dG 2: -2.9985926935927e-12
---
StyleLoss:updateOutput self.G 1: 6084252.5
StyleLoss:updateOutput self.G 2: 0.55056089162827
StyleLoss:updateGradInput self.gradInput 1: -9.0336037317229e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054201629245654
dG 1: -3.0704428354511e-05
dG 2: -2.7784280952348e-12
---
Iteration 33 / 2500
Content 1 loss: 673064.550781
Style 1 loss: 56487.728119
Style 2 loss: 61860421.875000
Style 3 loss: 75530701.171875
Style 4 loss: 5122387.573242
Style 5 loss: 196831.741333
Total loss: 143439894.640350
---
x1 value: -5.6908445358276
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 702669056
StyleLoss:updateOutput self.G 2: 1.999324798584
StyleLoss:updateGradInput self.gradInput 1: -2.8452478151308e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071486581699e-05
dG 1: -0.0009199651540257
dG 2: -2.6176036165004e-12
---
StyleLoss:updateOutput self.G 1: 7882967040
StyleLoss:updateOutput self.G 2: 44.859264373779
StyleLoss:updateGradInput self.gradInput 1: -5.6456457286913e-09
StyleLoss:updateGradInput self.gradInput 2: -3.8053953176131e-05
dG 1: -0.0098981717601418
dG 2: -5.63271165821e-11
---
StyleLoss:updateOutput self.G 1: 4034073344
StyleLoss:updateOutput self.G 2: 45.872436523438
StyleLoss:updateGradInput self.gradInput 1: -1.0270849060134e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3825405959506e-05
dG 1: -0.0023297960869968
dG 2: -2.649268304733e-11
---
StyleLoss:updateOutput self.G 1: 273772448
StyleLoss:updateOutput self.G 2: 6.2152662277222
StyleLoss:updateGradInput self.gradInput 1: -1.9212977875327e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012179723125882
dG 1: -0.00013313161616679
dG 2: -3.0223946175661e-12
---
StyleLoss:updateOutput self.G 1: 5863013
StyleLoss:updateOutput self.G 2: 0.5305410027504
StyleLoss:updateGradInput self.gradInput 1: -9.033697523364e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054202199680731
dG 1: -3.0857165256748e-05
dG 2: -2.7922495045296e-12
---
Iteration 34 / 2500
Content 1 loss: 663540.429688
Style 1 loss: 57341.972351
Style 2 loss: 62558542.968750
Style 3 loss: 76507746.093750
Style 4 loss: 5170224.609375
Style 5 loss: 198570.968628
Total loss: 145155967.042542
---
x1 value: -5.6620225906372
feval(x) grad value: 7.9497575815393e-17
---
StyleLoss:updateOutput self.G 1: 698348992
StyleLoss:updateOutput self.G 2: 1.9870326519012
StyleLoss:updateGradInput self.gradInput 1: -2.8452744604834e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071646652767e-05
dG 1: -0.00092596706235781
dG 2: -2.6346808849192e-12
---
StyleLoss:updateOutput self.G 1: 7801437184
StyleLoss:updateOutput self.G 2: 44.395313262939
StyleLoss:updateGradInput self.gradInput 1: -5.6458939745596e-09
StyleLoss:updateGradInput self.gradInput 2: -3.7658664950868e-05
dG 1: -0.0099548073485494
dG 2: -5.6649400448361e-11
---
StyleLoss:updateOutput self.G 1: 3967986944
StyleLoss:updateOutput self.G 2: 45.120952606201
StyleLoss:updateGradInput self.gradInput 1: -1.0295768682056e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3818828493822e-05
dG 1: -0.0023527294397354
dG 2: -2.675346229275e-11
---
StyleLoss:updateOutput self.G 1: 267965600
StyleLoss:updateOutput self.G 2: 6.0834360122681
StyleLoss:updateGradInput self.gradInput 1: -1.9223996616802e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012178126053186
dG 1: -0.00013413738633972
dG 2: -3.0452287826804e-12
---
StyleLoss:updateOutput self.G 1: 5654413
StyleLoss:updateOutput self.G 2: 0.51166492700577
StyleLoss:updateGradInput self.gradInput 1: -9.0337941571761e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054202770115808
dG 1: -3.1001181923784e-05
dG 2: -2.8052807472811e-12
---
Iteration 35 / 2500
Content 1 loss: 654587.890625
Style 1 loss: 58173.219681
Style 2 loss: 63226347.656250
Style 3 loss: 77451996.093750
Style 4 loss: 5216204.223633
Style 5 loss: 200212.188721
Total loss: 146807521.272659
---
x1 value: -5.6341166496277
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 694198784
StyleLoss:updateOutput self.G 2: 1.9752240180969
StyleLoss:updateGradInput self.gradInput 1: -2.8452937783641e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071763068088e-05
dG 1: -0.0009317331132479
dG 2: -2.6510874658742e-12
---
StyleLoss:updateOutput self.G 1: 7723768832
StyleLoss:updateOutput self.G 2: 43.953330993652
StyleLoss:updateGradInput self.gradInput 1: -5.6461426645171e-09
StyleLoss:updateGradInput self.gradInput 2: -3.7262245314196e-05
dG 1: -0.010008759796619
dG 2: -5.6956425686927e-11
---
StyleLoss:updateOutput self.G 1: 3904667136
StyleLoss:updateOutput self.G 2: 44.400928497314
StyleLoss:updateGradInput self.gradInput 1: -1.0318216503435e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3792358560022e-05
dG 1: -0.0023747030645609
dG 2: -2.7003330127506e-11
---
StyleLoss:updateOutput self.G 1: 262388816
StyleLoss:updateOutput self.G 2: 5.9568309783936
StyleLoss:updateGradInput self.gradInput 1: -1.9233482362324e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012176765449112
dG 1: -0.00013510331336875
dG 2: -3.0671574221403e-12
---
StyleLoss:updateOutput self.G 1: 5455974.5
StyleLoss:updateOutput self.G 2: 0.49370843172073
StyleLoss:updateGradInput self.gradInput 1: -9.0339199232403e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054203515173867
dG 1: -3.1138180929702e-05
dG 2: -2.8176779486022e-12
---
Iteration 36 / 2500
Content 1 loss: 646149.072266
Style 1 loss: 58983.833313
Style 2 loss: 63865371.093750
Style 3 loss: 78363919.921875
Style 4 loss: 5260343.994141
Style 5 loss: 201772.201538
Total loss: 148396540.116882
---
x1 value: -5.6070952415466
feval(x) grad value: 3.3565645916087e-17
---
StyleLoss:updateOutput self.G 1: 690208576
StyleLoss:updateOutput self.G 2: 1.9638705253601
StyleLoss:updateGradInput self.gradInput 1: -2.845308433308e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707185037958e-05
dG 1: -0.00093727669445798
dG 2: -2.6668610896008e-12
---
StyleLoss:updateOutput self.G 1: 7649739264
StyleLoss:updateOutput self.G 2: 43.532051086426
StyleLoss:updateGradInput self.gradInput 1: -5.6463891340286e-09
StyleLoss:updateGradInput self.gradInput 2: -3.686733180075e-05
dG 1: -0.010060184635222
dG 2: -5.7249073537324e-11
---
StyleLoss:updateOutput self.G 1: 3843948544
StyleLoss:updateOutput self.G 2: 43.710468292236
StyleLoss:updateGradInput self.gradInput 1: -1.0338568223744e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3757775933482e-05
dG 1: -0.0023957740049809
dG 2: -2.7242931868732e-11
---
StyleLoss:updateOutput self.G 1: 257039952
StyleLoss:updateOutput self.G 2: 5.8353996276855
StyleLoss:updateGradInput self.gradInput 1: -1.9240474102844e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001217424578499
dG 1: -0.00013602974649984
dG 2: -3.0881896432439e-12
---
StyleLoss:updateOutput self.G 1: 5267013.5
StyleLoss:updateOutput self.G 2: 0.47660943865776
StyleLoss:updateGradInput self.gradInput 1: -9.034060610702e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054204365005717
dG 1: -3.1268631573766e-05
dG 2: -2.8294827418562e-12
---
Iteration 37 / 2500
Content 1 loss: 638209.619141
Style 1 loss: 59774.333954
Style 2 loss: 64477007.812500
Style 3 loss: 79245158.203125
Style 4 loss: 5302771.362305
Style 5 loss: 203258.766174
Total loss: 149926180.097198
---
x1 value: -5.5809245109558
feval(x) grad value: -4.0632094379172e-17
---
StyleLoss:updateOutput self.G 1: 686368768
StyleLoss:updateOutput self.G 2: 1.9529452323914
StyleLoss:updateGradInput self.gradInput 1: -2.8453173150922e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071906768251e-05
dG 1: -0.00094261125195771
dG 2: -2.6820394863347e-12
---
StyleLoss:updateOutput self.G 1: 7579129344
StyleLoss:updateOutput self.G 2: 43.130226135254
StyleLoss:updateGradInput self.gradInput 1: -5.6466360476293e-09
StyleLoss:updateGradInput self.gradInput 2: -3.6484299926087e-05
dG 1: -0.010109237395227
dG 2: -5.7528204422397e-11
---
StyleLoss:updateOutput self.G 1: 3785660416
StyleLoss:updateOutput self.G 2: 43.047676086426
StyleLoss:updateGradInput self.gradInput 1: -1.0357417146167e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3701074395794e-05
dG 1: -0.0024160009343177
dG 2: -2.7472933650241e-11
---
StyleLoss:updateOutput self.G 1: 251906608
StyleLoss:updateOutput self.G 2: 5.7188596725464
StyleLoss:updateGradInput self.gradInput 1: -1.924581560786e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012166515080025
dG 1: -0.00013691888307221
dG 2: -3.1083746687699e-12
---
StyleLoss:updateOutput self.G 1: 5087641
StyleLoss:updateOutput self.G 2: 0.46037811040878
StyleLoss:updateGradInput self.gradInput 1: -9.0342268777022e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054205360356718
dG 1: -3.1392472010339e-05
dG 2: -2.8406886218302e-12
---
Iteration 38 / 2500
Content 1 loss: 630720.263672
Style 1 loss: 60545.173645
Style 2 loss: 65062611.328125
Style 3 loss: 80096021.484375
Style 4 loss: 5343449.707031
Style 5 loss: 204671.287537
Total loss: 151398019.244385
---
x1 value: -5.5555672645569
feval(x) grad value: 5.6531614174462e-17
---
StyleLoss:updateOutput self.G 1: 682674496
StyleLoss:updateOutput self.G 2: 1.9424334764481
StyleLoss:updateGradInput self.gradInput 1: -2.8453230882519e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071937691071e-05
dG 1: -0.00094774400349706
dG 2: -2.6966432559172e-12
---
StyleLoss:updateOutput self.G 1: 7511714304
StyleLoss:updateOutput self.G 2: 42.746593475342
StyleLoss:updateGradInput self.gradInput 1: -5.6468834053192e-09
StyleLoss:updateGradInput self.gradInput 2: -3.609448322095e-05
dG 1: -0.010156065225601
dG 2: -5.7794696112223e-11
---
StyleLoss:updateOutput self.G 1: 3729766912
StyleLoss:updateOutput self.G 2: 42.412094116211
StyleLoss:updateGradInput self.gradInput 1: -1.0374899162002e-08
StyleLoss:updateGradInput self.gradInput 2: -6.363405555021e-05
dG 1: -0.0024353968910873
dG 2: -2.7693498536041e-11
---
StyleLoss:updateOutput self.G 1: 246979840
StyleLoss:updateOutput self.G 2: 5.6070127487183
StyleLoss:updateGradInput self.gradInput 1: -1.9250180116615e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001216226737597
dG 1: -0.00013777222193312
dG 2: -3.1277471931879e-12
---
StyleLoss:updateOutput self.G 1: 4917918
StyleLoss:updateOutput self.G 2: 0.44501975178719
StyleLoss:updateGradInput self.gradInput 1: -9.034437198352e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054206629283726
dG 1: -3.1509640393779e-05
dG 2: -2.8512919022367e-12
---
Iteration 39 / 2500
Content 1 loss: 623634.716797
Style 1 loss: 61295.310974
Style 2 loss: 65623570.312500
Style 3 loss: 80917828.125000
Style 4 loss: 5382424.438477
Style 5 loss: 206007.774353
Total loss: 152814760.678101
---
x1 value: -5.53098487854
feval(x) grad value: -1.1659645423483e-16
---
StyleLoss:updateOutput self.G 1: 679113664
StyleLoss:updateOutput self.G 2: 1.9323017597198
StyleLoss:updateGradInput self.gradInput 1: -2.845326418921e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071957699955e-05
dG 1: -0.0009526910725981
dG 2: -2.710719669563e-12
---
StyleLoss:updateOutput self.G 1: 7447314944
StyleLoss:updateOutput self.G 2: 42.38011932373
StyleLoss:updateGradInput self.gradInput 1: -5.6471352039011e-09
StyleLoss:updateGradInput self.gradInput 2: -3.570769331418e-05
dG 1: -0.010200802236795
dG 2: -5.8049280660111e-11
---
StyleLoss:updateOutput self.G 1: 3676201984
StyleLoss:updateOutput self.G 2: 41.802997589111
StyleLoss:updateGradInput self.gradInput 1: -1.0391015159428e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3554514781572e-05
dG 1: -0.002453985856846
dG 2: -2.7904869387418e-11
---
StyleLoss:updateOutput self.G 1: 242230896
StyleLoss:updateOutput self.G 2: 5.4991998672485
StyleLoss:updateGradInput self.gradInput 1: -1.9254370542399e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012156152661191
dG 1: -0.0001385947689414
dG 2: -3.1464210577259e-12
---
StyleLoss:updateOutput self.G 1: 4757461
StyleLoss:updateOutput self.G 2: 0.43050017952919
StyleLoss:updateGradInput self.gradInput 1: -9.0347157311044e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054208311485127
dG 1: -3.1620420486433e-05
dG 2: -2.8613155681617e-12
---
Iteration 40 / 2500
Content 1 loss: 616938.916016
Style 1 loss: 62028.671265
Style 2 loss: 66161132.812500
Style 3 loss: 81711574.218750
Style 4 loss: 5419770.263672
Style 5 loss: 207271.041870
Total loss: 154178715.924072
---
x1 value: -5.5071353912354
feval(x) grad value: -1.766612942952e-17
---
StyleLoss:updateOutput self.G 1: 675677312
StyleLoss:updateOutput self.G 2: 1.9225240945816
StyleLoss:updateGradInput self.gradInput 1: -2.8453279732332e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.00095746526494622
dG 2: -2.7243038554225e-12
---
StyleLoss:updateOutput self.G 1: 7385730048
StyleLoss:updateOutput self.G 2: 42.029663085938
StyleLoss:updateGradInput self.gradInput 1: -5.6473870024831e-09
StyleLoss:updateGradInput self.gradInput 2: -3.5329409001861e-05
dG 1: -0.010243581607938
dG 2: -5.8292724813835e-11
---
StyleLoss:updateOutput self.G 1: 3624777984
StyleLoss:updateOutput self.G 2: 41.218238830566
StyleLoss:updateGradInput self.gradInput 1: -1.0406095540816e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3470950408373e-05
dG 1: -0.0024718309286982
dG 2: -2.8107797339638e-11
---
StyleLoss:updateOutput self.G 1: 237674160
StyleLoss:updateOutput self.G 2: 5.3957509994507
StyleLoss:updateGradInput self.gradInput 1: -1.9257047512156e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012151227565482
dG 1: -0.00013938402116764
dG 2: -3.1643394501901e-12
---
StyleLoss:updateOutput self.G 1: 4605622.5
StyleLoss:updateOutput self.G 2: 0.41676035523415
StyleLoss:updateGradInput self.gradInput 1: -9.0350418702201e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054210249800235
dG 1: -3.1725245207781e-05
dG 2: -2.8708010361284e-12
---
Iteration 41 / 2500
Content 1 loss: 610619.921875
Style 1 loss: 62746.942520
Style 2 loss: 66676558.593750
Style 3 loss: 82477605.468750
Style 4 loss: 5455523.803711
Style 5 loss: 208465.644836
Total loss: 155491520.375443
---
x1 value: -5.483980178833
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 672361856
StyleLoss:updateOutput self.G 2: 1.9130909442902
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.00096207152819261
dG 2: -2.7374096912836e-12
---
StyleLoss:updateOutput self.G 1: 7326809088
StyleLoss:updateOutput self.G 2: 41.694370269775
StyleLoss:updateGradInput self.gradInput 1: -5.647642797868e-09
StyleLoss:updateGradInput self.gradInput 2: -3.4959743061336e-05
dG 1: -0.01028451230377
dG 2: -5.8525642665508e-11
---
StyleLoss:updateOutput self.G 1: 3575333632
StyleLoss:updateOutput self.G 2: 40.655990600586
StyleLoss:updateGradInput self.gradInput 1: -1.0420285079249e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3376966863871e-05
dG 1: -0.0024889898486435
dG 2: -2.8302903423705e-11
---
StyleLoss:updateOutput self.G 1: 233306240
StyleLoss:updateOutput self.G 2: 5.2965898513794
StyleLoss:updateGradInput self.gradInput 1: -1.9258237671238e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012143884669058
dG 1: -0.00014014054613654
dG 2: -3.181514079964e-12
---
StyleLoss:updateOutput self.G 1: 4461240.5
StyleLoss:updateOutput self.G 2: 0.40369537472725
StyleLoss:updateGradInput self.gradInput 1: -9.0354127735282e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054212473332882
dG 1: -3.1824925827095e-05
dG 2: -2.8798205140013e-12
---
Iteration 42 / 2500
Content 1 loss: 604671.875000
Style 1 loss: 63447.578430
Style 2 loss: 67170820.312500
Style 3 loss: 83217603.515625
Style 4 loss: 5489667.846680
Style 5 loss: 209597.763062
Total loss: 156755808.891296
---
x1 value: -5.4614844322205
feval(x) grad value: -3.5332258859039e-17
---
StyleLoss:updateOutput self.G 1: 669160256
StyleLoss:updateOutput self.G 2: 1.9039809703827
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.00096651958301663
dG 2: -2.7500662337643e-12
---
StyleLoss:updateOutput self.G 1: 7270384640
StyleLoss:updateOutput self.G 2: 41.373275756836
StyleLoss:updateGradInput self.gradInput 1: -5.6479039223234e-09
StyleLoss:updateGradInput self.gradInput 2: -3.4607714042068e-05
dG 1: -0.010323707945645
dG 2: -5.8748693410049e-11
---
StyleLoss:updateOutput self.G 1: 3527764480
StyleLoss:updateOutput self.G 2: 40.115070343018
StyleLoss:updateGradInput self.gradInput 1: -1.0433709896063e-08
StyleLoss:updateGradInput self.gradInput 2: -6.328529707389e-05
dG 1: -0.002505497308448
dG 2: -2.8490623055211e-11
---
StyleLoss:updateOutput self.G 1: 229107952
StyleLoss:updateOutput self.G 2: 5.2012791633606
StyleLoss:updateGradInput self.gradInput 1: -1.9257962335928e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012136611621827
dG 1: -0.00014086773444433
dG 2: -3.1980221422423e-12
---
StyleLoss:updateOutput self.G 1: 4323837.5
StyleLoss:updateOutput self.G 2: 0.3912618458271
StyleLoss:updateGradInput self.gradInput 1: -9.03579504552e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054214778356254
dG 1: -3.191978612449e-05
dG 2: -2.8884047931221e-12
---
Iteration 43 / 2500
Content 1 loss: 599055.664062
Style 1 loss: 64133.399963
Style 2 loss: 67645042.968750
Style 3 loss: 83931867.187500
Style 4 loss: 5522329.833984
Style 5 loss: 210674.377441
Total loss: 157973103.431702
---
x1 value: -5.4396147727966
feval(x) grad value: 1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 666064576
StyleLoss:updateOutput self.G 2: 1.8951729536057
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.00097082048887387
dG 2: -2.7623034068447e-12
---
StyleLoss:updateOutput self.G 1: 7216322048
StyleLoss:updateOutput self.G 2: 41.065628051758
StyleLoss:updateGradInput self.gradInput 1: -5.6481685994925e-09
StyleLoss:updateGradInput self.gradInput 2: -3.4247888834216e-05
dG 1: -0.010361262597144
dG 2: -5.8962397464501e-11
---
StyleLoss:updateOutput self.G 1: 3481995264
StyleLoss:updateOutput self.G 2: 39.594615936279
StyleLoss:updateGradInput self.gradInput 1: -1.0446409071108e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3180290453602e-05
dG 1: -0.0025213800836354
dG 2: -2.8671225116295e-11
---
StyleLoss:updateOutput self.G 1: 225072624
StyleLoss:updateOutput self.G 2: 5.109667301178
StyleLoss:updateGradInput self.gradInput 1: -1.9256631844655e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012128495291108
dG 1: -0.00014156667748466
dG 2: -3.2138898747175e-12
---
StyleLoss:updateOutput self.G 1: 4193755.25
StyleLoss:updateOutput self.G 2: 0.37949076294899
StyleLoss:updateGradInput self.gradInput 1: -9.0361723437127e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054217042634264
dG 1: -3.2009596907301e-05
dG 2: -2.8965321894475e-12
---
Iteration 44 / 2500
Content 1 loss: 593744.042969
Style 1 loss: 64804.367065
Style 2 loss: 68100175.781250
Style 3 loss: 84621134.765625
Style 4 loss: 5553545.288086
Style 5 loss: 211693.267822
Total loss: 159145097.512817
---
x1 value: -5.4183330535889
feval(x) grad value: -7.0664517718078e-17
---
StyleLoss:updateOutput self.G 1: 663071104
StyleLoss:updateOutput self.G 2: 1.886655330658
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.00097497942624614
dG 2: -2.7741372567169e-12
---
StyleLoss:updateOutput self.G 1: 7164470784
StyleLoss:updateOutput self.G 2: 40.770557403564
StyleLoss:updateGradInput self.gradInput 1: -5.6484354971076e-09
StyleLoss:updateGradInput self.gradInput 2: -3.3902098948602e-05
dG 1: -0.010397281497717
dG 2: -5.9167379329317e-11
---
StyleLoss:updateOutput self.G 1: 3437896192
StyleLoss:updateOutput self.G 2: 39.093162536621
StyleLoss:updateGradInput self.gradInput 1: -1.0458482080367e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3059815147426e-05
dG 1: -0.0025366833433509
dG 2: -2.8845247371234e-11
---
StyleLoss:updateOutput self.G 1: 221203568
StyleLoss:updateOutput self.G 2: 5.0218315124512
StyleLoss:updateGradInput self.gradInput 1: -1.9254580152506e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012120678002248
dG 1: -0.00014223682228476
dG 2: -3.2291042669635e-12
---
StyleLoss:updateOutput self.G 1: 4070843.25
StyleLoss:updateOutput self.G 2: 0.36836850643158
StyleLoss:updateGradInput self.gradInput 1: -9.0365567473327e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054219336016104
dG 1: -3.2094449124997e-05
dG 2: -2.9042100755522e-12
---
Iteration 45 / 2500
Content 1 loss: 588720.507812
Style 1 loss: 65459.781647
Style 2 loss: 68537378.906250
Style 3 loss: 85286460.937500
Style 4 loss: 5583320.800781
Style 5 loss: 212653.884888
Total loss: 160273994.818878
---
x1 value: -5.3976039886475
feval(x) grad value: -1.4132903543616e-17
---
StyleLoss:updateOutput self.G 1: 660171456
StyleLoss:updateOutput self.G 2: 1.8784050941467
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0009790079202503
dG 2: -2.7856000926058e-12
---
StyleLoss:updateOutput self.G 1: 7114697216
StyleLoss:updateOutput self.G 2: 40.487312316895
StyleLoss:updateGradInput self.gradInput 1: -5.6487086119716e-09
StyleLoss:updateGradInput self.gradInput 2: -3.3557975257281e-05
dG 1: -0.010431859642267
dG 2: -5.9364131665962e-11
---
StyleLoss:updateOutput self.G 1: 3395354624
StyleLoss:updateOutput self.G 2: 38.609405517578
StyleLoss:updateGradInput self.gradInput 1: -1.0470016853503e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2942519434728e-05
dG 1: -0.0025514457374811
dG 2: -2.9013120031451e-11
---
StyleLoss:updateOutput self.G 1: 217487072
StyleLoss:updateOutput self.G 2: 4.9374580383301
StyleLoss:updateGradInput self.gradInput 1: -1.9252119898283e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001211055641761
dG 1: -0.00014288049715105
dG 2: -3.2437171438443e-12
---
StyleLoss:updateOutput self.G 1: 3953906
StyleLoss:updateOutput self.G 2: 0.35778704285622
StyleLoss:updateGradInput self.gradInput 1: -9.0369532301793e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054221710888669
dG 1: -3.2175179512706e-05
dG 2: -2.9115158634713e-12
---
Iteration 46 / 2500
Content 1 loss: 583965.283203
Style 1 loss: 66102.115631
Style 2 loss: 68957607.421875
Style 3 loss: 85928994.140625
Style 4 loss: 5611752.685547
Style 5 loss: 213566.642761
Total loss: 161361988.289642
---
x1 value: -5.3773922920227
feval(x) grad value: -2.8265807087231e-17
---
StyleLoss:updateOutput self.G 1: 657360832
StyleLoss:updateOutput self.G 2: 1.8704075813293
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.00098291272297502
dG 2: -2.7967103459481e-12
---
StyleLoss:updateOutput self.G 1: 7066879488
StyleLoss:updateOutput self.G 2: 40.215198516846
StyleLoss:updateGradInput self.gradInput 1: -5.6489830591033e-09
StyleLoss:updateGradInput self.gradInput 2: -3.3222804631805e-05
dG 1: -0.010465074330568
dG 2: -5.9553161013692e-11
---
StyleLoss:updateOutput self.G 1: 3354268672
StyleLoss:updateOutput self.G 2: 38.142211914062
StyleLoss:updateGradInput self.gradInput 1: -1.0481117307393e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2828854424879e-05
dG 1: -0.0025657028891146
dG 2: -2.9175242083346e-11
---
StyleLoss:updateOutput self.G 1: 213915376
StyleLoss:updateOutput self.G 2: 4.8563723564148
StyleLoss:updateGradInput self.gradInput 1: -1.9249322136261e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001210157861351
dG 1: -0.00014349915727507
dG 2: -3.2577621156271e-12
---
StyleLoss:updateOutput self.G 1: 3842072.75
StyleLoss:updateOutput self.G 2: 0.34766724705696
StyleLoss:updateGradInput self.gradInput 1: -9.0373376337993e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054224027553573
dG 1: -3.225238469895e-05
dG 2: -2.918501594909e-12
---
Iteration 47 / 2500
Content 1 loss: 579441.162109
Style 1 loss: 66731.197357
Style 2 loss: 69361816.406250
Style 3 loss: 86549332.031250
Style 4 loss: 5638958.129883
Style 5 loss: 214440.216064
Total loss: 162410719.142914
---
x1 value: -5.3576683998108
feval(x) grad value: -3.886548143622e-17
---
StyleLoss:updateOutput self.G 1: 654633728
StyleLoss:updateOutput self.G 2: 1.8626484870911
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0009867015760392
dG 2: -2.8074905681491e-12
---
StyleLoss:updateOutput self.G 1: 7020893696
StyleLoss:updateOutput self.G 2: 39.953514099121
StyleLoss:updateGradInput self.gradInput 1: -5.6492597266811e-09
StyleLoss:updateGradInput self.gradInput 2: -3.2910651498241e-05
dG 1: -0.010497018694878
dG 2: -5.9734939217293e-11
---
StyleLoss:updateOutput self.G 1: 3314578176
StyleLoss:updateOutput self.G 2: 37.690879821777
StyleLoss:updateGradInput self.gradInput 1: -1.0491847390881e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2721512222197e-05
dG 1: -0.0025794769171625
dG 2: -2.9331866796545e-11
---
StyleLoss:updateOutput self.G 1: 210486048
StyleLoss:updateOutput self.G 2: 4.7785186767578
StyleLoss:updateGradInput self.gradInput 1: -1.9245710802807e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012088655785192
dG 1: -0.00014409313735086
dG 2: -3.2712463380463e-12
---
StyleLoss:updateOutput self.G 1: 3735594.5
StyleLoss:updateOutput self.G 2: 0.33803200721741
StyleLoss:updateGradInput self.gradInput 1: -9.0377263006758e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054226361680776
dG 1: -3.2325897336705e-05
dG 2: -2.9251536089181e-12
---
Iteration 48 / 2500
Content 1 loss: 575168.066406
Style 1 loss: 67349.790573
Style 2 loss: 69750890.625000
Style 3 loss: 87148265.625000
Style 4 loss: 5665061.279297
Style 5 loss: 215271.697998
Total loss: 163422007.084274
---
x1 value: -5.338408946991
feval(x) grad value: -1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 651985728
StyleLoss:updateOutput self.G 2: 1.8551139831543
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.00099038053303957
dG 2: -2.8179585401245e-12
---
StyleLoss:updateOutput self.G 1: 6976625664
StyleLoss:updateOutput self.G 2: 39.701595306396
StyleLoss:updateGradInput self.gradInput 1: -5.6495399469725e-09
StyleLoss:updateGradInput self.gradInput 2: -3.2590796763543e-05
dG 1: -0.010527769103646
dG 2: -5.9909945060443e-11
---
StyleLoss:updateOutput self.G 1: 3276260608
StyleLoss:updateOutput self.G 2: 37.255153656006
StyleLoss:updateGradInput self.gradInput 1: -1.0502186675865e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2609891756438e-05
dG 1: -0.0025927745737135
dG 2: -2.9483072233605e-11
---
StyleLoss:updateOutput self.G 1: 207207392
StyleLoss:updateOutput self.G 2: 4.7040863037109
StyleLoss:updateGradInput self.gradInput 1: -1.9240772530793e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012073829566361
dG 1: -0.00014466099673882
dG 2: -3.2841381523985e-12
---
StyleLoss:updateOutput self.G 1: 3634593.5
StyleLoss:updateOutput self.G 2: 0.32889249920845
StyleLoss:updateGradInput self.gradInput 1: -9.0381035988685e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054228620138019
dG 1: -3.23956264765e-05
dG 2: -2.931463665562e-12
---
Iteration 49 / 2500
Content 1 loss: 571161.132812
Style 1 loss: 67956.996918
Style 2 loss: 70125738.281250
Style 3 loss: 87726638.671875
Style 4 loss: 5690083.740234
Style 5 loss: 216061.454773
Total loss: 164397640.277863
---
x1 value: -5.3195843696594
feval(x) grad value: 1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 649411520
StyleLoss:updateOutput self.G 2: 1.847789645195
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.00099395681172609
dG 2: -2.8281339943537e-12
---
StyleLoss:updateOutput self.G 1: 6933971968
StyleLoss:updateOutput self.G 2: 39.458866119385
StyleLoss:updateGradInput self.gradInput 1: -5.6498223877099e-09
StyleLoss:updateGradInput self.gradInput 2: -3.2289961382048e-05
dG 1: -0.010557400994003
dG 2: -6.0078560182308e-11
---
StyleLoss:updateOutput self.G 1: 3239244800
StyleLoss:updateOutput self.G 2: 36.834251403809
StyleLoss:updateGradInput self.gradInput 1: -1.0512237302862e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2496939790435e-05
dG 1: -0.0026056196074933
dG 2: -2.9629139419729e-11
---
StyleLoss:updateOutput self.G 1: 204070352
StyleLoss:updateOutput self.G 2: 4.6328687667847
StyleLoss:updateGradInput self.gradInput 1: -1.9234885684227e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012059597065672
dG 1: -0.00014520435070153
dG 2: -3.2964737710361e-12
---
StyleLoss:updateOutput self.G 1: 3539007
StyleLoss:updateOutput self.G 2: 0.32024291157722
StyleLoss:updateGradInput self.gradInput 1: -9.0384595807791e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054230756359175
dG 1: -3.2461619412061e-05
dG 2: -2.9374350174471e-12
---
Iteration 50 / 2500
Content 1 loss: 567378.515625
Style 1 loss: 68553.068161
Style 2 loss: 70487138.671875
Style 3 loss: 88285177.734375
Style 4 loss: 5714059.936523
Style 5 loss: 216808.387756
Total loss: 165339116.314316
---
x1 value: -5.3011674880981
feval(x) grad value: -3.886548143622e-17
---
StyleLoss:updateOutput self.G 1: 646907584
StyleLoss:updateOutput self.G 2: 1.840665102005
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.00099743553437293
dG 2: -2.838032543348e-12
---
StyleLoss:updateOutput self.G 1: 6892833280
StyleLoss:updateOutput self.G 2: 39.224754333496
StyleLoss:updateGradInput self.gradInput 1: -5.6501083811611e-09
StyleLoss:updateGradInput self.gradInput 2: -3.1993396987673e-05
dG 1: -0.010585977695882
dG 2: -6.024118009984e-11
---
StyleLoss:updateOutput self.G 1: 3203488768
StyleLoss:updateOutput self.G 2: 36.427658081055
StyleLoss:updateGradInput self.gradInput 1: -1.0522041904437e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2389452068601e-05
dG 1: -0.0026180283166468
dG 2: -2.9770234888371e-11
---
StyleLoss:updateOutput self.G 1: 201060992
StyleLoss:updateOutput self.G 2: 4.5645480155945
StyleLoss:updateGradInput self.gradInput 1: -1.9228144410022e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012042130401824
dG 1: -0.00014572561485693
dG 2: -3.308307404068e-12
---
StyleLoss:updateOutput self.G 1: 3448507
StyleLoss:updateOutput self.G 2: 0.31205362081528
StyleLoss:updateGradInput self.gradInput 1: -9.0388127205188e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054232880938798
dG 1: -3.2524094422115e-05
dG 2: -2.9430889149362e-12
---
Iteration 51 / 2500
Content 1 loss: 563815.380859
Style 1 loss: 69139.223099
Style 2 loss: 70835800.781250
Style 3 loss: 88824632.812500
Style 4 loss: 5737135.253906
Style 5 loss: 217514.213562
Total loss: 166248037.665176
---
x1 value: -5.283139705658
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 644472256
StyleLoss:updateOutput self.G 2: 1.8337359428406
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010008191457018
dG 2: -2.8476596081184e-12
---
StyleLoss:updateOutput self.G 1: 6853121024
StyleLoss:updateOutput self.G 2: 38.99877166748
StyleLoss:updateGradInput self.gradInput 1: -5.6503965950583e-09
StyleLoss:updateGradInput self.gradInput 2: -3.1714826036477e-05
dG 1: -0.010613564401865
dG 2: -6.0398165635522e-11
---
StyleLoss:updateOutput self.G 1: 3168879872
StyleLoss:updateOutput self.G 2: 36.034114837646
StyleLoss:updateGradInput self.gradInput 1: -1.0531704397465e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2291044741869e-05
dG 1: -0.0026300377212465
dG 2: -2.9906802728741e-11
---
StyleLoss:updateOutput self.G 1: 198168976
StyleLoss:updateOutput self.G 2: 4.498893737793
StyleLoss:updateGradInput self.gradInput 1: -1.922061443338e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012027321645292
dG 1: -0.00014622652088292
dG 2: -3.3196789501339e-12
---
StyleLoss:updateOutput self.G 1: 3361687.5
StyleLoss:updateOutput self.G 2: 0.30419737100601
StyleLoss:updateGradInput self.gradInput 1: -9.0391665708012e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054234982235357
dG 1: -3.2584033760941e-05
dG 2: -2.9485123110434e-12
---
Iteration 52 / 2500
Content 1 loss: 560449.658203
Style 1 loss: 69715.696335
Style 2 loss: 71172468.750000
Style 3 loss: 89345917.968750
Style 4 loss: 5759337.158203
Style 5 loss: 218191.017151
Total loss: 167126080.248642
---
x1 value: -5.2654805183411
feval(x) grad value: -2.4732579546966e-17
---
StyleLoss:updateOutput self.G 1: 642098688
StyleLoss:updateOutput self.G 2: 1.8269821405411
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010041168425232
dG 2: -2.8570429442404e-12
---
StyleLoss:updateOutput self.G 1: 6814750208
StyleLoss:updateOutput self.G 2: 38.780410766602
StyleLoss:updateGradInput self.gradInput 1: -5.6506883616692e-09
StyleLoss:updateGradInput self.gradInput 2: -3.1438485166291e-05
dG 1: -0.010640218853951
dG 2: -6.0549856795156e-11
---
StyleLoss:updateOutput self.G 1: 3135341056
StyleLoss:updateOutput self.G 2: 35.652729034424
StyleLoss:updateGradInput self.gradInput 1: -1.0541290507149e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2187369621824e-05
dG 1: -0.0026416771579534
dG 2: -3.0039151721617e-11
---
StyleLoss:updateOutput self.G 1: 195386896
StyleLoss:updateOutput self.G 2: 4.4357328414917
StyleLoss:updateGradInput self.gradInput 1: -1.9213199919932e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012010858335998
dG 1: -0.00014670837845188
dG 2: -3.3306187668947e-12
---
StyleLoss:updateOutput self.G 1: 3278554
StyleLoss:updateOutput self.G 2: 0.29667463898659
StyleLoss:updateGradInput self.gradInput 1: -9.0395268159682e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054237159201875
dG 1: -3.264143015258e-05
dG 2: -2.9537058562901e-12
---
Iteration 53 / 2500
Content 1 loss: 557271.240234
Style 1 loss: 70282.596588
Style 2 loss: 71497787.109375
Style 3 loss: 89849894.531250
Style 4 loss: 5780642.944336
Style 5 loss: 218838.935852
Total loss: 167974717.357635
---
x1 value: -5.2481741905212
feval(x) grad value: -1.4132903543616e-17
---
StyleLoss:updateOutput self.G 1: 639783040
StyleLoss:updateOutput self.G 2: 1.8203933238983
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0010073338635266
dG 2: -2.8661966463422e-12
---
StyleLoss:updateOutput self.G 1: 6777638400
StyleLoss:updateOutput self.G 2: 38.569225311279
StyleLoss:updateGradInput self.gradInput 1: -5.65098012828e-09
StyleLoss:updateGradInput self.gradInput 2: -3.1178515200736e-05
dG 1: -0.010665999725461
dG 2: -6.0696558890072e-11
---
StyleLoss:updateOutput self.G 1: 3102841088
StyleLoss:updateOutput self.G 2: 35.28316116333
StyleLoss:updateGradInput self.gradInput 1: -1.0550733620107e-08
StyleLoss:updateGradInput self.gradInput 2: -6.20904029347e-05
dG 1: -0.0026529550086707
dG 2: -3.0167399828196e-11
---
StyleLoss:updateOutput self.G 1: 192704496
StyleLoss:updateOutput self.G 2: 4.3748359680176
StyleLoss:updateGradInput self.gradInput 1: -1.9205938173172e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011995143722743
dG 1: -0.00014717299200129
dG 2: -3.3411658856286e-12
---
StyleLoss:updateOutput self.G 1: 3198735.75
StyleLoss:updateOutput self.G 2: 0.28945198655128
StyleLoss:updateGradInput self.gradInput 1: -9.0398913243916e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005423934198916
dG 1: -3.2696530979592e-05
dG 2: -2.9586923189218e-12
---
Iteration 54 / 2500
Content 1 loss: 554256.884766
Style 1 loss: 70842.864990
Style 2 loss: 71812429.687500
Style 3 loss: 90337658.203125
Style 4 loss: 5801158.813477
Style 5 loss: 219461.677551
Total loss: 168795808.131409
---
x1 value: -5.2312068939209
feval(x) grad value: 2.4732579546966e-17
---
StyleLoss:updateOutput self.G 1: 637523200
StyleLoss:updateOutput self.G 2: 1.8139634132385
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010104735847563
dG 2: -2.8751298217222e-12
---
StyleLoss:updateOutput self.G 1: 6741706752
StyleLoss:updateOutput self.G 2: 38.364749908447
StyleLoss:updateGradInput self.gradInput 1: -5.6512754476046e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0928040359868e-05
dG 1: -0.010690959170461
dG 2: -6.0838598048285e-11
---
StyleLoss:updateOutput self.G 1: 3071347200
StyleLoss:updateOutput self.G 2: 34.92504119873
StyleLoss:updateGradInput self.gradInput 1: -1.0560059493514e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1992126575205e-05
dG 1: -0.0026638840790838
dG 2: -3.0291678887462e-11
---
StyleLoss:updateOutput self.G 1: 190117712
StyleLoss:updateOutput self.G 2: 4.3161106109619
StyleLoss:updateGradInput self.gradInput 1: -1.9198845180313e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011981693387497
dG 1: -0.00014762100181542
dG 2: -3.3513378704109e-12
---
StyleLoss:updateOutput self.G 1: 3121555
StyleLoss:updateOutput self.G 2: 0.28246793150902
StyleLoss:updateGradInput self.gradInput 1: -9.0402501484732e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054241507314146
dG 1: -3.2749820093159e-05
dG 2: -2.9635137659828e-12
---
Iteration 55 / 2500
Content 1 loss: 551397.314453
Style 1 loss: 71396.610260
Style 2 loss: 72117082.031250
Style 3 loss: 90809501.953125
Style 4 loss: 5820892.822266
Style 5 loss: 220064.323425
Total loss: 169590335.054779
---
x1 value: -5.2145619392395
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 635315840
StyleLoss:updateOutput self.G 2: 1.8076825141907
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010135401971638
dG 2: -2.8838559144873e-12
---
StyleLoss:updateOutput self.G 1: 6706895360
StyleLoss:updateOutput self.G 2: 38.166648864746
StyleLoss:updateGradInput self.gradInput 1: -5.6515712110183e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0690374842379e-05
dG 1: -0.010715141892433
dG 2: -6.0976203253293e-11
---
StyleLoss:updateOutput self.G 1: 3040807424
StyleLoss:updateOutput self.G 2: 34.577766418457
StyleLoss:updateGradInput self.gradInput 1: -1.0569246811087e-08
StyleLoss:updateGradInput self.gradInput 2: -6.190303247422e-05
dG 1: -0.0026744820643216
dG 2: -3.0412190127338e-11
---
StyleLoss:updateOutput self.G 1: 187624048
StyleLoss:updateOutput self.G 2: 4.2594976425171
StyleLoss:updateGradInput self.gradInput 1: -1.919169179132e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011968218313996
dG 1: -0.00014805296086706
dG 2: -3.3611436116993e-12
---
StyleLoss:updateOutput self.G 1: 3046771.5
StyleLoss:updateOutput self.G 2: 0.27570086717606
StyleLoss:updateGradInput self.gradInput 1: -9.0406125252684e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054243672639132
dG 1: -3.280144665041e-05
dG 2: -2.9681860268249e-12
---
Iteration 56 / 2500
Content 1 loss: 548678.076172
Style 1 loss: 71941.675186
Style 2 loss: 72412195.312500
Style 3 loss: 91266527.343750
Style 4 loss: 5839925.903320
Style 5 loss: 220648.475647
Total loss: 170359916.786575
---
x1 value: -5.1982283592224
feval(x) grad value: 3.3565645916087e-17
---
StyleLoss:updateOutput self.G 1: 633162240
StyleLoss:updateOutput self.G 2: 1.8015547990799
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010165324201807
dG 2: -2.892369286786e-12
---
StyleLoss:updateOutput self.G 1: 6673142272
StyleLoss:updateOutput self.G 2: 37.97456741333
StyleLoss:updateGradInput self.gradInput 1: -5.6518683066997e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0470409910777e-05
dG 1: -0.010738587938249
dG 2: -6.1109638183066e-11
---
StyleLoss:updateOutput self.G 1: 3011173376
StyleLoss:updateOutput self.G 2: 34.240787506104
StyleLoss:updateGradInput self.gradInput 1: -1.057831067186e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1821272538509e-05
dG 1: -0.0026847657281905
dG 2: -3.0529124367407e-11
---
StyleLoss:updateOutput self.G 1: 185213008
StyleLoss:updateOutput self.G 2: 4.2047634124756
StyleLoss:updateGradInput self.gradInput 1: -1.9185200983429e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011954832734773
dG 1: -0.00014847052807454
dG 2: -3.3706238754955e-12
---
StyleLoss:updateOutput self.G 1: 2974948.5
StyleLoss:updateOutput self.G 2: 0.2692015171051
StyleLoss:updateGradInput self.gradInput 1: -9.0409635333799e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054245773935691
dG 1: -3.2851028663572e-05
dG 2: -2.9726726722551e-12
---
Iteration 57 / 2500
Content 1 loss: 546094.873047
Style 1 loss: 72477.979660
Style 2 loss: 72698267.578125
Style 3 loss: 91709255.859375
Style 4 loss: 5858247.070312
Style 5 loss: 221210.426331
Total loss: 171105553.786850
---
x1 value: -5.182192325592
feval(x) grad value: 1.943274071811e-17
---
StyleLoss:updateOutput self.G 1: 631057664
StyleLoss:updateOutput self.G 2: 1.7955667972565
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071979527827e-05
dG 1: -0.0010194561909884
dG 2: -2.900688586896e-12
---
StyleLoss:updateOutput self.G 1: 6640386560
StyleLoss:updateOutput self.G 2: 37.78816986084
StyleLoss:updateGradInput self.gradInput 1: -5.6521685110056e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0254072044045e-05
dG 1: -0.010761342942715
dG 2: -6.1239117943312e-11
---
StyleLoss:updateOutput self.G 1: 2982402560
StyleLoss:updateOutput self.G 2: 33.913635253906
StyleLoss:updateGradInput self.gradInput 1: -1.0587296372933e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1735445342492e-05
dG 1: -0.0026947497390211
dG 2: -3.0642658549462e-11
---
StyleLoss:updateOutput self.G 1: 182882784
StyleLoss:updateOutput self.G 2: 4.1518616676331
StyleLoss:updateGradInput self.gradInput 1: -1.9179219989951e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011938509851461
dG 1: -0.0001488741254434
dG 2: -3.3797864680551e-12
---
StyleLoss:updateOutput self.G 1: 2905864
StyleLoss:updateOutput self.G 2: 0.26295018196106
StyleLoss:updateGradInput self.gradInput 1: -9.0412960673802e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054247776279226
dG 1: -3.2898726203712e-05
dG 2: -2.9769884474229e-12
---
Iteration 58 / 2500
Content 1 loss: 543625.195312
Style 1 loss: 73006.233215
Style 2 loss: 72975750.000000
Style 3 loss: 92138015.625000
Style 4 loss: 5875870.605469
Style 5 loss: 221751.182556
Total loss: 171828018.841553
---
x1 value: -5.166437625885
feval(x) grad value: 2.6499192489918e-17
---
StyleLoss:updateOutput self.G 1: 628997504
StyleLoss:updateOutput self.G 2: 1.7897047996521
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010223186109215
dG 2: -2.9088328967752e-12
---
StyleLoss:updateOutput self.G 1: 6608575488
StyleLoss:updateOutput self.G 2: 37.6071434021
StyleLoss:updateGradInput self.gradInput 1: -5.6524669389546e-09
StyleLoss:updateGradInput self.gradInput 2: -3.00592109852e-05
dG 1: -0.010783441364765
dG 2: -6.1364878456427e-11
---
StyleLoss:updateOutput self.G 1: 2954459392
StyleLoss:updateOutput self.G 2: 33.595890045166
StyleLoss:updateGradInput self.gradInput 1: -1.0596168387167e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1657141486648e-05
dG 1: -0.0027044464368373
dG 2: -3.0752921043042e-11
---
StyleLoss:updateOutput self.G 1: 180639152
StyleLoss:updateOutput self.G 2: 4.1009259223938
StyleLoss:updateGradInput self.gradInput 1: -1.9173446830223e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011922953854082
dG 1: -0.0001492627634434
dG 2: -3.3886090548135e-12
---
StyleLoss:updateOutput self.G 1: 2839734.25
StyleLoss:updateOutput self.G 2: 0.25696614384651
StyleLoss:updateGradInput self.gradInput 1: -9.0416172326968e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054249702952802
dG 1: -3.2944382837741e-05
dG 2: -2.9811203419022e-12
---
Iteration 59 / 2500
Content 1 loss: 541270.312500
Style 1 loss: 73528.896332
Style 2 loss: 73245123.046875
Style 3 loss: 92553761.718750
Style 4 loss: 5892808.593750
Style 5 loss: 222268.661499
Total loss: 172528761.229706
---
x1 value: -5.1509590148926
feval(x) grad value: 3.3565645916087e-17
---
StyleLoss:updateOutput self.G 1: 626980544
StyleLoss:updateOutput self.G 2: 1.7839660644531
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010251207277179
dG 2: -2.9168056858708e-12
---
StyleLoss:updateOutput self.G 1: 6577662464
StyleLoss:updateOutput self.G 2: 37.431228637695
StyleLoss:updateGradInput self.gradInput 1: -5.6527675873497e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9871222068323e-05
dG 1: -0.010804914869368
dG 2: -6.1487079316969e-11
---
StyleLoss:updateOutput self.G 1: 2927325952
StyleLoss:updateOutput self.G 2: 33.287334442139
StyleLoss:updateGradInput self.gradInput 1: -1.0604943589954e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1582082707901e-05
dG 1: -0.002713862573728
dG 2: -3.0859995114874e-11
---
StyleLoss:updateOutput self.G 1: 178484992
StyleLoss:updateOutput self.G 2: 4.0520210266113
StyleLoss:updateGradInput self.gradInput 1: -1.9167778475548e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011909308523173
dG 1: -0.00014963588910177
dG 2: -3.3970794927063e-12
---
StyleLoss:updateOutput self.G 1: 2776164.5
StyleLoss:updateOutput self.G 2: 0.25121361017227
StyleLoss:updateGradInput self.gradInput 1: -9.0419256082441e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054251553956419
dG 1: -3.2988260500133e-05
dG 2: -2.9850913407792e-12
---
Iteration 60 / 2500
Content 1 loss: 539030.175781
Style 1 loss: 74045.408249
Style 2 loss: 73506796.875000
Style 3 loss: 92956804.687500
Style 4 loss: 5909042.724609
Style 5 loss: 222765.335083
Total loss: 173208485.206223
---
x1 value: -5.1357421875
feval(x) grad value: -2.6499192489918e-17
---
StyleLoss:updateOutput self.G 1: 625006400
StyleLoss:updateOutput self.G 2: 1.7783489227295
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010278633562848
dG 2: -2.9246095562679e-12
---
StyleLoss:updateOutput self.G 1: 6547592704
StyleLoss:updateOutput self.G 2: 37.260105133057
StyleLoss:updateGradInput self.gradInput 1: -5.6530695680124e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9680642910535e-05
dG 1: -0.010825804434717
dG 2: -6.1605949508436e-11
---
StyleLoss:updateOutput self.G 1: 2900961792
StyleLoss:updateOutput self.G 2: 32.987548828125
StyleLoss:updateGradInput self.gradInput 1: -1.0613650403002e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1510625528172e-05
dG 1: -0.0027230111882091
dG 2: -3.0964033420622e-11
---
StyleLoss:updateOutput self.G 1: 176407504
StyleLoss:updateOutput self.G 2: 4.0048565864563
StyleLoss:updateGradInput self.gradInput 1: -1.9162623488e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011895657371497
dG 1: -0.00014999571430963
dG 2: -3.4052483055547e-12
---
StyleLoss:updateOutput self.G 1: 2714793.75
StyleLoss:updateOutput self.G 2: 0.24566023051739
StyleLoss:updateGradInput self.gradInput 1: -9.0422311416205e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054253387497738
dG 1: -3.3030642953236e-05
dG 2: -2.9889252965015e-12
---
Iteration 61 / 2500
Content 1 loss: 536905.761719
Style 1 loss: 74554.824829
Style 2 loss: 73761199.218750
Style 3 loss: 93347724.609375
Style 4 loss: 5924635.986328
Style 5 loss: 223244.110107
Total loss: 173868264.511108
---
x1 value: -5.1207814216614
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 623073408
StyleLoss:updateOutput self.G 2: 1.7728488445282
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010305491741747
dG 2: -2.9322512300201e-12
---
StyleLoss:updateOutput self.G 1: 6518325248
StyleLoss:updateOutput self.G 2: 37.093563079834
StyleLoss:updateGradInput self.gradInput 1: -5.6533724368535e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9515977075789e-05
dG 1: -0.010846133343875
dG 2: -6.1721634747602e-11
---
StyleLoss:updateOutput self.G 1: 2875323136
StyleLoss:updateOutput self.G 2: 32.696006774902
StyleLoss:updateGradInput self.gradInput 1: -1.0622333235233e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1447477492038e-05
dG 1: -0.0027319090440869
dG 2: -3.1065195554847e-11
---
StyleLoss:updateOutput self.G 1: 174405184
StyleLoss:updateOutput self.G 2: 3.959400177002
StyleLoss:updateGradInput self.gradInput 1: -1.9158260755603e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001188101596199
dG 1: -0.00015034248644952
dG 2: -3.4131219985717e-12
---
StyleLoss:updateOutput self.G 1: 2655877
StyleLoss:updateOutput self.G 2: 0.2403289526701
StyleLoss:updateGradInput self.gradInput 1: -9.0425409382533e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054255221039057
dG 1: -3.3071308280341e-05
dG 2: -2.9926059460367e-12
---
Iteration 62 / 2500
Content 1 loss: 534878.125000
Style 1 loss: 75058.078766
Style 2 loss: 74008623.046875
Style 3 loss: 93726861.328125
Style 4 loss: 5939564.575195
Style 5 loss: 223702.789307
Total loss: 174508687.943268
---
x1 value: -5.1060671806335
feval(x) grad value: -1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 621177408
StyleLoss:updateOutput self.G 2: 1.7674541473389
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071979527827e-05
dG 1: -0.0010331831872463
dG 2: -2.939746102798e-12
---
StyleLoss:updateOutput self.G 1: 6489822208
StyleLoss:updateOutput self.G 2: 36.9313621521
StyleLoss:updateGradInput self.gradInput 1: -5.6536753056946e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9353710488067e-05
dG 1: -0.010865934193134
dG 2: -6.1834315445708e-11
---
StyleLoss:updateOutput self.G 1: 2850330368
StyleLoss:updateOutput self.G 2: 32.411808013916
StyleLoss:updateGradInput self.gradInput 1: -1.0631047153709e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1390310293064e-05
dG 1: -0.0027405822183937
dG 2: -3.1163828462244e-11
---
StyleLoss:updateOutput self.G 1: 172472768
StyleLoss:updateOutput self.G 2: 3.9155304431915
StyleLoss:updateGradInput self.gradInput 1: -1.9154656527576e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011869099398609
dG 1: -0.0001506772096036
dG 2: -3.4207203042369e-12
---
StyleLoss:updateOutput self.G 1: 2599385.75
StyleLoss:updateOutput self.G 2: 0.23521709442139
StyleLoss:updateGradInput self.gradInput 1: -9.0428414978305e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054257048759609
dG 1: -3.3110307413153e-05
dG 2: -2.9961350241081e-12
---
Iteration 63 / 2500
Content 1 loss: 532934.667969
Style 1 loss: 75556.526184
Style 2 loss: 74249431.640625
Style 3 loss: 94095023.437500
Style 4 loss: 5953862.182617
Style 5 loss: 224142.379761
Total loss: 175130950.834656
---
x1 value: -5.0915923118591
feval(x) grad value: -1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 619318784
StyleLoss:updateOutput self.G 2: 1.7621657848358
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010357652790844
dG 2: -2.9470930903996e-12
---
StyleLoss:updateOutput self.G 1: 6462046720
StyleLoss:updateOutput self.G 2: 36.773292541504
StyleLoss:updateGradInput self.gradInput 1: -5.6539772863573e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9200582503108e-05
dG 1: -0.010885230265558
dG 2: -6.1944116502843e-11
---
StyleLoss:updateOutput self.G 1: 2825946624
StyleLoss:updateOutput self.G 2: 32.134521484375
StyleLoss:updateGradInput self.gradInput 1: -1.063980814564e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1337770603132e-05
dG 1: -0.002749043982476
dG 2: -3.1260046634562e-11
---
StyleLoss:updateOutput self.G 1: 170604528
StyleLoss:updateOutput self.G 2: 3.8731157779694
StyleLoss:updateGradInput self.gradInput 1: -1.9151423558128e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011858544166898
dG 1: -0.00015100080054253
dG 2: -3.4280666413172e-12
---
StyleLoss:updateOutput self.G 1: 2544538
StyleLoss:updateOutput self.G 2: 0.23025396466255
StyleLoss:updateGradInput self.gradInput 1: -9.0431392152368e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054258841555566
dG 1: -3.3148182410514e-05
dG 2: -2.999561536654e-12
---
Iteration 64 / 2500
Content 1 loss: 531061.035156
Style 1 loss: 76048.439026
Style 2 loss: 74483935.546875
Style 3 loss: 94452755.859375
Style 4 loss: 5967628.417969
Style 5 loss: 224568.717957
Total loss: 175735998.016357
---
x1 value: -5.0773496627808
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 617494400
StyleLoss:updateOutput self.G 2: 1.7569750547409
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010382999898866
dG 2: -2.954305203251e-12
---
StyleLoss:updateOutput self.G 1: 6434967552
StyleLoss:updateOutput self.G 2: 36.619197845459
StyleLoss:updateGradInput self.gradInput 1: -5.6542823756445e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9056696803309e-05
dG 1: -0.010904039256275
dG 2: -6.2051162819099e-11
---
StyleLoss:updateOutput self.G 1: 2802154496
StyleLoss:updateOutput self.G 2: 31.863985061646
StyleLoss:updateGradInput self.gradInput 1: -1.064860999378e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1289829318412e-05
dG 1: -0.0027572996914387
dG 2: -3.1353933338529e-11
---
StyleLoss:updateOutput self.G 1: 168798448
StyleLoss:updateOutput self.G 2: 3.8321139812469
StyleLoss:updateGradInput self.gradInput 1: -1.9148679086811e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011846326378873
dG 1: -0.00015131360851228
dG 2: -3.435168165547e-12
---
StyleLoss:updateOutput self.G 1: 2491213.25
StyleLoss:updateOutput self.G 2: 0.22542861104012
StyleLoss:updateGradInput self.gradInput 1: -9.0434348010149e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054260605247691
dG 1: -3.3184991480084e-05
dG 2: -3.0028928562492e-12
---
Iteration 65 / 2500
Content 1 loss: 529257.519531
Style 1 loss: 76535.825729
Style 2 loss: 74712386.718750
Style 3 loss: 94800269.531250
Style 4 loss: 5980864.379883
Style 5 loss: 224982.994080
Total loss: 176324296.969223
---
x1 value: -5.0633330345154
feval(x) grad value: 1.766612942952e-17
---
StyleLoss:updateOutput self.G 1: 615704128
StyleLoss:updateOutput self.G 2: 1.7518807649612
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010407874360681
dG 2: -2.9613824413521e-12
---
StyleLoss:updateOutput self.G 1: 6408552960
StyleLoss:updateOutput self.G 2: 36.46887588501
StyleLoss:updateGradInput self.gradInput 1: -5.6545848003964e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8913889764226e-05
dG 1: -0.010922387242317
dG 2: -6.2155572355671e-11
---
StyleLoss:updateOutput self.G 1: 2778929152
StyleLoss:updateOutput self.G 2: 31.599880218506
StyleLoss:updateGradInput self.gradInput 1: -1.0657423388238e-08
StyleLoss:updateGradInput self.gradInput 2: -6.123908679001e-05
dG 1: -0.00276535958983
dG 2: -3.1445582249212e-11
---
StyleLoss:updateOutput self.G 1: 167051632
StyleLoss:updateOutput self.G 2: 3.7924571037292
StyleLoss:updateGradInput self.gradInput 1: -1.9146151331029e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011832936434075
dG 1: -0.00015161617193371
dG 2: -3.442037236831e-12
---
StyleLoss:updateOutput self.G 1: 2439463.75
StyleLoss:updateOutput self.G 2: 0.22074584662914
StyleLoss:updateGradInput self.gradInput 1: -9.0437197286519e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054262316552922
dG 1: -3.322071643197e-05
dG 2: -3.006126163968e-12
---
Iteration 66 / 2500
Content 1 loss: 527518.115234
Style 1 loss: 77017.530441
Style 2 loss: 74935060.546875
Style 3 loss: 95138173.828125
Style 4 loss: 5993611.083984
Style 5 loss: 225385.322571
Total loss: 176896766.427231
---
x1 value: -5.0495400428772
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 613945728
StyleLoss:updateOutput self.G 2: 1.7468779087067
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.001043230178766
dG 2: -2.9683330446395e-12
---
StyleLoss:updateOutput self.G 1: 6382766592
StyleLoss:updateOutput self.G 2: 36.322147369385
StyleLoss:updateGradInput self.gradInput 1: -5.6548872251483e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8786131224479e-05
dG 1: -0.010940303094685
dG 2: -6.2257504707119e-11
---
StyleLoss:updateOutput self.G 1: 2756265216
StyleLoss:updateOutput self.G 2: 31.342166900635
StyleLoss:updateGradInput self.gradInput 1: -1.0666219907307e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1197752074804e-05
dG 1: -0.0027732248418033
dG 2: -3.153501765274e-11
---
StyleLoss:updateOutput self.G 1: 165354720
StyleLoss:updateOutput self.G 2: 3.7539341449738
StyleLoss:updateGradInput self.gradInput 1: -1.914427905092e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011820210784208
dG 1: -0.00015191010606941
dG 2: -3.44870920016e-12
---
StyleLoss:updateOutput self.G 1: 2389115.5
StyleLoss:updateOutput self.G 2: 0.21618987619877
StyleLoss:updateGradInput self.gradInput 1: -9.0439947086907e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054263969650492
dG 1: -3.325548095745e-05
dG 2: -3.0092710007895e-12
---
Iteration 67 / 2500
Content 1 loss: 525829.541016
Style 1 loss: 77495.292664
Style 2 loss: 75152273.437500
Style 3 loss: 95466744.140625
Style 4 loss: 6005909.545898
Style 5 loss: 225777.763367
Total loss: 177454029.721069
---
x1 value: -5.0359616279602
feval(x) grad value: -4.4165320265076e-17
---
StyleLoss:updateOutput self.G 1: 612218880
StyleLoss:updateOutput self.G 2: 1.7419642210007
StyleLoss:updateGradInput self.gradInput 1: -2.8453297495901e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010456293821335
dG 2: -2.9751596151983e-12
---
StyleLoss:updateOutput self.G 1: 6357580800
StyleLoss:updateOutput self.G 2: 36.178821563721
StyleLoss:updateGradInput self.gradInput 1: -5.6551923144355e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8668431696133e-05
dG 1: -0.010957797057927
dG 2: -6.2357070895747e-11
---
StyleLoss:updateOutput self.G 1: 2734129408
StyleLoss:updateOutput self.G 2: 31.090448379517
StyleLoss:updateGradInput self.gradInput 1: -1.0674995998272e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1167258536443e-05
dG 1: -0.00278090685606
dG 2: -3.1622371388096e-11
---
StyleLoss:updateOutput self.G 1: 163707568
StyleLoss:updateOutput self.G 2: 3.7165403366089
StyleLoss:updateGradInput self.gradInput 1: -1.9142827767382e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011809911666205
dG 1: -0.00015219539636746
dG 2: -3.4551868744598e-12
---
StyleLoss:updateOutput self.G 1: 2340079.75
StyleLoss:updateOutput self.G 2: 0.21175260841846
StyleLoss:updateGradInput self.gradInput 1: -9.0442604516738e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054265564540401
dG 1: -3.328933235025e-05
dG 2: -3.0123345224481e-12
---
Iteration 68 / 2500
Content 1 loss: 524188.183594
Style 1 loss: 77967.853546
Style 2 loss: 75364277.343750
Style 3 loss: 95786566.406250
Style 4 loss: 6017802.978516
Style 5 loss: 226160.453796
Total loss: 177996963.219452
---
x1 value: -5.0226001739502
feval(x) grad value: -4.769854615098e-17
---
StyleLoss:updateOutput self.G 1: 610522240
StyleLoss:updateOutput self.G 2: 1.7371366024017
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010479865595698
dG 2: -2.9818669235182e-12
---
StyleLoss:updateOutput self.G 1: 6332966912
StyleLoss:updateOutput self.G 2: 36.038749694824
StyleLoss:updateGradInput self.gradInput 1: -5.6554938510089e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8557076802826e-05
dG 1: -0.010974894277751
dG 2: -6.2454375004961e-11
---
StyleLoss:updateOutput self.G 1: 2712494080
StyleLoss:updateOutput self.G 2: 30.844434738159
StyleLoss:updateGradInput self.gradInput 1: -1.0683762319275e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1136583099142e-05
dG 1: -0.0027884147129953
dG 2: -3.1707740599796e-11
---
StyleLoss:updateOutput self.G 1: 162108240
StyleLoss:updateOutput self.G 2: 3.6802310943604
StyleLoss:updateGradInput self.gradInput 1: -1.9142030183161e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011801112123067
dG 1: -0.00015247237752192
dG 2: -3.4614750302198e-12
---
StyleLoss:updateOutput self.G 1: 2292466.75
StyleLoss:updateOutput self.G 2: 0.20744410157204
StyleLoss:updateGradInput self.gradInput 1: -9.0445169576014e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054267107043415
dG 1: -3.3322201488772e-05
dG 2: -3.0153089226881e-12
---
Iteration 69 / 2500
Content 1 loss: 522595.849609
Style 1 loss: 78435.253143
Style 2 loss: 75571312.500000
Style 3 loss: 96097857.421875
Style 4 loss: 6029273.803711
Style 5 loss: 226532.180786
Total loss: 178526007.009125
---
x1 value: -5.0094413757324
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 608854656
StyleLoss:updateOutput self.G 2: 1.7323919534683
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010503033408895
dG 2: -2.988458439046e-12
---
StyleLoss:updateOutput self.G 1: 6308892672
StyleLoss:updateOutput self.G 2: 35.901752471924
StyleLoss:updateGradInput self.gradInput 1: -5.6557958316716e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8458649467211e-05
dG 1: -0.010991618968546
dG 2: -6.2549541934853e-11
---
StyleLoss:updateOutput self.G 1: 2691351040
StyleLoss:updateOutput self.G 2: 30.604013442993
StyleLoss:updateGradInput self.gradInput 1: -1.0692496665854e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1105980421416e-05
dG 1: -0.0027957512065768
dG 2: -3.1791170390649e-11
---
StyleLoss:updateOutput self.G 1: 160554240
StyleLoss:updateOutput self.G 2: 3.6449518203735
StyleLoss:updateGradInput self.gradInput 1: -1.9142065710298e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011793331213994
dG 1: -0.00015274155884981
dG 2: -3.4675860273448e-12
---
StyleLoss:updateOutput self.G 1: 2246194
StyleLoss:updateOutput self.G 2: 0.20325689017773
StyleLoss:updateGradInput self.gradInput 1: -9.0447642264735e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054268579697236
dG 1: -3.3354150218656e-05
dG 2: -3.0181996225204e-12
---
Iteration 70 / 2500
Content 1 loss: 521054.980469
Style 1 loss: 78898.155212
Style 2 loss: 75773677.734375
Style 3 loss: 96400904.296875
Style 4 loss: 6040324.951172
Style 5 loss: 226893.882751
Total loss: 179041754.000854
---
x1 value: -4.9964909553528
feval(x) grad value: -2.8265807087231e-17
---
StyleLoss:updateOutput self.G 1: 607213568
StyleLoss:updateOutput self.G 2: 1.7277224063873
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071981346817e-05
dG 1: -0.0010525833349675
dG 2: -2.9949463048462e-12
---
StyleLoss:updateOutput self.G 1: 6285345280
StyleLoss:updateOutput self.G 2: 35.767749786377
StyleLoss:updateGradInput self.gradInput 1: -5.6560942596207e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8361815566313e-05
dG 1: -0.011007976718247
dG 2: -6.2642634135468e-11
---
StyleLoss:updateOutput self.G 1: 2670685696
StyleLoss:updateOutput self.G 2: 30.36901473999
StyleLoss:updateGradInput self.gradInput 1: -1.0701172392658e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1080332670826e-05
dG 1: -0.0028029230888933
dG 2: -3.1872719741255e-11
---
StyleLoss:updateOutput self.G 1: 159039792
StyleLoss:updateOutput self.G 2: 3.6105699539185
StyleLoss:updateGradInput self.gradInput 1: -1.9143165275182e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011784955859184
dG 1: -0.0001530038571218
dG 2: -3.4735406825165e-12
---
StyleLoss:updateOutput self.G 1: 2201136.25
StyleLoss:updateOutput self.G 2: 0.19917970895767
StyleLoss:updateGradInput self.gradInput 1: -9.0450036793754e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054270029067993
dG 1: -3.3385262213415e-05
dG 2: -3.0210144282006e-12
---
Iteration 71 / 2500
Content 1 loss: 519557.373047
Style 1 loss: 79357.915878
Style 2 loss: 75971519.531250
Style 3 loss: 96696169.921875
Style 4 loss: 6050975.097656
Style 5 loss: 227246.109009
Total loss: 179544825.948715
---
x1 value: -4.9837393760681
feval(x) grad value: -2.1199353661062e-17
---
StyleLoss:updateOutput self.G 1: 605599424
StyleLoss:updateOutput self.G 2: 1.7231295108795
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0010548259597272
dG 2: -3.0013270514717e-12
---
StyleLoss:updateOutput self.G 1: 6262289920
StyleLoss:updateOutput self.G 2: 35.636558532715
StyleLoss:updateGradInput self.gradInput 1: -5.6563931316589e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8279489924898e-05
dG 1: -0.01102399174124
dG 2: -6.2733755690214e-11
---
StyleLoss:updateOutput self.G 1: 2650477056
StyleLoss:updateOutput self.G 2: 30.139219284058
StyleLoss:updateGradInput self.gradInput 1: -1.0709776177009e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1062615714036e-05
dG 1: -0.0028099352493882
dG 2: -3.1952464979446e-11
---
StyleLoss:updateOutput self.G 1: 157562944
StyleLoss:updateOutput self.G 2: 3.5770423412323
StyleLoss:updateGradInput self.gradInput 1: -1.9145279139821e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011776219616877
dG 1: -0.00015325967979152
dG 2: -3.4793476693523e-12
---
StyleLoss:updateOutput self.G 1: 2157473.25
StyleLoss:updateOutput self.G 2: 0.19522865116596
StyleLoss:updateGradInput self.gradInput 1: -9.04523602685e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054271414410323
dG 1: -3.3415399229852e-05
dG 2: -3.0237420640261e-12
---
Iteration 72 / 2500
Content 1 loss: 518105.664062
Style 1 loss: 79813.213348
Style 2 loss: 76165107.421875
Style 3 loss: 96984046.875000
Style 4 loss: 6061230.102539
Style 5 loss: 227587.440491
Total loss: 180035890.717316
---
x1 value: -4.9711833000183
feval(x) grad value: -4.2398707322124e-17
---
StyleLoss:updateOutput self.G 1: 604009536
StyleLoss:updateOutput self.G 2: 1.7186058759689
StyleLoss:updateGradInput self.gradInput 1: -2.8453297495901e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0010570348240435
dG 2: -3.007612388306e-12
---
StyleLoss:updateOutput self.G 1: 6239709696
StyleLoss:updateOutput self.G 2: 35.508060455322
StyleLoss:updateGradInput self.gradInput 1: -5.6566888950726e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8198337531649e-05
dG 1: -0.011039676144719
dG 2: -6.2823031499182e-11
---
StyleLoss:updateOutput self.G 1: 2630706432
StyleLoss:updateOutput self.G 2: 29.914405822754
StyleLoss:updateGradInput self.gradInput 1: -1.0718287590805e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1050377553329e-05
dG 1: -0.0028167965356261
dG 2: -3.2030482433054e-11
---
StyleLoss:updateOutput self.G 1: 156125488
StyleLoss:updateOutput self.G 2: 3.5444090366364
StyleLoss:updateGradInput self.gradInput 1: -1.9148322039086e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011769298725994
dG 1: -0.00015350866306107
dG 2: -3.4850004826392e-12
---
StyleLoss:updateOutput self.G 1: 2115101.5
StyleLoss:updateOutput self.G 2: 0.19139444828033
StyleLoss:updateGradInput self.gradInput 1: -9.0454555845554e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054272741544992
dG 1: -3.3444648579462e-05
dG 2: -3.0263896857313e-12
---
Iteration 73 / 2500
Content 1 loss: 516694.677734
Style 1 loss: 80264.591217
Style 2 loss: 76354623.046875
Style 3 loss: 97264898.437500
Style 4 loss: 6071097.656250
Style 5 loss: 227918.930054
Total loss: 180515497.339630
---
x1 value: -4.9588170051575
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 602444544
StyleLoss:updateOutput self.G 2: 1.7141528129578
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0010592091130093
dG 2: -3.0137988459022e-12
---
StyleLoss:updateOutput self.G 1: 6217587200
StyleLoss:updateOutput self.G 2: 35.382164001465
StyleLoss:updateGradInput self.gradInput 1: -5.6569824380404e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8121743525844e-05
dG 1: -0.011055044829845
dG 2: -6.2910482379053e-11
---
StyleLoss:updateOutput self.G 1: 2611345408
StyleLoss:updateOutput self.G 2: 29.694246292114
StyleLoss:updateGradInput self.gradInput 1: -1.0726711963116e-08
StyleLoss:updateGradInput self.gradInput 2: -6.104107160354e-05
dG 1: -0.0028235150966793
dG 2: -3.2106879654936e-11
---
StyleLoss:updateOutput self.G 1: 154721632
StyleLoss:updateOutput self.G 2: 3.512538433075
StyleLoss:updateGradInput self.gradInput 1: -1.91523383819e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011763297516154
dG 1: -0.00015375182556454
dG 2: -3.4905205895802e-12
---
StyleLoss:updateOutput self.G 1: 2073923.375
StyleLoss:updateOutput self.G 2: 0.18766829371452
StyleLoss:updateGradInput self.gradInput 1: -9.0456644841197e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054273998830467
dG 1: -3.3473086659797e-05
dG 2: -3.0289616301249e-12
---
Iteration 74 / 2500
Content 1 loss: 515321.777344
Style 1 loss: 80711.769104
Style 2 loss: 76540183.593750
Style 3 loss: 97539128.906250
Style 4 loss: 6080615.844727
Style 5 loss: 228241.081238
Total loss: 180984202.972412
---
x1 value: -4.9466366767883
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 600904192
StyleLoss:updateOutput self.G 2: 1.7097699642181
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010613491758704
dG 2: -3.0198877253029e-12
---
StyleLoss:updateOutput self.G 1: 6195896832
StyleLoss:updateOutput self.G 2: 35.258728027344
StyleLoss:updateGradInput self.gradInput 1: -5.6572733164728e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8055084840162e-05
dG 1: -0.01107011269778
dG 2: -6.2996226291023e-11
---
StyleLoss:updateOutput self.G 1: 2592383744
StyleLoss:updateOutput self.G 2: 29.478628158569
StyleLoss:updateGradInput self.gradInput 1: -1.0735046629406e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1030830693198e-05
dG 1: -0.0028300951234996
dG 2: -3.2181705217349e-11
---
StyleLoss:updateOutput self.G 1: 153352176
StyleLoss:updateOutput self.G 2: 3.4814484119415
StyleLoss:updateGradInput self.gradInput 1: -1.9157173625217e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011757785978261
dG 1: -0.00015398897812702
dG 2: -3.4959051712496e-12
---
StyleLoss:updateOutput self.G 1: 2033941.125
StyleLoss:updateOutput self.G 2: 0.18405032157898
StyleLoss:updateGradInput self.gradInput 1: -9.0458676993421e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054275209549814
dG 1: -3.3500684367027e-05
dG 2: -3.0314591982494e-12
---
Iteration 75 / 2500
Content 1 loss: 513981.201172
Style 1 loss: 81153.511047
Style 2 loss: 76722041.015625
Style 3 loss: 97806943.359375
Style 4 loss: 6089801.513672
Style 5 loss: 228553.916931
Total loss: 181442474.517822
---
x1 value: -4.934636592865
feval(x) grad value: -2.1199353661062e-17
---
StyleLoss:updateOutput self.G 1: 599385152
StyleLoss:updateOutput self.G 2: 1.7054480314255
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010634596692398
dG 2: -3.0258926874555e-12
---
StyleLoss:updateOutput self.G 1: 6174627840
StyleLoss:updateOutput self.G 2: 35.1376953125
StyleLoss:updateGradInput self.gradInput 1: -5.6575624185484e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7993963158224e-05
dG 1: -0.011084886267781
dG 2: -6.3080297929563e-11
---
StyleLoss:updateOutput self.G 1: 2573807872
StyleLoss:updateOutput self.G 2: 29.267402648926
StyleLoss:updateGradInput self.gradInput 1: -1.0743277378822e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1020058637951e-05
dG 1: -0.0028365412726998
dG 2: -3.225500769255e-11
---
StyleLoss:updateOutput self.G 1: 152016464
StyleLoss:updateOutput self.G 2: 3.4511249065399
StyleLoss:updateGradInput self.gradInput 1: -1.9162788689187e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011754022852983
dG 1: -0.00015422032447532
dG 2: -3.5011576970945e-12
---
StyleLoss:updateOutput self.G 1: 1995056.375
StyleLoss:updateOutput self.G 2: 0.18053163588047
StyleLoss:updateGradInput self.gradInput 1: -9.046058835338e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054276367882267
dG 1: -3.3527529012645e-05
dG 2: -3.0338891121584e-12
---
Iteration 76 / 2500
Content 1 loss: 512671.435547
Style 1 loss: 81593.290329
Style 2 loss: 76900253.906250
Style 3 loss: 98068699.218750
Style 4 loss: 6098664.184570
Style 5 loss: 228858.375549
Total loss: 181890740.410995
---
x1 value: -4.9228157997131
feval(x) grad value: -2.6499192489918e-17
---
StyleLoss:updateOutput self.G 1: 597888960
StyleLoss:updateOutput self.G 2: 1.7011907100677
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.001065538264811
dG 2: -3.0318070103064e-12
---
StyleLoss:updateOutput self.G 1: 6153763328
StyleLoss:updateOutput self.G 2: 35.018962860107
StyleLoss:updateGradInput self.gradInput 1: -5.6578461915535e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7938656785409e-05
dG 1: -0.01109938044101
dG 2: -6.3162787500293e-11
---
StyleLoss:updateOutput self.G 1: 2555607808
StyleLoss:updateOutput self.G 2: 29.060434341431
StyleLoss:updateGradInput self.gradInput 1: -1.0751386447794e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1018665292067e-05
dG 1: -0.0028428579680622
dG 2: -3.2326828713902e-11
---
StyleLoss:updateOutput self.G 1: 150713808
StyleLoss:updateOutput self.G 2: 3.4215514659882
StyleLoss:updateGradInput self.gradInput 1: -1.9169121401319e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011749366967706
dG 1: -0.00015444599557668
dG 2: -3.5062801186786e-12
---
StyleLoss:updateOutput self.G 1: 1957316.875
StyleLoss:updateOutput self.G 2: 0.17711661756039
StyleLoss:updateGradInput self.gradInput 1: -9.0462449975348e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054277473827824
dG 1: -3.355358785484e-05
dG 2: -3.0362466013623e-12
---
Iteration 77 / 2500
Content 1 loss: 511393.603516
Style 1 loss: 82028.703690
Style 2 loss: 77075021.484375
Style 3 loss: 98324589.843750
Style 4 loss: 6107219.238281
Style 5 loss: 229153.976440
Total loss: 182329406.850052
---
x1 value: -4.9111671447754
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 596414208
StyleLoss:updateOutput self.G 2: 1.6969949007034
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010675871744752
dG 2: -3.0376365485474e-12
---
StyleLoss:updateOutput self.G 1: 6133283840
StyleLoss:updateOutput self.G 2: 34.902420043945
StyleLoss:updateGradInput self.gradInput 1: -5.6581281882018e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7886268071597e-05
dG 1: -0.011113606393337
dG 2: -6.324374357547e-11
---
StyleLoss:updateOutput self.G 1: 2537764352
StyleLoss:updateOutput self.G 2: 28.857534408569
StyleLoss:updateGradInput self.gradInput 1: -1.0759382718106e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1019680288155e-05
dG 1: -0.0028490491677076
dG 2: -3.2397237670345e-11
---
StyleLoss:updateOutput self.G 1: 149444080
StyleLoss:updateOutput self.G 2: 3.3927249908447
StyleLoss:updateGradInput self.gradInput 1: -1.9176217946892e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011745219671866
dG 1: -0.00015466587501578
dG 2: -3.5112726528425e-12
---
StyleLoss:updateOutput self.G 1: 1920683.375
StyleLoss:updateOutput self.G 2: 0.17380166053772
StyleLoss:updateGradInput self.gradInput 1: -9.046421922676e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005427852156572
dG 1: -3.3578871807549e-05
dG 2: -3.0385355689888e-12
---
Iteration 78 / 2500
Content 1 loss: 510145.312500
Style 1 loss: 82459.407806
Style 2 loss: 77246478.515625
Style 3 loss: 98574832.031250
Style 4 loss: 6115464.477539
Style 5 loss: 229440.856934
Total loss: 182758820.601654
---
x1 value: -4.8996901512146
feval(x) grad value: -3.7098871801991e-17
---
StyleLoss:updateOutput self.G 1: 594959232
StyleLoss:updateOutput self.G 2: 1.6928548812866
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010696086101234
dG 2: -3.0433884579129e-12
---
StyleLoss:updateOutput self.G 1: 6113178624
StyleLoss:updateOutput self.G 2: 34.78800201416
StyleLoss:updateGradInput self.gradInput 1: -5.6584021912442e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7841231712955e-05
dG 1: -0.011127572506666
dG 2: -6.3323214727351e-11
---
StyleLoss:updateOutput self.G 1: 2520265984
StyleLoss:updateOutput self.G 2: 28.658555984497
StyleLoss:updateGradInput self.gradInput 1: -1.0767250202548e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1022707086522e-05
dG 1: -0.002855122089386
dG 2: -3.2466286603583e-11
---
StyleLoss:updateOutput self.G 1: 148204816
StyleLoss:updateOutput self.G 2: 3.3645911216736
StyleLoss:updateGradInput self.gradInput 1: -1.9183968191783e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011743253708119
dG 1: -0.00015488055942114
dG 2: -3.5161454910865e-12
---
StyleLoss:updateOutput self.G 1: 1885142.25
StyleLoss:updateOutput self.G 2: 0.17058555781841
StyleLoss:updateGradInput self.gradInput 1: -9.0465910318471e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054279563482851
dG 1: -3.3603406336624e-05
dG 2: -3.0407560150381e-12
---
Iteration 79 / 2500
Content 1 loss: 508928.515625
Style 1 loss: 82887.960434
Style 2 loss: 77414730.468750
Style 3 loss: 98819660.156250
Style 4 loss: 6123427.368164
Style 5 loss: 229719.337463
Total loss: 183179353.806686
---
x1 value: -4.8883814811707
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 593525760
StyleLoss:updateOutput self.G 2: 1.6887757778168
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010716003598645
dG 2: -3.049055365828e-12
---
StyleLoss:updateOutput self.G 1: 6093435392
StyleLoss:updateOutput self.G 2: 34.675666809082
StyleLoss:updateGradInput self.gradInput 1: -5.658670421127e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7797907023341e-05
dG 1: -0.011141288094223
dG 2: -6.3401263405982e-11
---
StyleLoss:updateOutput self.G 1: 2503092480
StyleLoss:updateOutput self.G 2: 28.463275909424
StyleLoss:updateGradInput self.gradInput 1: -1.0775004000152e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1028109485051e-05
dG 1: -0.002861081622541
dG 2: -3.2534055310895e-11
---
StyleLoss:updateOutput self.G 1: 146993360
StyleLoss:updateOutput self.G 2: 3.3370883464813
StyleLoss:updateGradInput self.gradInput 1: -1.9192393452272e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011740478657885
dG 1: -0.00015509036893491
dG 2: -3.5209099091132e-12
---
StyleLoss:updateOutput self.G 1: 1850727.625
StyleLoss:updateOutput self.G 2: 0.16747142374516
StyleLoss:updateGradInput self.gradInput 1: -9.0467523250481e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054280529730022
dG 1: -3.3627173252171e-05
dG 2: -3.0429053374248e-12
---
Iteration 80 / 2500
Content 1 loss: 507737.597656
Style 1 loss: 83312.828064
Style 2 loss: 77579876.953125
Style 3 loss: 99059390.625000
Style 4 loss: 6131129.150391
Style 5 loss: 229989.418030
Total loss: 183591436.572266
---
x1 value: -4.877236366272
feval(x) grad value: -2.4732579546966e-17
---
StyleLoss:updateOutput self.G 1: 592110592
StyleLoss:updateOutput self.G 2: 1.6847496032715
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010735662654042
dG 2: -3.0546491985167e-12
---
StyleLoss:updateOutput self.G 1: 6074045440
StyleLoss:updateOutput self.G 2: 34.565315246582
StyleLoss:updateGradInput self.gradInput 1: -5.658930657404e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7767784558819e-05
dG 1: -0.011154757812619
dG 2: -6.3477903489151e-11
---
StyleLoss:updateOutput self.G 1: 2486221824
StyleLoss:updateOutput self.G 2: 28.271438598633
StyleLoss:updateGradInput self.gradInput 1: -1.0782649439989e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1046695918776e-05
dG 1: -0.002866935916245
dG 2: -3.260062705901e-11
---
StyleLoss:updateOutput self.G 1: 145809152
StyleLoss:updateOutput self.G 2: 3.3102040290833
StyleLoss:updateGradInput self.gradInput 1: -1.9201481293862e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011737831664504
dG 1: -0.00015529546362814
dG 2: -3.5255656900823e-12
---
StyleLoss:updateOutput self.G 1: 1817260.25
StyleLoss:updateOutput self.G 2: 0.16444297134876
StyleLoss:updateGradInput self.gradInput 1: -9.0469079339073e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054281461052597
dG 1: -3.3650278055575e-05
dG 2: -3.0449961128942e-12
---
Iteration 81 / 2500
Content 1 loss: 506570.751953
Style 1 loss: 83735.561371
Style 2 loss: 77742005.859375
Style 3 loss: 99294292.968750
Style 4 loss: 6138580.078125
Style 5 loss: 230252.265930
Total loss: 183995437.485504
---
x1 value: -4.8662519454956
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 590715264
StyleLoss:updateOutput self.G 2: 1.6807794570923
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010755049297586
dG 2: -3.0601656191703e-12
---
StyleLoss:updateOutput self.G 1: 6054987264
StyleLoss:updateOutput self.G 2: 34.456855773926
StyleLoss:updateGradInput self.gradInput 1: -5.6591793473615e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7737933123717e-05
dG 1: -0.011167995631695
dG 2: -6.3553245999159e-11
---
StyleLoss:updateOutput self.G 1: 2469651712
StyleLoss:updateOutput self.G 2: 28.083011627197
StyleLoss:updateGradInput self.gradInput 1: -1.079018563388e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1058279243298e-05
dG 1: -0.0028726861346513
dG 2: -3.2666015725713e-11
---
StyleLoss:updateOutput self.G 1: 144648464
StyleLoss:updateOutput self.G 2: 3.2838542461395
StyleLoss:updateGradInput self.gradInput 1: -1.9211215729342e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011734670260921
dG 1: -0.00015549655654468
dG 2: -3.5301297475476e-12
---
StyleLoss:updateOutput self.G 1: 1784743
StyleLoss:updateOutput self.G 2: 0.16150046885014
StyleLoss:updateGradInput self.gradInput 1: -9.0470564373391e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054282345809042
dG 1: -3.3672724384815e-05
dG 2: -3.0470274740846e-12
---
Iteration 82 / 2500
Content 1 loss: 505427.246094
Style 1 loss: 84154.426575
Style 2 loss: 77901292.968750
Style 3 loss: 99524496.093750
Style 4 loss: 6145805.419922
Style 5 loss: 230507.835388
Total loss: 184391683.990479
---
x1 value: -4.8554272651672
feval(x) grad value: -1.5899516486568e-17
---
StyleLoss:updateOutput self.G 1: 589339008
StyleLoss:updateOutput self.G 2: 1.6768635511398
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.001077416818589
dG 2: -3.0656059288314e-12
---
StyleLoss:updateOutput self.G 1: 6036254208
StyleLoss:updateOutput self.G 2: 34.350257873535
StyleLoss:updateGradInput self.gradInput 1: -5.6594169350888e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7712992960005e-05
dG 1: -0.01118100900203
dG 2: -6.3627304813796e-11
---
StyleLoss:updateOutput self.G 1: 2453372672
StyleLoss:updateOutput self.G 2: 27.897897720337
StyleLoss:updateGradInput self.gradInput 1: -1.0797608140933e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1070299125277e-05
dG 1: -0.0028783355373889
dG 2: -3.2730256005475e-11
---
StyleLoss:updateOutput self.G 1: 143509552
StyleLoss:updateOutput self.G 2: 3.2579972743988
StyleLoss:updateGradInput self.gradInput 1: -1.9221728209118e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011733968858607
dG 1: -0.00015569377865177
dG 2: -3.5346079362009e-12
---
StyleLoss:updateOutput self.G 1: 1753175.5
StyleLoss:updateOutput self.G 2: 0.15864391624928
StyleLoss:updateGradInput self.gradInput 1: -9.0471971248007e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054283178178594
dG 1: -3.3694515877869e-05
dG 2: -3.0489992041555e-12
---
Iteration 83 / 2500
Content 1 loss: 504306.787109
Style 1 loss: 84569.194794
Style 2 loss: 78057832.031250
Style 3 loss: 99750164.062500
Style 4 loss: 6152797.119141
Style 5 loss: 230756.011963
Total loss: 184780425.206757
---
x1 value: -4.8447585105896
feval(x) grad value: 2.8265807087231e-17
---
StyleLoss:updateOutput self.G 1: 587981184
StyleLoss:updateOutput self.G 2: 1.6730000972748
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010793034452945
dG 2: -3.0709731632661e-12
---
StyleLoss:updateOutput self.G 1: 6017836032
StyleLoss:updateOutput self.G 2: 34.245445251465
StyleLoss:updateGradInput self.gradInput 1: -5.6596394237829e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7694728487404e-05
dG 1: -0.011193802580237
dG 2: -6.370011462753e-11
---
StyleLoss:updateOutput self.G 1: 2437380352
StyleLoss:updateOutput self.G 2: 27.716041564941
StyleLoss:updateGradInput self.gradInput 1: -1.0804914296614e-08
StyleLoss:updateGradInput self.gradInput 2: -6.108724483056e-05
dG 1: -0.0028838852886111
dG 2: -3.2793361776084e-11
---
StyleLoss:updateOutput self.G 1: 142391552
StyleLoss:updateOutput self.G 2: 3.2326171398163
StyleLoss:updateGradInput self.gradInput 1: -1.9232988535123e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001173546188511
dG 1: -0.00015588743553963
dG 2: -3.5390041591699e-12
---
StyleLoss:updateOutput self.G 1: 1722477.125
StyleLoss:updateOutput self.G 2: 0.15586607158184
StyleLoss:updateGradInput self.gradInput 1: -9.0473299962923e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054283981444314
dG 1: -3.3715714380378e-05
dG 2: -3.0509175914795e-12
---
Iteration 84 / 2500
Content 1 loss: 503211.181641
Style 1 loss: 84979.866028
Style 2 loss: 78211675.781250
Style 3 loss: 99971472.656250
Style 4 loss: 6159564.697266
Style 5 loss: 230997.413635
Total loss: 185161901.596069
---
x1 value: -4.8342418670654
feval(x) grad value: 2.2965966604014e-17
---
StyleLoss:updateOutput self.G 1: 586639360
StyleLoss:updateOutput self.G 2: 1.669182062149
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010811676038429
dG 2: -3.0762775139748e-12
---
StyleLoss:updateOutput self.G 1: 5999720448
StyleLoss:updateOutput self.G 2: 34.142360687256
StyleLoss:updateGradInput self.gradInput 1: -5.6598508102468e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7683530788636e-05
dG 1: -0.011206386610866
dG 2: -6.3771724012618e-11
---
StyleLoss:updateOutput self.G 1: 2421668608
StyleLoss:updateOutput self.G 2: 27.537391662598
StyleLoss:updateGradInput self.gradInput 1: -1.0812103212743e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1108388763387e-05
dG 1: -0.0028893372509629
dG 2: -3.2855360793116e-11
---
StyleLoss:updateOutput self.G 1: 141295152
StyleLoss:updateOutput self.G 2: 3.2077262401581
StyleLoss:updateGradInput self.gradInput 1: -1.9244895455017e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011735328735085
dG 1: -0.00015607735258527
dG 2: -3.5433162480503e-12
---
StyleLoss:updateOutput self.G 1: 1692586.5
StyleLoss:updateOutput self.G 2: 0.15316127240658
StyleLoss:updateGradInput self.gradInput 1: -9.0474564728993e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054284726502374
dG 1: -3.3736341720214e-05
dG 2: -3.0527852381418e-12
---
Iteration 85 / 2500
Content 1 loss: 502139.013672
Style 1 loss: 85388.328552
Style 2 loss: 78362953.125000
Style 3 loss: 100188503.906250
Style 4 loss: 6166113.281250
Style 5 loss: 231232.635498
Total loss: 185536330.290222
---
x1 value: -4.8238773345947
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 585313984
StyleLoss:updateOutput self.G 2: 1.6654109954834
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0010830089449883
dG 2: -3.0815170293935e-12
---
StyleLoss:updateOutput self.G 1: 5981893120
StyleLoss:updateOutput self.G 2: 34.040912628174
StyleLoss:updateGradInput self.gradInput 1: -5.6600510944804e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7668786060531e-05
dG 1: -0.011218771338463
dG 2: -6.3842202358e-11
---
StyleLoss:updateOutput self.G 1: 2406227968
StyleLoss:updateOutput self.G 2: 27.36180305481
StyleLoss:updateGradInput self.gradInput 1: -1.0819184659283e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1127138906159e-05
dG 1: -0.0028946956153959
dG 2: -3.2916294689933e-11
---
StyleLoss:updateOutput self.G 1: 140220928
StyleLoss:updateOutput self.G 2: 3.1833386421204
StyleLoss:updateGradInput self.gradInput 1: -1.9257333505607e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011735214502551
dG 1: -0.00015626338426955
dG 2: -3.5475400828738e-12
---
StyleLoss:updateOutput self.G 1: 1663561.25
StyleLoss:updateOutput self.G 2: 0.15053477883339
StyleLoss:updateGradInput self.gradInput 1: -9.0475751335362e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054285454098135
dG 1: -3.3756386983441e-05
dG 2: -3.0545975904933e-12
---
Iteration 86 / 2500
Content 1 loss: 501087.451172
Style 1 loss: 85794.799805
Style 2 loss: 78511787.109375
Style 3 loss: 100401515.625000
Style 4 loss: 6172449.462891
Style 5 loss: 231461.151123
Total loss: 185904095.599365
---
x1 value: -4.8136563301086
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 584006400
StyleLoss:updateOutput self.G 2: 1.6616905927658
StyleLoss:updateGradInput self.gradInput 1: -2.8453297495901e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010848256060854
dG 2: -3.0866858548306e-12
---
StyleLoss:updateOutput self.G 1: 5964350976
StyleLoss:updateOutput self.G 2: 33.941082000732
StyleLoss:updateGradInput self.gradInput 1: -5.6602447173759e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7661892090691e-05
dG 1: -0.011230956763029
dG 2: -6.3911542724782e-11
---
StyleLoss:updateOutput self.G 1: 2391050496
StyleLoss:updateOutput self.G 2: 27.189224243164
StyleLoss:updateGradInput self.gradInput 1: -1.0826152418986e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1150392866693e-05
dG 1: -0.0028999622445554
dG 2: -3.2976194691559e-11
---
StyleLoss:updateOutput self.G 1: 139167456
StyleLoss:updateOutput self.G 2: 3.1594221591949
StyleLoss:updateGradInput self.gradInput 1: -1.9270155249274e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011736855230993
dG 1: -0.00015644582163077
dG 2: -3.5516819520132e-12
---
StyleLoss:updateOutput self.G 1: 1635367.875
StyleLoss:updateOutput self.G 2: 0.14798361063004
StyleLoss:updateGradInput self.gradInput 1: -9.047683136032e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054286094382405
dG 1: -3.3775850170059e-05
dG 2: -3.0563594190236e-12
---
Iteration 87 / 2500
Content 1 loss: 500057.519531
Style 1 loss: 86197.368622
Style 2 loss: 78658224.609375
Style 3 loss: 100610648.437500
Style 4 loss: 6178595.214844
Style 5 loss: 231683.212280
Total loss: 186265406.362152
---
x1 value: -4.803581237793
feval(x) grad value: 0
---
StyleLoss:updateOutput self.G 1: 582715456
StyleLoss:updateOutput self.G 2: 1.658017039299
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010866192169487
dG 2: -3.0917891944565e-12
---
StyleLoss:updateOutput self.G 1: 5947078656
StyleLoss:updateOutput self.G 2: 33.842788696289
StyleLoss:updateGradInput self.gradInput 1: -5.6604330112009e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7651023629005e-05
dG 1: -0.011242956854403
dG 2: -6.3979814501902e-11
---
StyleLoss:updateOutput self.G 1: 2376130816
StyleLoss:updateOutput self.G 2: 27.019565582275
StyleLoss:updateGradInput self.gradInput 1: -1.0833010044564e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1172446294222e-05
dG 1: -0.0029051401652396
dG 2: -3.3035060797992e-11
---
StyleLoss:updateOutput self.G 1: 138135024
StyleLoss:updateOutput self.G 2: 3.1359837055206
StyleLoss:updateGradInput self.gradInput 1: -1.9283307395312e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011739771434804
dG 1: -0.00015662467922084
dG 2: -3.5557414217874e-12
---
StyleLoss:updateOutput self.G 1: 1607909.5
StyleLoss:updateOutput self.G 2: 0.14549890160561
StyleLoss:updateGradInput self.gradInput 1: -9.0477854541859e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054286728845909
dG 1: -3.3794804039644e-05
dG 2: -3.0580754942222e-12
---
Iteration 88 / 2500
Content 1 loss: 499049.218750
Style 1 loss: 86597.070694
Style 2 loss: 78802382.812500
Style 3 loss: 100816054.687500
Style 4 loss: 6184552.001953
Style 5 loss: 231899.620056
Total loss: 186620535.411453
---
x1 value: -4.7936458587646
feval(x) grad value: 8.8330647147598e-18
---
StyleLoss:updateOutput self.G 1: 581438784
StyleLoss:updateOutput self.G 2: 1.6543847322464
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0010883929207921
dG 2: -3.096835938729e-12
---
StyleLoss:updateOutput self.G 1: 5930073600
StyleLoss:updateOutput self.G 2: 33.746021270752
StyleLoss:updateGradInput self.gradInput 1: -5.6606164200446e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7643909561448e-05
dG 1: -0.011254770681262
dG 2: -6.4047045444937e-11
---
StyleLoss:updateOutput self.G 1: 2361459200
StyleLoss:updateOutput self.G 2: 26.852733612061
StyleLoss:updateGradInput self.gradInput 1: -1.0839761976911e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1192273278721e-05
dG 1: -0.0029102310072631
dG 2: -3.309295545928e-11
---
StyleLoss:updateOutput self.G 1: 137122592
StyleLoss:updateOutput self.G 2: 3.1129989624023
StyleLoss:updateGradInput self.gradInput 1: -1.9296811260006e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011741966591217
dG 1: -0.00015680002979934
dG 2: -3.5597221784839e-12
---
StyleLoss:updateOutput self.G 1: 1581185.75
StyleLoss:updateOutput self.G 2: 0.14308071136475
StyleLoss:updateGradInput self.gradInput 1: -9.0478785352843e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054287275997922
dG 1: -3.3813259506132e-05
dG 2: -3.0597442982061e-12
---
Iteration 89 / 2500
Content 1 loss: 498060.009766
Style 1 loss: 86995.204926
Style 2 loss: 78944285.156250
Style 3 loss: 101017804.687500
Style 4 loss: 6190331.542969
Style 5 loss: 232110.557556
Total loss: 186969587.158966
---
x1 value: -4.783851146698
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 580179520
StyleLoss:updateOutput self.G 2: 1.6508014202118
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010901424102485
dG 2: -3.1018139445838e-12
---
StyleLoss:updateOutput self.G 1: 5913327616
StyleLoss:updateOutput self.G 2: 33.650726318359
StyleLoss:updateGradInput self.gradInput 1: -5.6607953879961e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7642667191685e-05
dG 1: -0.011266401037574
dG 2: -6.4113235553886e-11
---
StyleLoss:updateOutput self.G 1: 2347027968
StyleLoss:updateOutput self.G 2: 26.688634872437
StyleLoss:updateGradInput self.gradInput 1: -1.0846417985988e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1218670452945e-05
dG 1: -0.0029152391944081
dG 2: -3.3149899492102e-11
---
StyleLoss:updateOutput self.G 1: 136130608
StyleLoss:updateOutput self.G 2: 3.090478181839
StyleLoss:updateGradInput self.gradInput 1: -1.9310551380158e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011744759103749
dG 1: -0.00015697182971053
dG 2: -3.5636233547409e-12
---
StyleLoss:updateOutput self.G 1: 1555211.875
StyleLoss:updateOutput self.G 2: 0.14073033630848
StyleLoss:updateGradInput self.gradInput 1: -9.0479673531263e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054287811508402
dG 1: -3.3831191103673e-05
dG 2: -3.0613671320179e-12
---
Iteration 90 / 2500
Content 1 loss: 497091.210938
Style 1 loss: 87389.362335
Style 2 loss: 79084013.671875
Style 3 loss: 101216074.218750
Style 4 loss: 6195941.162109
Style 5 loss: 232315.635681
Total loss: 187312825.261688
---
x1 value: -4.7741928100586
feval(x) grad value: -1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 578932736
StyleLoss:updateOutput self.G 2: 1.6472541093826
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0010918744374067
dG 2: -3.106742293979e-12
---
StyleLoss:updateOutput self.G 1: 5896824832
StyleLoss:updateOutput self.G 2: 33.556816101074
StyleLoss:updateGradInput self.gradInput 1: -5.6609734677693e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7642512577586e-05
dG 1: -0.011277865618467
dG 2: -6.4178481973265e-11
---
StyleLoss:updateOutput self.G 1: 2332827136
StyleLoss:updateOutput self.G 2: 26.527149200439
StyleLoss:updateGradInput self.gradInput 1: -1.0852980736331e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1244631069712e-05
dG 1: -0.0029201677534729
dG 2: -3.3205941468717e-11
---
StyleLoss:updateOutput self.G 1: 135157040
StyleLoss:updateOutput self.G 2: 3.0683767795563
StyleLoss:updateGradInput self.gradInput 1: -1.932458992826e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011747101234505
dG 1: -0.00015714048640803
dG 2: -3.5674514557715e-12
---
StyleLoss:updateOutput self.G 1: 1529938
StyleLoss:updateOutput self.G 2: 0.13844329118729
StyleLoss:updateGradInput self.gradInput 1: -9.0480455128272e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054288282990456
dG 1: -3.3848635212053e-05
dG 2: -3.062945730381e-12
---
Iteration 91 / 2500
Content 1 loss: 496137.988281
Style 1 loss: 87782.844543
Style 2 loss: 79221697.265625
Style 3 loss: 101410980.468750
Style 4 loss: 6201391.113281
Style 5 loss: 232515.151978
Total loss: 187650504.832458
---
x1 value: -4.7646670341492
feval(x) grad value: -1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 577702144
StyleLoss:updateOutput self.G 2: 1.6437524557114
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071979527827e-05
dG 1: -0.0010935843456537
dG 2: -3.1116075428078e-12
---
StyleLoss:updateOutput self.G 1: 5880566784
StyleLoss:updateOutput self.G 2: 33.464298248291
StyleLoss:updateGradInput self.gradInput 1: -5.6611497711856e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7642641725834e-05
dG 1: -0.01128915976733
dG 2: -6.4242743069709e-11
---
StyleLoss:updateOutput self.G 1: 2318851584
StyleLoss:updateOutput self.G 2: 26.368221282959
StyleLoss:updateGradInput self.gradInput 1: -1.085945022794e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1270184232853e-05
dG 1: -0.0029250173829496
dG 2: -3.3261088328018e-11
---
StyleLoss:updateOutput self.G 1: 134202072
StyleLoss:updateOutput self.G 2: 3.0466966629028
StyleLoss:updateGradInput self.gradInput 1: -1.9338857626394e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011750016710721
dG 1: -0.00015730588347651
dG 2: -3.5712064815757e-12
---
StyleLoss:updateOutput self.G 1: 1505355.625
StyleLoss:updateOutput self.G 2: 0.13621884584427
StyleLoss:updateGradInput self.gradInput 1: -9.0481215409e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054288737010211
dG 1: -3.3865610021167e-05
dG 2: -3.0644816111786e-12
---
Iteration 92 / 2500
Content 1 loss: 495203.466797
Style 1 loss: 88172.492981
Style 2 loss: 79357312.500000
Style 3 loss: 101602675.781250
Style 4 loss: 6206688.720703
Style 5 loss: 232709.266663
Total loss: 187982762.228394
---
x1 value: -4.7552728652954
feval(x) grad value: -2.4732579546966e-17
---
StyleLoss:updateOutput self.G 1: 576484352
StyleLoss:updateOutput self.G 2: 1.6402876377106
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010952760931104
dG 2: -3.1164211836132e-12
---
StyleLoss:updateOutput self.G 1: 5864543232
StyleLoss:updateOutput self.G 2: 33.373115539551
StyleLoss:updateGradInput self.gradInput 1: -5.6613251864235e-09
StyleLoss:updateGradInput self.gradInput 2: -2.765363205981e-05
dG 1: -0.011300290003419
dG 2: -6.4306081293264e-11
---
StyleLoss:updateOutput self.G 1: 2305098496
StyleLoss:updateOutput self.G 2: 26.21183013916
StyleLoss:updateGradInput self.gradInput 1: -1.0865828237172e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1305530834943e-05
dG 1: -0.0029297899454832
dG 2: -3.3315360886688e-11
---
StyleLoss:updateOutput self.G 1: 133264648
StyleLoss:updateOutput self.G 2: 3.0254149436951
StyleLoss:updateGradInput self.gradInput 1: -1.9353329605565e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011753078433685
dG 1: -0.00015746826829854
dG 2: -3.5748921184409e-12
---
StyleLoss:updateOutput self.G 1: 1481379.25
StyleLoss:updateOutput self.G 2: 0.13404923677444
StyleLoss:updateGradInput self.gradInput 1: -9.048194016259e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054289161926135
dG 1: -3.388215918676e-05
dG 2: -3.0659797617405e-12
---
Iteration 93 / 2500
Content 1 loss: 494286.181641
Style 1 loss: 88560.808182
Style 2 loss: 79490953.125000
Style 3 loss: 101791207.031250
Style 4 loss: 6211842.041016
Style 5 loss: 232898.735046
Total loss: 188309747.922134
---
x1 value: -4.7460055351257
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 575281600
StyleLoss:updateOutput self.G 2: 1.6368653774261
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0010969472350553
dG 2: -3.12117562698e-12
---
StyleLoss:updateOutput self.G 1: 5848748544
StyleLoss:updateOutput self.G 2: 33.283226013184
StyleLoss:updateGradInput self.gradInput 1: -5.6614988253045e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7663070795825e-05
dG 1: -0.011311262845993
dG 2: -6.4368531338399e-11
---
StyleLoss:updateOutput self.G 1: 2291561472
StyleLoss:updateOutput self.G 2: 26.057899475098
StyleLoss:updateGradInput self.gradInput 1: -1.0872122757632e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1332466430031e-05
dG 1: -0.0029344875365496
dG 2: -3.336877649196e-11
---
StyleLoss:updateOutput self.G 1: 132344032
StyleLoss:updateOutput self.G 2: 3.004515171051
StyleLoss:updateGradInput self.gradInput 1: -1.9368084025473e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011756445019273
dG 1: -0.00015762768452987
dG 2: -3.5785122694948e-12
---
StyleLoss:updateOutput self.G 1: 1458038.625
StyleLoss:updateOutput self.G 2: 0.13193714618683
StyleLoss:updateGradInput self.gradInput 1: -9.0482544123915e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054289534455165
dG 1: -3.3898275432875e-05
dG 2: -3.0674373631412e-12
---
Iteration 94 / 2500
Content 1 loss: 493385.253906
Style 1 loss: 88944.379807
Style 2 loss: 79622718.750000
Style 3 loss: 101976632.812500
Style 4 loss: 6216852.539062
Style 5 loss: 233083.259583
Total loss: 188631616.994858
---
x1 value: -4.7368602752686
feval(x) grad value: -1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 574092928
StyleLoss:updateOutput self.G 2: 1.6334834098816
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0010985985863954
dG 2: -3.1258745591956e-12
---
StyleLoss:updateOutput self.G 1: 5833175552
StyleLoss:updateOutput self.G 2: 33.194610595703
StyleLoss:updateGradInput self.gradInput 1: -5.6616720200964e-09
StyleLoss:updateGradInput self.gradInput 2: -2.766814759525e-05
dG 1: -0.011322079226375
dG 2: -6.4430093205115e-11
---
StyleLoss:updateOutput self.G 1: 2278238976
StyleLoss:updateOutput self.G 2: 25.906414031982
StyleLoss:updateGradInput self.gradInput 1: -1.0878318690288e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1358194216155e-05
dG 1: -0.00293911062181
dG 2: -3.3421345552176e-11
---
StyleLoss:updateOutput self.G 1: 131440624
StyleLoss:updateOutput self.G 2: 2.9840059280396
StyleLoss:updateGradInput self.gradInput 1: -1.9382973448501e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011759773769882
dG 1: -0.00015778417582624
dG 2: -3.5820647663332e-12
---
StyleLoss:updateOutput self.G 1: 1435289.875
StyleLoss:updateOutput self.G 2: 0.1298786252737
StyleLoss:updateGradInput self.gradInput 1: -9.0483148085241e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054289883701131
dG 1: -3.3913976949407e-05
dG 2: -3.0688585353489e-12
---
Iteration 95 / 2500
Content 1 loss: 492503.759766
Style 1 loss: 89325.147629
Style 2 loss: 79752591.796875
Style 3 loss: 102159082.031250
Style 4 loss: 6221732.666016
Style 5 loss: 233263.092041
Total loss: 188948498.493576
---
x1 value: -4.7278356552124
feval(x) grad value: 1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 572916736
StyleLoss:updateOutput self.G 2: 1.6301364898682
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011002327082679
dG 2: -3.130524051792e-12
---
StyleLoss:updateOutput self.G 1: 5817816064
StyleLoss:updateOutput self.G 2: 33.107196807861
StyleLoss:updateGradInput self.gradInput 1: -5.6618438826206e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7676636818796e-05
dG 1: -0.011332749389112
dG 2: -6.449080158788e-11
---
StyleLoss:updateOutput self.G 1: 2265125120
StyleLoss:updateOutput self.G 2: 25.757286071777
StyleLoss:updateGradInput self.gradInput 1: -1.088441603514e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1391074268613e-05
dG 1: -0.0029436619952321
dG 2: -3.3473099292358e-11
---
StyleLoss:updateOutput self.G 1: 130553768
StyleLoss:updateOutput self.G 2: 2.9638714790344
StyleLoss:updateGradInput self.gradInput 1: -1.9397996098292e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011764199734898
dG 1: -0.00015793781494722
dG 2: -3.585552644722e-12
---
StyleLoss:updateOutput self.G 1: 1413134.625
StyleLoss:updateOutput self.G 2: 0.12787386775017
StyleLoss:updateGradInput self.gradInput 1: -9.0483709414002e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054290221305564
dG 1: -3.3929274650291e-05
dG 2: -3.0702430615231e-12
---
Iteration 96 / 2500
Content 1 loss: 491640.820312
Style 1 loss: 89703.540802
Style 2 loss: 79880689.453125
Style 3 loss: 102338660.156250
Style 4 loss: 6226488.281250
Style 5 loss: 233438.301086
Total loss: 189260620.552826
---
x1 value: -4.7189292907715
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 571753344
StyleLoss:updateOutput self.G 2: 1.6268265247345
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011018489021808
dG 2: -3.1351228037269e-12
---
StyleLoss:updateOutput self.G 1: 5802665984
StyleLoss:updateOutput self.G 2: 33.02099609375
StyleLoss:updateGradInput self.gradInput 1: -5.6620153010556e-09
StyleLoss:updateGradInput self.gradInput 2: -2.768983176793e-05
dG 1: -0.011343273334205
dG 2: -6.4550698120058e-11
---
StyleLoss:updateOutput self.G 1: 2252214528
StyleLoss:updateOutput self.G 2: 25.610486984253
StyleLoss:updateGradInput self.gradInput 1: -1.0890419233078e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1426369938999e-05
dG 1: -0.0029481418896466
dG 2: -3.3524041181954e-11
---
StyleLoss:updateOutput self.G 1: 129681928
StyleLoss:updateOutput self.G 2: 2.9440786838531
StyleLoss:updateGradInput self.gradInput 1: -1.9413228358189e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011768241529353
dG 1: -0.00015808879106771
dG 2: -3.588980675151e-12
---
StyleLoss:updateOutput self.G 1: 1391529.375
StyleLoss:updateOutput self.G 2: 0.12591876089573
StyleLoss:updateGradInput self.gradInput 1: -9.0484235215627e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054290541447699
dG 1: -3.39441903634e-05
dG 2: -3.0715920258662e-12
---
Iteration 97 / 2500
Content 1 loss: 490796.191406
Style 1 loss: 90079.708099
Style 2 loss: 80007023.437500
Style 3 loss: 102515425.781250
Style 4 loss: 6231123.779297
Style 5 loss: 233609.230042
Total loss: 189568058.127594
---
x1 value: -4.7101397514343
feval(x) grad value: -1.943274071811e-17
---
StyleLoss:updateOutput self.G 1: 570602112
StyleLoss:updateOutput self.G 2: 1.6235506534576
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011034484487027
dG 2: -3.1396738507661e-12
---
StyleLoss:updateOutput self.G 1: 5787726848
StyleLoss:updateOutput self.G 2: 32.935970306396
StyleLoss:updateGradInput self.gradInput 1: -5.6621849431338e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7697948098648e-05
dG 1: -0.011353652924299
dG 2: -6.4609755046074e-11
---
StyleLoss:updateOutput self.G 1: 2239503616
StyleLoss:updateOutput self.G 2: 25.465942382812
StyleLoss:updateGradInput self.gradInput 1: -1.089631940232e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1455357354134e-05
dG 1: -0.00295255263336
dG 2: -3.3574198976538e-11
---
StyleLoss:updateOutput self.G 1: 128824728
StyleLoss:updateOutput self.G 2: 2.924619436264
StyleLoss:updateGradInput self.gradInput 1: -1.9428650688269e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011771622666856
dG 1: -0.00015823723515496
dG 2: -3.5923510260244e-12
---
StyleLoss:updateOutput self.G 1: 1370467.375
StyleLoss:updateOutput self.G 2: 0.12401288002729
StyleLoss:updateGradInput self.gradInput 1: -9.0484704173832e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054290820844471
dG 1: -3.395873500267e-05
dG 2: -3.0729080304631e-12
---
Iteration 98 / 2500
Content 1 loss: 489967.773438
Style 1 loss: 90454.113007
Style 2 loss: 80131623.046875
Style 3 loss: 102689484.375000
Style 4 loss: 6235643.554688
Style 5 loss: 233775.878906
Total loss: 189870948.741913
---
x1 value: -4.7014656066895
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 569464896
StyleLoss:updateOutput self.G 2: 1.6203148365021
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071981346817e-05
dG 1: -0.0011050284374505
dG 2: -3.1441693866541e-12
---
StyleLoss:updateOutput self.G 1: 5772982784
StyleLoss:updateOutput self.G 2: 32.852069854736
StyleLoss:updateGradInput self.gradInput 1: -5.6623532529443e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7712472729036e-05
dG 1: -0.01136389374733
dG 2: -6.4668041754867e-11
---
StyleLoss:updateOutput self.G 1: 2226983424
StyleLoss:updateOutput self.G 2: 25.323575973511
StyleLoss:updateGradInput self.gradInput 1: -1.0902128977364e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1488310166169e-05
dG 1: -0.0029568974860013
dG 2: -3.3623607370581e-11
---
StyleLoss:updateOutput self.G 1: 127981680
StyleLoss:updateOutput self.G 2: 2.9054794311523
StyleLoss:updateGradInput self.gradInput 1: -1.9444327037377e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011775624443544
dG 1: -0.00015838327817619
dG 2: -3.595666082587e-12
---
StyleLoss:updateOutput self.G 1: 1349932.375
StyleLoss:updateOutput self.G 2: 0.12215468287468
StyleLoss:updateGradInput self.gradInput 1: -9.0485144710328e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054291094420478
dG 1: -3.3972912206082e-05
dG 2: -3.0741908584736e-12
---
Iteration 99 / 2500
Content 1 loss: 489154.199219
Style 1 loss: 90825.176239
Style 2 loss: 80254582.031250
Style 3 loss: 102860906.250000
Style 4 loss: 6240048.339844
Style 5 loss: 233938.385010
Total loss: 190169454.381561
---
x1 value: -4.6929035186768
feval(x) grad value: -1.5899516486568e-17
---
StyleLoss:updateOutput self.G 1: 568339584
StyleLoss:updateOutput self.G 2: 1.6171128749847
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011065917788073
dG 2: -3.1486178681678e-12
---
StyleLoss:updateOutput self.G 1: 5758435328
StyleLoss:updateOutput self.G 2: 32.76927947998
StyleLoss:updateGradInput self.gradInput 1: -5.6625206745764e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7726857297239e-05
dG 1: -0.011373999528587
dG 2: -6.4725544368649e-11
---
StyleLoss:updateOutput self.G 1: 2214651136
StyleLoss:updateOutput self.G 2: 25.183338165283
StyleLoss:updateGradInput self.gradInput 1: -1.0907837300067e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1521452153102e-05
dG 1: -0.0029611771460623
dG 2: -3.3672269833529e-11
---
StyleLoss:updateOutput self.G 1: 127151616
StyleLoss:updateOutput self.G 2: 2.886634349823
StyleLoss:updateGradInput self.gradInput 1: -1.9460227207446e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011779633496189
dG 1: -0.00015852706565056
dG 2: -3.5989301816475e-12
---
StyleLoss:updateOutput self.G 1: 1329912.375
StyleLoss:updateOutput self.G 2: 0.12034308165312
StyleLoss:updateGradInput self.gradInput 1: -9.0485563930542e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054291327251121
dG 1: -3.3986740163527e-05
dG 2: -3.0754415940998e-12
---
Iteration 100 / 2500
Content 1 loss: 488355.273438
Style 1 loss: 91194.007874
Style 2 loss: 80375894.531250
Style 3 loss: 103029808.593750
Style 4 loss: 6244349.121094
Style 5 loss: 234096.702576
Total loss: 190463698.229980
---
x1 value: -4.6844539642334
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 567225984
StyleLoss:updateOutput self.G 2: 1.6139448881149
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011081389384344
dG 2: -3.1530195121476e-12
---
StyleLoss:updateOutput self.G 1: 5744073728
StyleLoss:updateOutput self.G 2: 32.687561035156
StyleLoss:updateGradInput self.gradInput 1: -5.6626858757625e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7745401894208e-05
dG 1: -0.011383976787329
dG 2: -6.4782318398571e-11
---
StyleLoss:updateOutput self.G 1: 2202501632
StyleLoss:updateOutput self.G 2: 25.045185089111
StyleLoss:updateGradInput self.gradInput 1: -1.0913449699501e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1554746935144e-05
dG 1: -0.0029653932433575
dG 2: -3.3720207182064e-11
---
StyleLoss:updateOutput self.G 1: 126334672
StyleLoss:updateOutput self.G 2: 2.8680891990662
StyleLoss:updateGradInput self.gradInput 1: -1.9476281920561e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011785428796429
dG 1: -0.00015866855392233
dG 2: -3.6021422390037e-12
---
StyleLoss:updateOutput self.G 1: 1310383
StyleLoss:updateOutput self.G 2: 0.11857589334249
StyleLoss:updateGradInput self.gradInput 1: -9.0485940518192e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054291571723297
dG 1: -3.400021159905e-05
dG 2: -3.0766617552247e-12
---
Iteration 101 / 2500
Content 1 loss: 487572.314453
Style 1 loss: 91559.852600
Style 2 loss: 80495677.734375
Style 3 loss: 103196261.718750
Style 4 loss: 6248552.490234
Style 5 loss: 234251.106262
Total loss: 190753875.216675
---
x1 value: -4.676112651825
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 566124352
StyleLoss:updateOutput self.G 2: 1.610809803009
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011096695670858
dG 2: -3.1573758364767e-12
---
StyleLoss:updateOutput self.G 1: 5729896960
StyleLoss:updateOutput self.G 2: 32.606887817383
StyleLoss:updateGradInput self.gradInput 1: -5.6628510769485e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7759826480178e-05
dG 1: -0.01139382366091
dG 2: -6.4838349966845e-11
---
StyleLoss:updateOutput self.G 1: 2190530560
StyleLoss:updateOutput self.G 2: 24.909059524536
StyleLoss:updateGradInput self.gradInput 1: -1.091895818206e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1584534705617e-05
dG 1: -0.0029695478733629
dG 2: -3.3767457580103e-11
---
StyleLoss:updateOutput self.G 1: 125530056
StyleLoss:updateOutput self.G 2: 2.8498215675354
StyleLoss:updateGradInput self.gradInput 1: -1.9492473413152e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001179011669592
dG 1: -0.00015880791761447
dG 2: -3.6053055072621e-12
---
StyleLoss:updateOutput self.G 1: 1291319.375
StyleLoss:updateOutput self.G 2: 0.11685084551573
StyleLoss:updateGradInput self.gradInput 1: -9.0486281578706e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054291769629344
dG 1: -3.4013377444353e-05
dG 2: -3.0778530765718e-12
---
Iteration 102 / 2500
Content 1 loss: 486802.441406
Style 1 loss: 91922.996521
Style 2 loss: 80613925.781250
Style 3 loss: 103360300.781250
Style 4 loss: 6252665.771484
Style 5 loss: 234401.802063
Total loss: 191040019.573975
---
x1 value: -4.6678786277771
feval(x) grad value: 1.4132903543616e-17
---
StyleLoss:updateOutput self.G 1: 565033472
StyleLoss:updateOutput self.G 2: 1.6077061891556
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011111850617453
dG 2: -3.1616870579954e-12
---
StyleLoss:updateOutput self.G 1: 5715901952
StyleLoss:updateOutput self.G 2: 32.527244567871
StyleLoss:updateGradInput self.gradInput 1: -5.6630158340454e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7779818992713e-05
dG 1: -0.011403545737267
dG 2: -6.4893673767941e-11
---
StyleLoss:updateOutput self.G 1: 2178737152
StyleLoss:updateOutput self.G 2: 24.774950027466
StyleLoss:updateGradInput self.gradInput 1: -1.0924360971387e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1617793107871e-05
dG 1: -0.0029736401047558
dG 2: -3.3813993272069e-11
---
StyleLoss:updateOutput self.G 1: 124738240
StyleLoss:updateOutput self.G 2: 2.8318455219269
StyleLoss:updateGradInput self.gradInput 1: -1.9508743065444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011795308819273
dG 1: -0.00015894504031166
dG 2: -3.6084199864228e-12
---
StyleLoss:updateOutput self.G 1: 1272721
StyleLoss:updateOutput self.G 2: 0.11516787111759
StyleLoss:updateGradInput self.gradInput 1: -9.0486622639219e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054291973356158
dG 1: -3.4026215871563e-05
dG 2: -3.0790149076199e-12
---
Iteration 103 / 2500
Content 1 loss: 486046.044922
Style 1 loss: 92285.499573
Style 2 loss: 80730662.109375
Style 3 loss: 103522054.687500
Style 4 loss: 6256692.626953
Style 5 loss: 234548.812866
Total loss: 191322289.781189
---
x1 value: -4.6597514152527
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 563954624
StyleLoss:updateOutput self.G 2: 1.6046365499496
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011126840254292
dG 2: -3.1659523093419e-12
---
StyleLoss:updateOutput self.G 1: 5702081024
StyleLoss:updateOutput self.G 2: 32.448596954346
StyleLoss:updateGradInput self.gradInput 1: -5.6631783706962e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7798741939478e-05
dG 1: -0.011413144879043
dG 2: -6.494831061854e-11
---
StyleLoss:updateOutput self.G 1: 2167118080
StyleLoss:updateOutput self.G 2: 24.64282989502
StyleLoss:updateGradInput self.gradInput 1: -1.0929659843839e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1648861446884e-05
dG 1: -0.0029776720330119
dG 2: -3.3859842013539e-11
---
StyleLoss:updateOutput self.G 1: 123958176
StyleLoss:updateOutput self.G 2: 2.814136505127
StyleLoss:updateGradInput self.gradInput 1: -1.9525099759221e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011800206266344
dG 1: -0.00015908015484456
dG 2: -3.6114871943688e-12
---
StyleLoss:updateOutput self.G 1: 1254575.125
StyleLoss:updateOutput self.G 2: 0.11352587491274
StyleLoss:updateGradInput self.gradInput 1: -9.0486906856313e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292142158374
dG 1: -3.4038741432596e-05
dG 2: -3.080148332571e-12
---
Iteration 104 / 2500
Content 1 loss: 485302.539062
Style 1 loss: 92644.151688
Style 2 loss: 80845939.453125
Style 3 loss: 103681523.437500
Style 4 loss: 6260637.451172
Style 5 loss: 234692.230225
Total loss: 191600739.262772
---
x1 value: -4.6517291069031
feval(x) grad value: -2.8265807087231e-17
---
StyleLoss:updateOutput self.G 1: 562885760
StyleLoss:updateOutput self.G 2: 1.6015951633453
StyleLoss:updateGradInput self.gradInput 1: -2.8453297495901e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011141689028591
dG 2: -3.1701774452081e-12
---
StyleLoss:updateOutput self.G 1: 5688432128
StyleLoss:updateOutput self.G 2: 32.370922088623
StyleLoss:updateGradInput self.gradInput 1: -5.6633391309902e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7812557163998e-05
dG 1: -0.011422626674175
dG 2: -6.5002267457537e-11
---
StyleLoss:updateOutput self.G 1: 2155667712
StyleLoss:updateOutput self.G 2: 24.512624740601
StyleLoss:updateGradInput self.gradInput 1: -1.0934855687594e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1677834310103e-05
dG 1: -0.0029816459864378
dG 2: -3.3905017682301e-11
---
StyleLoss:updateOutput self.G 1: 123190056
StyleLoss:updateOutput self.G 2: 2.79669880867
StyleLoss:updateGradInput self.gradInput 1: -1.9541561258052e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011805647227447
dG 1: -0.00015921320300549
dG 2: -3.6145075647809e-12
---
StyleLoss:updateOutput self.G 1: 1236880.5
StyleLoss:updateOutput self.G 2: 0.11192467808723
StyleLoss:updateGradInput self.gradInput 1: -9.048718396798e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292310960591
dG 1: -3.405095776543e-05
dG 2: -3.0812535682656e-12
---
Iteration 105 / 2500
Content 1 loss: 484574.511719
Style 1 loss: 93000.864029
Style 2 loss: 80959810.546875
Style 3 loss: 103838765.625000
Style 4 loss: 6264495.849609
Style 5 loss: 234832.054138
Total loss: 191875479.451370
---
x1 value: -4.6438088417053
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 561827840
StyleLoss:updateOutput self.G 2: 1.5985851287842
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011156388791278
dG 2: -3.1743596466682e-12
---
StyleLoss:updateOutput self.G 1: 5674950656
StyleLoss:updateOutput self.G 2: 32.294200897217
StyleLoss:updateGradInput self.gradInput 1: -5.6635003353733e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7829584723804e-05
dG 1: -0.011431992053986
dG 2: -6.5055558162719e-11
---
StyleLoss:updateOutput self.G 1: 2144383488
StyleLoss:updateOutput self.G 2: 24.384311676025
StyleLoss:updateGradInput self.gradInput 1: -1.0939942285404e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1709659348708e-05
dG 1: -0.0029855617322028
dG 2: -3.3949551503376e-11
---
StyleLoss:updateOutput self.G 1: 122433168
StyleLoss:updateOutput self.G 2: 2.779515504837
StyleLoss:updateGradInput self.gradInput 1: -1.9558060060376e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011809560237452
dG 1: -0.00015934433031362
dG 2: -3.6174841334252e-12
---
StyleLoss:updateOutput self.G 1: 1219568
StyleLoss:updateOutput self.G 2: 0.11035807430744
StyleLoss:updateGradInput self.gradInput 1: -9.0487446868792e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292456479743
dG 1: -3.406291216379e-05
dG 2: -3.0823358188742e-12
---
Iteration 106 / 2500
Content 1 loss: 483860.546875
Style 1 loss: 93355.911255
Style 2 loss: 81072281.250000
Style 3 loss: 103993863.281250
Style 4 loss: 6268279.541016
Style 5 loss: 234968.765259
Total loss: 192146609.295654
---
x1 value: -4.6359901428223
feval(x) grad value: -2.4732579546966e-17
---
StyleLoss:updateOutput self.G 1: 560780224
StyleLoss:updateOutput self.G 2: 1.5956044197083
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.001117094187066
dG 2: -3.1785006484458e-12
---
StyleLoss:updateOutput self.G 1: 5661630464
StyleLoss:updateOutput self.G 2: 32.218402862549
StyleLoss:updateGradInput self.gradInput 1: -5.6636588752212e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7854719519382e-05
dG 1: -0.011441244743764
dG 2: -6.5108217428556e-11
---
StyleLoss:updateOutput self.G 1: 2133261056
StyleLoss:updateOutput self.G 2: 24.257831573486
StyleLoss:updateGradInput self.gradInput 1: -1.0944928519052e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1745311541017e-05
dG 1: -0.0029894215986133
dG 2: -3.3993436537871e-11
---
StyleLoss:updateOutput self.G 1: 121687056
StyleLoss:updateOutput self.G 2: 2.7625765800476
StyleLoss:updateGradInput self.gradInput 1: -1.9574635246045e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011816026380984
dG 1: -0.00015947355132084
dG 2: -3.6204175508231e-12
---
StyleLoss:updateOutput self.G 1: 1202640.875
StyleLoss:updateOutput self.G 2: 0.108826354146
StyleLoss:updateGradInput self.gradInput 1: -9.0487674242468e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292607819661
dG 1: -3.4074597351719e-05
dG 2: -3.0833926991519e-12
---
Iteration 107 / 2500
Content 1 loss: 483160.791016
Style 1 loss: 93707.908630
Style 2 loss: 81183427.734375
Style 3 loss: 104146863.281250
Style 4 loss: 6271987.792969
Style 5 loss: 235102.317810
Total loss: 192414249.826050
---
x1 value: -4.6282715797424
feval(x) grad value: 0
---
StyleLoss:updateOutput self.G 1: 559742848
StyleLoss:updateOutput self.G 2: 1.5926523208618
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011185355251655
dG 2: -3.182601534743e-12
---
StyleLoss:updateOutput self.G 1: 5648470016
StyleLoss:updateOutput self.G 2: 32.143508911133
StyleLoss:updateGradInput self.gradInput 1: -5.6638165268907e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7878983019036e-05
dG 1: -0.011450387537479
dG 2: -6.5160245255047e-11
---
StyleLoss:updateOutput self.G 1: 2122295424
StyleLoss:updateOutput self.G 2: 24.133138656616
StyleLoss:updateGradInput self.gradInput 1: -1.0949814388539e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1779086536262e-05
dG 1: -0.0029932265169919
dG 2: -3.4036710949703e-11
---
StyleLoss:updateOutput self.G 1: 120951992
StyleLoss:updateOutput self.G 2: 2.7458896636963
StyleLoss:updateGradInput self.gradInput 1: -1.9591260169705e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001182177948067
dG 1: -0.00015960085147526
dG 2: -3.6233076001341e-12
---
StyleLoss:updateOutput self.G 1: 1186095
StyleLoss:updateOutput self.G 2: 0.10732913017273
StyleLoss:updateGradInput self.gradInput 1: -9.0487894510716e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292724234983
dG 1: -3.4086020605173e-05
dG 2: -3.0844257269819e-12
---
Iteration 108 / 2500
Content 1 loss: 482473.632812
Style 1 loss: 94058.143616
Style 2 loss: 81293267.578125
Style 3 loss: 104297777.343750
Style 4 loss: 6275619.873047
Style 5 loss: 235232.826233
Total loss: 192678429.397583
---
x1 value: -4.6206517219543
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 558716096
StyleLoss:updateOutput self.G 2: 1.5897309780121
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011199620785192
dG 2: -3.186660353996e-12
---
StyleLoss:updateOutput self.G 1: 5635466240
StyleLoss:updateOutput self.G 2: 32.069511413574
StyleLoss:updateGradInput self.gradInput 1: -5.663973734471e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7902988222195e-05
dG 1: -0.011459420435131
dG 2: -6.5211641642193e-11
---
StyleLoss:updateOutput self.G 1: 2111482368
StyleLoss:updateOutput self.G 2: 24.010189056396
StyleLoss:updateGradInput self.gradInput 1: -1.0954591900258e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1810911574867e-05
dG 1: -0.0029969790484756
dG 2: -3.4079381677765e-11
---
StyleLoss:updateOutput self.G 1: 120227928
StyleLoss:updateOutput self.G 2: 2.7294507026672
StyleLoss:updateGradInput self.gradInput 1: -1.9607886869721e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011828329297714
dG 1: -0.0001597262598807
dG 2: -3.6261549318795e-12
---
StyleLoss:updateOutput self.G 1: 1169927.5
StyleLoss:updateOutput self.G 2: 0.10586611926556
StyleLoss:updateGradInput self.gradInput 1: -9.0488086357254e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292852291837
dG 1: -3.4097181924153e-05
dG 2: -3.0854359865662e-12
---
Iteration 109 / 2500
Content 1 loss: 481799.365234
Style 1 loss: 94405.906677
Style 2 loss: 81401794.921875
Style 3 loss: 104446734.375000
Style 4 loss: 6279185.302734
Style 5 loss: 235360.267639
Total loss: 192939280.139160
---
x1 value: -4.6131286621094
feval(x) grad value: -1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 557698816
StyleLoss:updateOutput self.G 2: 1.5868368148804
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011213753605261
dG 2: -3.1906818766941e-12
---
StyleLoss:updateOutput self.G 1: 5622615040
StyleLoss:updateOutput self.G 2: 31.996377944946
StyleLoss:updateGradInput self.gradInput 1: -5.6641291656945e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7927202609135e-05
dG 1: -0.011468348093331
dG 2: -6.5262448223358e-11
---
StyleLoss:updateOutput self.G 1: 2100817920
StyleLoss:updateOutput self.G 2: 23.888910293579
StyleLoss:updateGradInput self.gradInput 1: -1.0959269935995e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1843828007113e-05
dG 1: -0.0030006794258952
dG 2: -3.4121459130398e-11
---
StyleLoss:updateOutput self.G 1: 119514408
StyleLoss:updateOutput self.G 2: 2.7132530212402
StyleLoss:updateGradInput self.gradInput 1: -1.962452955695e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011835047189379
dG 1: -0.00015984984929673
dG 2: -3.6289610639423e-12
---
StyleLoss:updateOutput self.G 1: 1154111.25
StyleLoss:updateOutput self.G 2: 0.10443492978811
StyleLoss:updateGradInput self.gradInput 1: -9.0488249782084e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054292957065627
dG 1: -3.4108095860574e-05
dG 2: -3.0864241284262e-12
---
Iteration 110 / 2500
Content 1 loss: 481137.646484
Style 1 loss: 94751.335144
Style 2 loss: 81509080.078125
Style 3 loss: 104593757.812500
Style 4 loss: 6282681.152344
Style 5 loss: 235484.893799
Total loss: 193196892.918396
---
x1 value: -4.6057000160217
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 556691456
StyleLoss:updateOutput self.G 2: 1.5839703083038
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011227747891098
dG 2: -3.1946639344332e-12
---
StyleLoss:updateOutput self.G 1: 5609911296
StyleLoss:updateOutput self.G 2: 31.924083709717
StyleLoss:updateGradInput self.gradInput 1: -5.6642841528287e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7949899958912e-05
dG 1: -0.011477172374725
dG 2: -6.531266499854e-11
---
StyleLoss:updateOutput self.G 1: 2090301184
StyleLoss:updateOutput self.G 2: 23.769323348999
StyleLoss:updateGradInput self.gradInput 1: -1.0963843166678e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1876780819148e-05
dG 1: -0.0030043297447264
dG 2: -3.4162964124285e-11
---
StyleLoss:updateOutput self.G 1: 118811320
StyleLoss:updateOutput self.G 2: 2.6972906589508
StyleLoss:updateGradInput self.gradInput 1: -1.9641140269755e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011840950901387
dG 1: -0.0001599716488272
dG 2: -3.6317251289608e-12
---
StyleLoss:updateOutput self.G 1: 1138623.125
StyleLoss:updateOutput self.G 2: 0.10303343832493
StyleLoss:updateGradInput self.gradInput 1: -9.048842031234e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293050197884
dG 1: -3.4118798794225e-05
dG 2: -3.0873921041258e-12
---
Iteration 111 / 2500
Content 1 loss: 480487.255859
Style 1 loss: 95095.161438
Style 2 loss: 81615134.765625
Style 3 loss: 104738894.531250
Style 4 loss: 6286114.746094
Style 5 loss: 235606.819153
Total loss: 193451333.279419
---
x1 value: -4.59836769104
feval(x) grad value: -1.4132903543616e-17
---
StyleLoss:updateOutput self.G 1: 555693760
StyleLoss:updateOutput self.G 2: 1.5811313390732
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011241609463468
dG 2: -3.1986080450963e-12
---
StyleLoss:updateOutput self.G 1: 5597353472
StyleLoss:updateOutput self.G 2: 31.852621078491
StyleLoss:updateGradInput self.gradInput 1: -5.6644369195169e-09
StyleLoss:updateGradInput self.gradInput 2: -2.7973443138762e-05
dG 1: -0.011485897004604
dG 2: -6.5362305845529e-11
---
StyleLoss:updateOutput self.G 1: 2079928704
StyleLoss:updateOutput self.G 2: 23.651376724243
StyleLoss:updateGradInput self.gradInput 1: -1.0968323138627e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1908132920507e-05
dG 1: -0.003007928840816
dG 2: -3.4203896659424e-11
---
StyleLoss:updateOutput self.G 1: 118118800
StyleLoss:updateOutput self.G 2: 2.6815693378448
StyleLoss:updateGradInput self.gradInput 1: -1.9657674599216e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011845850531245
dG 1: -0.00016009158571251
dG 2: -3.6344482111372e-12
---
StyleLoss:updateOutput self.G 1: 1123472.125
StyleLoss:updateOutput self.G 2: 0.10166244208813
StyleLoss:updateGradInput self.gradInput 1: -9.0488548210033e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293125867844
dG 1: -3.4129250707338e-05
dG 2: -3.0883386126224e-12
---
Iteration 112 / 2500
Content 1 loss: 479848.828125
Style 1 loss: 95438.026428
Style 2 loss: 81719994.140625
Style 3 loss: 104882214.843750
Style 4 loss: 6289491.210938
Style 5 loss: 235726.043701
Total loss: 193702713.093567
---
x1 value: -4.5911269187927
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 554705408
StyleLoss:updateOutput self.G 2: 1.5783196687698
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011255340650678
dG 2: -3.2025146423642e-12
---
StyleLoss:updateOutput self.G 1: 5584935936
StyleLoss:updateOutput self.G 2: 31.781965255737
StyleLoss:updateGradInput self.gradInput 1: -5.6645892421159e-09
StyleLoss:updateGradInput self.gradInput 2: -2.79975720332e-05
dG 1: -0.011494521982968
dG 2: -6.5411398519899e-11
---
StyleLoss:updateOutput self.G 1: 2069699200
StyleLoss:updateOutput self.G 2: 23.535051345825
StyleLoss:updateGradInput self.gradInput 1: -1.0972708075485e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1939448642079e-05
dG 1: -0.0030114788096398
dG 2: -3.4244267144157e-11
---
StyleLoss:updateOutput self.G 1: 117436424
StyleLoss:updateOutput self.G 2: 2.6660778522491
StyleLoss:updateGradInput self.gradInput 1: -1.9674136098047e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011852177703986
dG 1: -0.00016020977636799
dG 2: -3.6371318283546e-12
---
StyleLoss:updateOutput self.G 1: 1108642.875
StyleLoss:updateOutput self.G 2: 0.10032051801682
StyleLoss:updateGradInput self.gradInput 1: -9.0488676107725e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293201537803
dG 1: -3.4139484341722e-05
dG 2: -3.0892647381181e-12
---
Iteration 113 / 2500
Content 1 loss: 479222.265625
Style 1 loss: 95777.893066
Style 2 loss: 81823699.218750
Style 3 loss: 105023718.750000
Style 4 loss: 6292809.814453
Style 5 loss: 235842.681885
Total loss: 193951070.623779
---
x1 value: -4.5839757919312
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 553727360
StyleLoss:updateOutput self.G 2: 1.5755364894867
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011268928647041
dG 2: -3.2063815578326e-12
---
StyleLoss:updateOutput self.G 1: 5572661760
StyleLoss:updateOutput self.G 2: 31.712116241455
StyleLoss:updateGradInput self.gradInput 1: -5.6647406765364e-09
StyleLoss:updateGradInput self.gradInput 2: -2.802349627018e-05
dG 1: -0.011503047309816
dG 2: -6.5459915266075e-11
---
StyleLoss:updateOutput self.G 1: 2059606784
StyleLoss:updateOutput self.G 2: 23.420289993286
StyleLoss:updateGradInput self.gradInput 1: -1.097701041175e-08
StyleLoss:updateGradInput self.gradInput 2: -6.1973703850526e-05
dG 1: -0.0030149812810123
dG 2: -3.4284089456271e-11
---
StyleLoss:updateOutput self.G 1: 116763792
StyleLoss:updateOutput self.G 2: 2.6508076190948
StyleLoss:updateGradInput self.gradInput 1: -1.9690499897251e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011858208017657
dG 1: -0.00016032629355323
dG 2: -3.6397759806128e-12
---
StyleLoss:updateOutput self.G 1: 1094122.875
StyleLoss:updateOutput self.G 2: 0.099006608128548
StyleLoss:updateGradInput self.gradInput 1: -9.0488789794563e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293259745464
dG 1: -3.4149514249293e-05
dG 2: -3.0901715648152e-12
---
Iteration 114 / 2500
Content 1 loss: 478608.398438
Style 1 loss: 96114.852905
Style 2 loss: 81926220.703125
Style 3 loss: 105163500.000000
Style 4 loss: 6296074.951172
Style 5 loss: 235956.871033
Total loss: 194196475.776672
---
x1 value: -4.5769195556641
feval(x) grad value: -1.5016210015092e-17
---
StyleLoss:updateOutput self.G 1: 552758016
StyleLoss:updateOutput self.G 2: 1.5727784633636
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.001128239557147
dG 2: -3.2102131283102e-12
---
StyleLoss:updateOutput self.G 1: 5560524800
StyleLoss:updateOutput self.G 2: 31.643047332764
StyleLoss:updateGradInput self.gradInput 1: -5.6648903346002e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8046057195752e-05
dG 1: -0.011511478573084
dG 2: -6.5507890778527e-11
---
StyleLoss:updateOutput self.G 1: 2049650304
StyleLoss:updateOutput self.G 2: 23.307075500488
StyleLoss:updateGradInput self.gradInput 1: -1.0981223930173e-08
StyleLoss:updateGradInput self.gradInput 2: -6.200419011293e-05
dG 1: -0.0030184360221028
dG 2: -3.4323374004108e-11
---
StyleLoss:updateOutput self.G 1: 116100600
StyleLoss:updateOutput self.G 2: 2.6357514858246
StyleLoss:updateGradInput self.gradInput 1: -1.9706794418539e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011863410327351
dG 1: -0.00016044116637204
dG 2: -3.6423845710398e-12
---
StyleLoss:updateOutput self.G 1: 1079921.125
StyleLoss:updateOutput self.G 2: 0.097721502184868
StyleLoss:updateGradInput self.gradInput 1: -9.0488867954264e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293329594657
dG 1: -3.4159311326221e-05
dG 2: -3.0910590927136e-12
---
Iteration 115 / 2500
Content 1 loss: 478006.494141
Style 1 loss: 96449.329376
Style 2 loss: 82027628.906250
Style 3 loss: 105301558.593750
Style 4 loss: 6299285.888672
Style 5 loss: 236068.496704
Total loss: 194438997.708893
---
x1 value: -4.569947719574
feval(x) grad value: -8.8330647147598e-18
---
StyleLoss:updateOutput self.G 1: 551796672
StyleLoss:updateOutput self.G 2: 1.5700430870056
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011295751901343
dG 2: -3.2140132569247e-12
---
StyleLoss:updateOutput self.G 1: 5548521984
StyleLoss:updateOutput self.G 2: 31.574747085571
StyleLoss:updateGradInput self.gradInput 1: -5.6650386603962e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8068452593288e-05
dG 1: -0.011519816704094
dG 2: -6.5555345873936e-11
---
StyleLoss:updateOutput self.G 1: 2039828224
StyleLoss:updateOutput self.G 2: 23.195384979248
StyleLoss:updateGradInput self.gradInput 1: -1.0985355736182e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2034683651291e-05
dG 1: -0.0030218453612179
dG 2: -3.4362134665455e-11
---
StyleLoss:updateOutput self.G 1: 115446488
StyleLoss:updateOutput self.G 2: 2.6209013462067
StyleLoss:updateGradInput self.gradInput 1: -1.9723005451056e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011870198068209
dG 1: -0.00016055440937635
dG 2: -3.644956298593e-12
---
StyleLoss:updateOutput self.G 1: 1066020.375
StyleLoss:updateOutput self.G 2: 0.096463613212109
StyleLoss:updateGradInput self.gradInput 1: -9.0488967430247e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293381981552
dG 1: -3.4168915590271e-05
dG 2: -3.0919273218133e-12
---
Iteration 116 / 2500
Content 1 loss: 477415.234375
Style 1 loss: 96781.951904
Style 2 loss: 82127923.828125
Style 3 loss: 105437929.687500
Style 4 loss: 6302446.289062
Style 5 loss: 236177.742004
Total loss: 194678674.732971
---
x1 value: -4.5630674362183
feval(x) grad value: -1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 550844800
StyleLoss:updateOutput self.G 2: 1.5673347711563
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.001130897551775
dG 2: -3.2177760889845e-12
---
StyleLoss:updateOutput self.G 1: 5536648704
StyleLoss:updateOutput self.G 2: 31.507175445557
StyleLoss:updateGradInput self.gradInput 1: -5.6651874302815e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8096523237764e-05
dG 1: -0.011528064496815
dG 2: -6.5602280552302e-11
---
StyleLoss:updateOutput self.G 1: 2030137088
StyleLoss:updateOutput self.G 2: 23.085187911987
StyleLoss:updateGradInput self.gradInput 1: -1.0989398724348e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2066996179055e-05
dG 1: -0.0030252081342041
dG 2: -3.4400381848654e-11
---
StyleLoss:updateOutput self.G 1: 114801352
StyleLoss:updateOutput self.G 2: 2.6062560081482
StyleLoss:updateGradInput self.gradInput 1: -1.9739115231232e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011876374628628
dG 1: -0.00016066618263721
dG 2: -3.6474933316766e-12
---
StyleLoss:updateOutput self.G 1: 1052397.25
StyleLoss:updateOutput self.G 2: 0.095230884850025
StyleLoss:updateGradInput self.gradInput 1: -9.0489052695375e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293422726914
dG 1: -3.4178319765488e-05
dG 2: -3.0927795047209e-12
---
Iteration 117 / 2500
Content 1 loss: 476834.375000
Style 1 loss: 97113.246918
Style 2 loss: 82227152.343750
Style 3 loss: 105572660.156250
Style 4 loss: 6305557.617188
Style 5 loss: 236284.812927
Total loss: 194915602.552032
---
x1 value: -4.5562720298767
feval(x) grad value: -1.5899516486568e-17
---
StyleLoss:updateOutput self.G 1: 549901824
StyleLoss:updateOutput self.G 2: 1.5646516084671
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011322079226375
dG 2: -3.221503792894e-12
---
StyleLoss:updateOutput self.G 1: 5524898816
StyleLoss:updateOutput self.G 2: 31.440307617188
StyleLoss:updateGradInput self.gradInput 1: -5.6653353119884e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8122161893407e-05
dG 1: -0.011536229401827
dG 2: -6.56487225692e-11
---
StyleLoss:updateOutput self.G 1: 2020573312
StyleLoss:updateOutput self.G 2: 22.976430892944
StyleLoss:updateGradInput self.gradInput 1: -1.0993367105527e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2098981288727e-05
dG 1: -0.0030285264365375
dG 2: -3.443811902315e-11
---
StyleLoss:updateOutput self.G 1: 114164440
StyleLoss:updateOutput self.G 2: 2.5917963981628
StyleLoss:updateGradInput self.gradInput 1: -1.9755157509849e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011882963735843
dG 1: -0.00016077650070656
dG 2: -3.6499969713333e-12
---
StyleLoss:updateOutput self.G 1: 1039065.25
StyleLoss:updateOutput self.G 2: 0.094024494290352
StyleLoss:updateGradInput self.gradInput 1: -9.0489116644221e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293475113809
dG 1: -3.4187531127827e-05
dG 2: -3.0936117383085e-12
---
Iteration 118 / 2500
Content 1 loss: 476264.697266
Style 1 loss: 97442.390442
Style 2 loss: 82325378.906250
Style 3 loss: 105705796.875000
Style 4 loss: 6308625.000000
Style 5 loss: 236389.549255
Total loss: 195149897.418213
---
x1 value: -4.549560546875
feval(x) grad value: -1.6782822958044e-17
---
StyleLoss:updateOutput self.G 1: 548967296
StyleLoss:updateOutput self.G 2: 1.5619924068451
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011335063027218
dG 2: -3.2251983202169e-12
---
StyleLoss:updateOutput self.G 1: 5513281024
StyleLoss:updateOutput self.G 2: 31.374195098877
StyleLoss:updateGradInput self.gradInput 1: -5.6654800850708e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8148524506832e-05
dG 1: -0.011544297449291
dG 2: -6.5694658046844e-11
---
StyleLoss:updateOutput self.G 1: 2011134720
StyleLoss:updateOutput self.G 2: 22.869104385376
StyleLoss:updateGradInput self.gradInput 1: -1.0997255550649e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2127415731084e-05
dG 1: -0.0030318023636937
dG 2: -3.4475363536179e-11
---
StyleLoss:updateOutput self.G 1: 113535984
StyleLoss:updateOutput self.G 2: 2.5775284767151
StyleLoss:updateGradInput self.gradInput 1: -1.9771096759769e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011889049346792
dG 1: -0.0001608853781363
dG 2: -3.6524689522865e-12
---
StyleLoss:updateOutput self.G 1: 1025998.6875
StyleLoss:updateOutput self.G 2: 0.092842079699039
StyleLoss:updateGradInput self.gradInput 1: -9.0489159276785e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293498396873
dG 1: -3.4196553315269e-05
dG 2: -3.0944283593848e-12
---
Iteration 119 / 2500
Content 1 loss: 475704.394531
Style 1 loss: 97769.405365
Style 2 loss: 82422498.046875
Style 3 loss: 105837351.562500
Style 4 loss: 6311646.972656
Style 5 loss: 236492.111206
Total loss: 195381462.493134
---
x1 value: -4.5429348945618
feval(x) grad value: 1.6782822958044e-17
---
StyleLoss:updateOutput self.G 1: 548040576
StyleLoss:updateOutput self.G 2: 1.5593557357788
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011347935069352
dG 2: -3.2288614056769e-12
---
StyleLoss:updateOutput self.G 1: 5501784576
StyleLoss:updateOutput self.G 2: 31.308773040771
StyleLoss:updateGradInput self.gradInput 1: -5.6656257463317e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8171145459055e-05
dG 1: -0.011552285403013
dG 2: -6.5740093924127e-11
---
StyleLoss:updateOutput self.G 1: 2001819008
StyleLoss:updateOutput self.G 2: 22.76317024231
StyleLoss:updateGradInput self.gradInput 1: -1.1001068500605e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2158957007341e-05
dG 1: -0.0030350347515196
dG 2: -3.4512122326635e-11
---
StyleLoss:updateOutput self.G 1: 112915480
StyleLoss:updateOutput self.G 2: 2.5634422302246
StyleLoss:updateGradInput self.gradInput 1: -1.9786956073631e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011895289208042
dG 1: -0.00016099282947835
dG 2: -3.6549084071746e-12
---
StyleLoss:updateOutput self.G 1: 1013200
StyleLoss:updateOutput self.G 2: 0.091683954000473
StyleLoss:updateGradInput self.gradInput 1: -9.0489223225632e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0005429353332147
dG 1: -3.4205375413876e-05
dG 2: -3.0952276332263e-12
---
Iteration 120 / 2500
Content 1 loss: 475154.394531
Style 1 loss: 98094.612122
Style 2 loss: 82518626.953125
Style 3 loss: 105967359.375000
Style 4 loss: 6314625.000000
Style 5 loss: 236592.613220
Total loss: 195610452.947998
---
x1 value: -4.5363917350769
feval(x) grad value: 4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 547122624
StyleLoss:updateOutput self.G 2: 1.5567438602448
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011360690696165
dG 2: -3.2324900135078e-12
---
StyleLoss:updateOutput self.G 1: 5490408960
StyleLoss:updateOutput self.G 2: 31.244041442871
StyleLoss:updateGradInput self.gradInput 1: -5.6657696312357e-09
StyleLoss:updateGradInput self.gradInput 2: -2.81953762169e-05
dG 1: -0.011560186743736
dG 2: -6.5785064895518e-11
---
StyleLoss:updateOutput self.G 1: 1992623232
StyleLoss:updateOutput self.G 2: 22.658603668213
StyleLoss:updateGradInput self.gradInput 1: -1.1004805067216e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2188257288653e-05
dG 1: -0.0030382254626602
dG 2: -3.45484162112e-11
---
StyleLoss:updateOutput self.G 1: 112303304
StyleLoss:updateOutput self.G 2: 2.549544095993
StyleLoss:updateGradInput self.gradInput 1: -1.9802739004149e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011901855032193
dG 1: -0.0001610988547327
dG 2: -3.6573153359976e-12
---
StyleLoss:updateOutput self.G 1: 1000656.4375
StyleLoss:updateOutput self.G 2: 0.090548902750015
StyleLoss:updateGradInput self.gradInput 1: -9.0489265858196e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293550783768
dG 1: -3.4214044717373e-05
dG 2: -3.0960112945566e-12
---
Iteration 121 / 2500
Content 1 loss: 474613.525391
Style 1 loss: 98416.809082
Style 2 loss: 82613765.625000
Style 3 loss: 106095867.187500
Style 4 loss: 6317557.617188
Style 5 loss: 236691.032410
Total loss: 195836911.796570
---
x1 value: -4.5299277305603
feval(x) grad value: 2.6499192076328e-18
---
StyleLoss:updateOutput self.G 1: 546212928
StyleLoss:updateOutput self.G 2: 1.5541553497314
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011373329907656
dG 2: -3.2360865289544e-12
---
StyleLoss:updateOutput self.G 1: 5479152640
StyleLoss:updateOutput self.G 2: 31.179985046387
StyleLoss:updateGradInput self.gradInput 1: -5.6659112956936e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8221475076862e-05
dG 1: -0.011568006128073
dG 2: -6.582955708323e-11
---
StyleLoss:updateOutput self.G 1: 1983545344
StyleLoss:updateOutput self.G 2: 22.555379867554
StyleLoss:updateGradInput self.gradInput 1: -1.1008465250484e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2218045059126e-05
dG 1: -0.0030413765925914
dG 2: -3.4584238250979e-11
---
StyleLoss:updateOutput self.G 1: 111699104
StyleLoss:updateOutput self.G 2: 2.5358273983002
StyleLoss:updateGradInput self.gradInput 1: -1.9818436669539e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011907806037925
dG 1: -0.00016120349755511
dG 2: -3.6596914734788e-12
---
StyleLoss:updateOutput self.G 1: 988365
StyleLoss:updateOutput self.G 2: 0.089436635375023
StyleLoss:updateGradInput self.gradInput 1: -9.0489322701615e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293585708365
dG 1: -3.4222528483951e-05
dG 2: -3.0967786928543e-12
---
Iteration 122 / 2500
Content 1 loss: 474082.128906
Style 1 loss: 98737.014771
Style 2 loss: 82707931.640625
Style 3 loss: 106222898.437500
Style 4 loss: 6320447.021484
Style 5 loss: 236787.460327
Total loss: 196060883.703613
---
x1 value: -4.5235466957092
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 545310464
StyleLoss:updateOutput self.G 2: 1.5515878200531
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011385866673663
dG 2: -3.2396535541018e-12
---
StyleLoss:updateOutput self.G 1: 5468010496
StyleLoss:updateOutput self.G 2: 31.116580963135
StyleLoss:updateGradInput self.gradInput 1: -5.6660534042408e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8246911824681e-05
dG 1: -0.011575747281313
dG 2: -6.587361905952e-11
---
StyleLoss:updateOutput self.G 1: 1974584064
StyleLoss:updateOutput self.G 2: 22.453481674194
StyleLoss:updateGradInput self.gradInput 1: -1.1012057932192e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2247061578091e-05
dG 1: -0.0030444860458374
dG 2: -3.4619591915419e-11
---
StyleLoss:updateOutput self.G 1: 111102456
StyleLoss:updateOutput self.G 2: 2.5222821235657
StyleLoss:updateGradInput self.gradInput 1: -1.9834073938796e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011914269271074
dG 1: -0.00016130684525706
dG 2: -3.66203768698e-12
---
StyleLoss:updateOutput self.G 1: 976322.5
StyleLoss:updateOutput self.G 2: 0.088346906006336
StyleLoss:updateGradInput self.gradInput 1: -9.0489351123324e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293603170663
dG 1: -3.4230844903504e-05
dG 2: -3.0975313460024e-12
---
Iteration 123 / 2500
Content 1 loss: 473560.156250
Style 1 loss: 99056.190491
Style 2 loss: 82801160.156250
Style 3 loss: 106348453.125000
Style 4 loss: 6323291.748047
Style 5 loss: 236881.874084
Total loss: 196282403.250122
---
x1 value: -4.5172438621521
feval(x) grad value: 2.2965966604014e-17
---
StyleLoss:updateOutput self.G 1: 544416576
StyleLoss:updateOutput self.G 2: 1.5490443706512
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011398285860196
dG 2: -3.2431874026628e-12
---
StyleLoss:updateOutput self.G 1: 5456984576
StyleLoss:updateOutput self.G 2: 31.053834915161
StyleLoss:updateGradInput self.gradInput 1: -5.6661955127879e-09
StyleLoss:updateGradInput self.gradInput 2: -2.827301977959e-05
dG 1: -0.011583405546844
dG 2: -6.5917195313236e-11
---
StyleLoss:updateOutput self.G 1: 1965734912
StyleLoss:updateOutput self.G 2: 22.352849960327
StyleLoss:updateGradInput self.gradInput 1: -1.1015577783269e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2278188124765e-05
dG 1: -0.0030475568491966
dG 2: -3.4654515368437e-11
---
StyleLoss:updateOutput self.G 1: 110513352
StyleLoss:updateOutput self.G 2: 2.5089077949524
StyleLoss:updateGradInput self.gradInput 1: -1.9849622390211e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011920626275241
dG 1: -0.00016140891239047
dG 2: -3.6643539765013e-12
---
StyleLoss:updateOutput self.G 1: 964507.8125
StyleLoss:updateOutput self.G 2: 0.087277822196484
StyleLoss:updateGradInput self.gradInput 1: -9.0489379545033e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293626453727
dG 1: -3.423900125199e-05
dG 2: -3.0982696876819e-12
---
Iteration 124 / 2500
Content 1 loss: 473046.142578
Style 1 loss: 99372.894287
Style 2 loss: 82893427.734375
Style 3 loss: 106472601.562500
Style 4 loss: 6326095.458984
Style 5 loss: 236974.479675
Total loss: 196501518.272400
---
x1 value: -4.5110182762146
feval(x) grad value: -1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 543530112
StyleLoss:updateOutput self.G 2: 1.5465220212936
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011410601437092
dG 2: -3.2466919777652e-12
---
StyleLoss:updateOutput self.G 1: 5446068224
StyleLoss:updateOutput self.G 2: 30.991714477539
StyleLoss:updateGradInput self.gradInput 1: -5.666333180443e-09
StyleLoss:updateGradInput self.gradInput 2: -2.830022276612e-05
dG 1: -0.011590986512601
dG 2: -6.5960348294425e-11
---
StyleLoss:updateOutput self.G 1: 1956997632
StyleLoss:updateOutput self.G 2: 22.253498077393
StyleLoss:updateGradInput self.gradInput 1: -1.1019031020965e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2308405176736e-05
dG 1: -0.0030505890026689
dG 2: -3.4688994732246e-11
---
StyleLoss:updateOutput self.G 1: 109931528
StyleLoss:updateOutput self.G 2: 2.4956998825073
StyleLoss:updateGradInput self.gradInput 1: -1.9865078471071e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011926999286516
dG 1: -0.00016150966985151
dG 2: -3.666642510447e-12
---
StyleLoss:updateOutput self.G 1: 952916.6875
StyleLoss:updateOutput self.G 2: 0.08622894436121
StyleLoss:updateGradInput self.gradInput 1: -9.0489386650461e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293632274494
dG 1: -3.4246997529408e-05
dG 2: -3.0989937178927e-12
---
Iteration 125 / 2500
Content 1 loss: 472541.650391
Style 1 loss: 99688.911438
Style 2 loss: 82984787.109375
Style 3 loss: 106595308.593750
Style 4 loss: 6328862.548828
Style 5 loss: 237065.231323
Total loss: 196718254.045105
---
x1 value: -4.5048713684082
feval(x) grad value: -1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 542650880
StyleLoss:updateOutput self.G 2: 1.5440204143524
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011422818060964
dG 2: -3.2501670625684e-12
---
StyleLoss:updateOutput self.G 1: 5435265024
StyleLoss:updateOutput self.G 2: 30.930236816406
StyleLoss:updateGradInput self.gradInput 1: -5.6664730685441e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8330408895272e-05
dG 1: -0.011598493903875
dG 2: -6.6003064125297e-11
---
StyleLoss:updateOutput self.G 1: 1948370432
StyleLoss:updateOutput self.G 2: 22.155395507812
StyleLoss:updateGradInput self.gradInput 1: -1.1022421197993e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2337727285922e-05
dG 1: -0.0030535822734237
dG 2: -3.4723036945739e-11
---
StyleLoss:updateOutput self.G 1: 109356904
StyleLoss:updateOutput self.G 2: 2.4826538562775
StyleLoss:updateGradInput self.gradInput 1: -1.9880442181375e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011932375491597
dG 1: -0.00016160920495167
dG 2: -3.6689015540936e-12
---
StyleLoss:updateOutput self.G 1: 941554.4375
StyleLoss:updateOutput self.G 2: 0.085200771689415
StyleLoss:updateGradInput self.gradInput 1: -9.0489407966743e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293643916026
dG 1: -3.4254848287674e-05
dG 2: -3.0997032197944e-12
---
Iteration 126 / 2500
Content 1 loss: 472045.800781
Style 1 loss: 100002.742767
Style 2 loss: 83075238.281250
Style 3 loss: 106716667.968750
Style 4 loss: 6331589.355469
Style 5 loss: 237154.220581
Total loss: 196932698.369598
---
x1 value: -4.4987983703613
feval(x) grad value: 1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 541778560
StyleLoss:updateOutput self.G 2: 1.5415385961533
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011434936895967
dG 2: -3.2536154759982e-12
---
StyleLoss:updateOutput self.G 1: 5424570368
StyleLoss:updateOutput self.G 2: 30.86937713623
StyleLoss:updateGradInput self.gradInput 1: -5.6666111802883e-09
StyleLoss:updateGradInput self.gradInput 2: -2.83561530523e-05
dG 1: -0.011605921201408
dG 2: -6.6045328928066e-11
---
StyleLoss:updateOutput self.G 1: 1939849984
StyleLoss:updateOutput self.G 2: 22.058507919312
StyleLoss:updateGradInput self.gradInput 1: -1.1025750978888e-08
StyleLoss:updateGradInput self.gradInput 2: -6.236691842787e-05
dG 1: -0.0030565392225981
dG 2: -3.475665935615e-11
---
StyleLoss:updateOutput self.G 1: 108789288
StyleLoss:updateOutput self.G 2: 2.469767332077
StyleLoss:updateGradInput self.gradInput 1: -1.9895713521123e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011938291572733
dG 1: -0.00016170750313904
dG 2: -3.6711332758455e-12
---
StyleLoss:updateOutput self.G 1: 930415.4375
StyleLoss:updateOutput self.G 2: 0.08419281244278
StyleLoss:updateGradInput self.gradInput 1: -9.0489436388452e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293649736792
dG 1: -3.4262538974872e-05
dG 2: -3.10039971127e-12
---
Iteration 127 / 2500
Content 1 loss: 471558.056641
Style 1 loss: 100315.155029
Style 2 loss: 83164781.250000
Style 3 loss: 106836667.968750
Style 4 loss: 6334279.541016
Style 5 loss: 237241.333008
Total loss: 197144843.304443
---
x1 value: -4.4928026199341
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 540914048
StyleLoss:updateOutput self.G 2: 1.5390785932541
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011446946300566
dG 2: -3.2570330980863e-12
---
StyleLoss:updateOutput self.G 1: 5413981184
StyleLoss:updateOutput self.G 2: 30.809114456177
StyleLoss:updateGradInput self.gradInput 1: -5.6667466274973e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8382095479174e-05
dG 1: -0.011613277718425
dG 2: -6.6087191274988e-11
---
StyleLoss:updateOutput self.G 1: 1931437824
StyleLoss:updateOutput self.G 2: 21.96284866333
StyleLoss:updateGradInput self.gradInput 1: -1.1029014146402e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2394588894676e-05
dG 1: -0.0030594589188695
dG 2: -3.4789851555139e-11
---
StyleLoss:updateOutput self.G 1: 108228512
StyleLoss:updateOutput self.G 2: 2.4570369720459
StyleLoss:updateGradInput self.gradInput 1: -1.9910874726747e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011944436118938
dG 1: -0.00016180465172511
dG 2: -3.6733385430643e-12
---
StyleLoss:updateOutput self.G 1: 919483.75
StyleLoss:updateOutput self.G 2: 0.083203606307507
StyleLoss:updateGradInput self.gradInput 1: -9.0489436388452e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293655557558
dG 1: -3.4270087780897e-05
dG 2: -3.1010825417982e-12
---
Iteration 128 / 2500
Content 1 loss: 471079.736328
Style 1 loss: 100625.495911
Style 2 loss: 83253468.750000
Style 3 loss: 106955343.750000
Style 4 loss: 6336935.302734
Style 5 loss: 237326.843262
Total loss: 197354779.878235
---
x1 value: -4.4868817329407
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 540056832
StyleLoss:updateOutput self.G 2: 1.5366393327713
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011458855587989
dG 2: -3.2604218803967e-12
---
StyleLoss:updateOutput self.G 1: 5403496960
StyleLoss:updateOutput self.G 2: 30.749452590942
StyleLoss:updateGradInput self.gradInput 1: -5.6668816306171e-09
StyleLoss:updateGradInput self.gradInput 2: -2.84072048089e-05
dG 1: -0.011620561592281
dG 2: -6.612864422717e-11
---
StyleLoss:updateOutput self.G 1: 1923125632
StyleLoss:updateOutput self.G 2: 21.868335723877
StyleLoss:updateGradInput self.gradInput 1: -1.1032223135032e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2418817833532e-05
dG 1: -0.0030623434577137
dG 2: -3.4822644767729e-11
---
StyleLoss:updateOutput self.G 1: 107674456
StyleLoss:updateOutput self.G 2: 2.4444587230682
StyleLoss:updateGradInput self.gradInput 1: -1.9925940009102e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011950284533668
dG 1: -0.00016190059250221
dG 2: -3.6755169220692e-12
---
StyleLoss:updateOutput self.G 1: 908746.4375
StyleLoss:updateOutput self.G 2: 0.082232005894184
StyleLoss:updateGradInput self.gradInput 1: -9.048944349388e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293673019856
dG 1: -3.4277494705748e-05
dG 2: -3.1017532292621e-12
---
Iteration 129 / 2500
Content 1 loss: 470608.544922
Style 1 loss: 100934.326172
Style 2 loss: 83341289.062500
Style 3 loss: 107072742.187500
Style 4 loss: 6339556.640625
Style 5 loss: 237410.842896
Total loss: 197562541.604614
---
x1 value: -4.4810309410095
feval(x) grad value: 8.8330647147598e-19
---
StyleLoss:updateOutput self.G 1: 539206144
StyleLoss:updateOutput self.G 2: 1.5342190265656
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011470674071461
dG 2: -3.263784208174e-12
---
StyleLoss:updateOutput self.G 1: 5393114112
StyleLoss:updateOutput self.G 2: 30.690368652344
StyleLoss:updateGradInput self.gradInput 1: -5.6670175219153e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8436777938623e-05
dG 1: -0.011627774685621
dG 2: -6.6169680845718e-11
---
StyleLoss:updateOutput self.G 1: 1914917888
StyleLoss:updateOutput self.G 2: 21.774995803833
StyleLoss:updateGradInput self.gradInput 1: -1.1035369062995e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2446742958855e-05
dG 1: -0.0030651919078082
dG 2: -3.485503899392e-11
---
StyleLoss:updateOutput self.G 1: 107127368
StyleLoss:updateOutput self.G 2: 2.4320387840271
StyleLoss:updateGradInput self.gradInput 1: -1.994089160462e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011956467642449
dG 1: -0.00016199536912609
dG 2: -3.6776679791795e-12
---
StyleLoss:updateOutput self.G 1: 898215.3125
StyleLoss:updateOutput self.G 2: 0.081279054284096
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293661378324
dG 1: -3.4284770663362e-05
dG 2: -3.1024109062999e-12
---
Iteration 130 / 2500
Content 1 loss: 470146.142578
Style 1 loss: 101242.446899
Style 2 loss: 83428283.203125
Style 3 loss: 107188816.406250
Style 4 loss: 6342142.822266
Style 5 loss: 237493.171692
Total loss: 197768124.192810
---
x1 value: -4.4752569198608
feval(x) grad value: 1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 538363008
StyleLoss:updateOutput self.G 2: 1.5318200588226
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.001148239010945
dG 2: -3.2671174793331e-12
---
StyleLoss:updateOutput self.G 1: 5382835200
StyleLoss:updateOutput self.G 2: 30.631870269775
StyleLoss:updateGradInput self.gradInput 1: -5.6671503045891e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8463000489864e-05
dG 1: -0.011634914204478
dG 2: -6.6210321947313e-11
---
StyleLoss:updateOutput self.G 1: 1906806144
StyleLoss:updateOutput self.G 2: 21.682758331299
StyleLoss:updateGradInput self.gradInput 1: -1.1038461700252e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2474369769916e-05
dG 1: -0.0030680058989674
dG 2: -3.4887058519839e-11
---
StyleLoss:updateOutput self.G 1: 106587160
StyleLoss:updateOutput self.G 2: 2.4197747707367
StyleLoss:updateGradInput self.gradInput 1: -1.9955731289656e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011962444114033
dG 1: -0.00016208889428526
dG 2: -3.6797921480758e-12
---
StyleLoss:updateOutput self.G 1: 887878.5
StyleLoss:updateOutput self.G 2: 0.080343671143055
StyleLoss:updateGradInput self.gradInput 1: -9.0489457704734e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293673019856
dG 1: -3.4291904739803e-05
dG 2: -3.1030566571139e-12
---
Iteration 131 / 2500
Content 1 loss: 469691.748047
Style 1 loss: 101548.130035
Style 2 loss: 83514421.875000
Style 3 loss: 107303683.593750
Style 4 loss: 6344693.847656
Style 5 loss: 237573.921204
Total loss: 197971613.115692
---
x1 value: -4.4695520401001
feval(x) grad value: -1.766612942952e-17
---
StyleLoss:updateOutput self.G 1: 537527040
StyleLoss:updateOutput self.G 2: 1.5294411182404
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011494004866108
dG 2: -3.2704223443952e-12
---
StyleLoss:updateOutput self.G 1: 5372652544
StyleLoss:updateOutput self.G 2: 30.573930740356
StyleLoss:updateGradInput self.gradInput 1: -5.6672839754413e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8489770556916e-05
dG 1: -0.011641984805465
dG 2: -6.6250567531956e-11
---
StyleLoss:updateOutput self.G 1: 1898793728
StyleLoss:updateOutput self.G 2: 21.591648101807
StyleLoss:updateGradInput self.gradInput 1: -1.1041497494091e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2498787883669e-05
dG 1: -0.0030707875266671
dG 2: -3.4918665181571e-11
---
StyleLoss:updateOutput self.G 1: 106053776
StyleLoss:updateOutput self.G 2: 2.4076645374298
StyleLoss:updateGradInput self.gradInput 1: -1.9970450182427e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011968034232268
dG 1: -0.00016218131349888
dG 2: -3.6818898624391e-12
---
StyleLoss:updateOutput self.G 1: 877739.375
StyleLoss:updateOutput self.G 2: 0.079426184296608
StyleLoss:updateGradInput self.gradInput 1: -9.0489450599307e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4298904211028e-05
dG 2: -3.1036902648635e-12
---
Iteration 132 / 2500
Content 1 loss: 469244.921875
Style 1 loss: 101851.547241
Style 2 loss: 83599757.812500
Style 3 loss: 107417296.875000
Style 4 loss: 6347210.449219
Style 5 loss: 237653.068542
Total loss: 198173014.674377
---
x1 value: -4.4639196395874
feval(x) grad value: -1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 536697856
StyleLoss:updateOutput self.G 2: 1.5270817279816
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011505524162203
dG 2: -3.2737003212435e-12
---
StyleLoss:updateOutput self.G 1: 5362570752
StyleLoss:updateOutput self.G 2: 30.516553878784
StyleLoss:updateGradInput self.gradInput 1: -5.6674158699366e-09
StyleLoss:updateGradInput self.gradInput 2: -2.851382123481e-05
dG 1: -0.011648990213871
dG 2: -6.629042453854e-11
---
StyleLoss:updateOutput self.G 1: 1890877312
StyleLoss:updateOutput self.G 2: 21.501625061035
StyleLoss:updateGradInput self.gradInput 1: -1.1044475556332e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2524297391064e-05
dG 1: -0.0030735342297703
dG 2: -3.4949904081927e-11
---
StyleLoss:updateOutput self.G 1: 105526904
StyleLoss:updateOutput self.G 2: 2.3957040309906
StyleLoss:updateGradInput self.gradInput 1: -1.9985041177506e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011974565131823
dG 1: -0.00016227258311119
dG 2: -3.6839615559503e-12
---
StyleLoss:updateOutput self.G 1: 867785.5
StyleLoss:updateOutput self.G 2: 0.078525453805923
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4305776352994e-05
dG 2: -3.1043117295487e-12
---
Iteration 133 / 2500
Content 1 loss: 468806.005859
Style 1 loss: 102154.529572
Style 2 loss: 83684285.156250
Style 3 loss: 107529703.125000
Style 4 loss: 6349699.218750
Style 5 loss: 237730.773926
Total loss: 198372378.809357
---
x1 value: -4.4583578109741
feval(x) grad value: -1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 535875584
StyleLoss:updateOutput self.G 2: 1.5247423648834
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011516947997734
dG 2: -3.2769505425162e-12
---
StyleLoss:updateOutput self.G 1: 5352582656
StyleLoss:updateOutput self.G 2: 30.459720611572
StyleLoss:updateGradInput self.gradInput 1: -5.6675468762535e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8541981009766e-05
dG 1: -0.011655927635729
dG 2: -6.6329906844853e-11
---
StyleLoss:updateOutput self.G 1: 1883054336
StyleLoss:updateOutput self.G 2: 21.412670135498
StyleLoss:updateGradInput self.gradInput 1: -1.1047397663333e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2551174778491e-05
dG 1: -0.003076248569414
dG 2: -3.4980775220905e-11
---
StyleLoss:updateOutput self.G 1: 105006328
StyleLoss:updateOutput self.G 2: 2.3838863372803
StyleLoss:updateGradInput self.gradInput 1: -1.9999514933033e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011981202260358
dG 1: -0.00016236273222603
dG 2: -3.6860089633328e-12
---
StyleLoss:updateOutput self.G 1: 858009.8125
StyleLoss:updateOutput self.G 2: 0.077640861272812
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4312521165702e-05
dG 2: -3.1049223522123e-12
---
Iteration 134 / 2500
Content 1 loss: 468373.437500
Style 1 loss: 102455.726624
Style 2 loss: 83768021.484375
Style 3 loss: 107640914.062500
Style 4 loss: 6352157.226562
Style 5 loss: 237807.014465
Total loss: 198569728.952026
---
x1 value: -4.4528636932373
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 535059360
StyleLoss:updateOutput self.G 2: 1.5224198102951
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071981346817e-05
dG 1: -0.0011528288014233
dG 2: -3.2801771281815e-12
---
StyleLoss:updateOutput self.G 1: 5342688256
StyleLoss:updateOutput self.G 2: 30.403411865234
StyleLoss:updateGradInput self.gradInput 1: -5.667676994392e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8574615498655e-05
dG 1: -0.011662802658975
dG 2: -6.6369021389789e-11
---
StyleLoss:updateOutput self.G 1: 1875326336
StyleLoss:updateOutput self.G 2: 21.324794769287
StyleLoss:updateGradInput self.gradInput 1: -1.1050267367807e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2581537349615e-05
dG 1: -0.0030789307784289
dG 2: -3.5011271659613e-11
---
StyleLoss:updateOutput self.G 1: 104492016
StyleLoss:updateOutput self.G 2: 2.3722097873688
StyleLoss:updateGradInput self.gradInput 1: -2.0013866119939e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011987152538495
dG 1: -0.00016245181905106
dG 2: -3.6880312172249e-12
---
StyleLoss:updateOutput self.G 1: 848409.9375
StyleLoss:updateOutput self.G 2: 0.076772168278694
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4319149563089e-05
dG 2: -3.105522566535e-12
---
Iteration 135 / 2500
Content 1 loss: 467947.949219
Style 1 loss: 102754.554749
Style 2 loss: 83850996.093750
Style 3 loss: 107750929.687500
Style 4 loss: 6354585.937500
Style 5 loss: 237881.904602
Total loss: 198765096.127319
---
x1 value: -4.4474377632141
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 534250048
StyleLoss:updateOutput self.G 2: 1.5201172828674
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011539531406015
dG 2: -3.2833761751117e-12
---
StyleLoss:updateOutput self.G 1: 5332883456
StyleLoss:updateOutput self.G 2: 30.347618103027
StyleLoss:updateGradInput self.gradInput 1: -5.6678066684412e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8599633878912e-05
dG 1: -0.011669612489641
dG 2: -6.6407782051137e-11
---
StyleLoss:updateOutput self.G 1: 1867688704
StyleLoss:updateOutput self.G 2: 21.237945556641
StyleLoss:updateGradInput self.gradInput 1: -1.1053078452505e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2606901337858e-05
dG 1: -0.0030815813224763
dG 2: -3.5041410745285e-11
---
StyleLoss:updateOutput self.G 1: 103983512
StyleLoss:updateOutput self.G 2: 2.3606653213501
StyleLoss:updateGradInput self.gradInput 1: -2.0028124936289e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011993297812296
dG 1: -0.0001625398726901
dG 2: -3.690030486031e-12
---
StyleLoss:updateOutput self.G 1: 838984.3125
StyleLoss:updateOutput self.G 2: 0.075919263064861
StyleLoss:updateGradInput self.gradInput 1: -9.0489493231871e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4325657907175e-05
dG 2: -3.1061110714742e-12
---
Iteration 136 / 2500
Content 1 loss: 467529.150391
Style 1 loss: 103051.654816
Style 2 loss: 83933244.140625
Style 3 loss: 107859808.593750
Style 4 loss: 6356984.619141
Style 5 loss: 237955.398560
Total loss: 198958573.557281
---
x1 value: -4.4420809745789
feval(x) grad value: 2.6499192076328e-18
---
StyleLoss:updateOutput self.G 1: 533447072
StyleLoss:updateOutput self.G 2: 1.5178323984146
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011550688650459
dG 2: -3.2865511527536e-12
---
StyleLoss:updateOutput self.G 1: 5323173376
StyleLoss:updateOutput self.G 2: 30.29235458374
StyleLoss:updateGradInput self.gradInput 1: -5.6679358984013e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8625901904888e-05
dG 1: -0.011676359921694
dG 2: -6.6446168012213e-11
---
StyleLoss:updateOutput self.G 1: 1860140032
StyleLoss:updateOutput self.G 2: 21.152103424072
StyleLoss:updateGradInput self.gradInput 1: -1.1055839799212e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2632578192279e-05
dG 1: -0.003084200900048
dG 2: -3.5071199416814e-11
---
StyleLoss:updateOutput self.G 1: 103481080
StyleLoss:updateOutput self.G 2: 2.3492596149445
StyleLoss:updateGradInput self.gradInput 1: -2.0042248749519e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00011998836271232
dG 1: -0.000162626922247
dG 2: -3.6920063360701e-12
---
StyleLoss:updateOutput self.G 1: 829717.4375
StyleLoss:updateOutput self.G 2: 0.075080722570419
StyleLoss:updateGradInput self.gradInput 1: -9.0489457704734e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4332053473918e-05
dG 2: -3.1066898185939e-12
---
Iteration 137 / 2500
Content 1 loss: 467118.115234
Style 1 loss: 103347.244263
Style 2 loss: 84014712.890625
Style 3 loss: 107967539.062500
Style 4 loss: 6359356.201172
Style 5 loss: 238027.610779
Total loss: 199150101.124573
---
x1 value: -4.4367895126343
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 532649184
StyleLoss:updateOutput self.G 2: 1.5155620574951
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.001156177255325
dG 2: -3.2897046631924e-12
---
StyleLoss:updateOutput self.G 1: 5313551360
StyleLoss:updateOutput self.G 2: 30.237602233887
StyleLoss:updateGradInput self.gradInput 1: -5.6680629079153e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8650985768763e-05
dG 1: -0.011683043092489
dG 2: -6.64842000897e-11
---
StyleLoss:updateOutput self.G 1: 1852680064
StyleLoss:updateOutput self.G 2: 21.067279815674
StyleLoss:updateGradInput self.gradInput 1: -1.1058549631571e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2658844399266e-05
dG 1: -0.0030867892783135
dG 2: -3.5100637674201e-11
---
StyleLoss:updateOutput self.G 1: 102984248
StyleLoss:updateOutput self.G 2: 2.3379802703857
StyleLoss:updateGradInput self.gradInput 1: -2.0056290850334e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012004597374471
dG 1: -0.00016271298227366
dG 2: -3.6939596347041e-12
---
StyleLoss:updateOutput self.G 1: 820612.4375
StyleLoss:updateOutput self.G 2: 0.074256800115108
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4338347177254e-05
dG 2: -3.107258807894e-12
---
Iteration 138 / 2500
Content 1 loss: 466712.890625
Style 1 loss: 103641.929626
Style 2 loss: 84095443.359375
Style 3 loss: 108074156.250000
Style 4 loss: 6361699.218750
Style 5 loss: 238098.472595
Total loss: 199339752.120972
---
x1 value: -4.4315667152405
feval(x) grad value: -9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 531858368
StyleLoss:updateOutput self.G 2: 1.5133121013641
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011572760995477
dG 2: -3.292831068577e-12
---
StyleLoss:updateOutput self.G 1: 5304016896
StyleLoss:updateOutput self.G 2: 30.183349609375
StyleLoss:updateGradInput self.gradInput 1: -5.6681890292509e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8679931347142e-05
dG 1: -0.011689665727317
dG 2: -6.6521878283599e-11
---
StyleLoss:updateOutput self.G 1: 1845305216
StyleLoss:updateOutput self.G 2: 20.983415603638
StyleLoss:updateGradInput self.gradInput 1: -1.1061207061402e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2684463046025e-05
dG 1: -0.0030893483199179
dG 2: -3.5129739395234e-11
---
StyleLoss:updateOutput self.G 1: 102493560
StyleLoss:updateOutput self.G 2: 2.3268406391144
StyleLoss:updateGradInput self.gradInput 1: -2.0070213935242e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012010628415737
dG 1: -0.00016279798001051
dG 2: -3.6958890808902e-12
---
StyleLoss:updateOutput self.G 1: 811673.6875
StyleLoss:updateOutput self.G 2: 0.073447942733765
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4344513551332e-05
dG 2: -3.1078173888532e-12
---
Iteration 139 / 2500
Content 1 loss: 466315.283203
Style 1 loss: 103933.959961
Style 2 loss: 84175464.843750
Style 3 loss: 108179695.312500
Style 4 loss: 6364012.207031
Style 5 loss: 238168.075562
Total loss: 199527589.682007
---
x1 value: -4.4264049530029
feval(x) grad value: 1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 531073952
StyleLoss:updateOutput self.G 2: 1.5110801458359
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.00115836574696
dG 2: -3.2959318867903e-12
---
StyleLoss:updateOutput self.G 1: 5294570496
StyleLoss:updateOutput self.G 2: 30.129590988159
StyleLoss:updateGradInput self.gradInput 1: -5.6683147064973e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8709393518511e-05
dG 1: -0.011696227826178
dG 2: -6.6559237288377e-11
---
StyleLoss:updateOutput self.G 1: 1838016640
StyleLoss:updateOutput self.G 2: 20.900539398193
StyleLoss:updateGradInput self.gradInput 1: -1.1063820082313e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2712184444536e-05
dG 1: -0.0030918780248612
dG 2: -3.5158501110466e-11
---
StyleLoss:updateOutput self.G 1: 102008216
StyleLoss:updateOutput self.G 2: 2.3158218860626
StyleLoss:updateGradInput self.gradInput 1: -2.0084032215095e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012016533582937
dG 1: -0.00016288200276904
dG 2: -3.6977977103947e-12
---
StyleLoss:updateOutput self.G 1: 802884.875
StyleLoss:updateOutput self.G 2: 0.072652615606785
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4350581699982e-05
dG 2: -3.1083666456738e-12
---
Iteration 140 / 2500
Content 1 loss: 465924.316406
Style 1 loss: 104223.655701
Style 2 loss: 84254753.906250
Style 3 loss: 108284132.812500
Style 4 loss: 6366301.025391
Style 5 loss: 238236.373901
Total loss: 199713572.090149
---
x1 value: -4.4213094711304
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 530295552
StyleLoss:updateOutput self.G 2: 1.5088653564453
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011594472452998
dG 2: -3.2990088525559e-12
---
StyleLoss:updateOutput self.G 1: 5285208576
StyleLoss:updateOutput self.G 2: 30.076322555542
StyleLoss:updateGradInput self.gradInput 1: -5.6684399396545e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8736802050844e-05
dG 1: -0.011702729389071
dG 2: -6.6596235470673e-11
---
StyleLoss:updateOutput self.G 1: 1830810880
StyleLoss:updateOutput self.G 2: 20.818599700928
StyleLoss:updateGradInput self.gradInput 1: -1.1066383365232e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2737468397245e-05
dG 1: -0.0030943783931434
dG 2: -3.5186933228237e-11
---
StyleLoss:updateOutput self.G 1: 101528600
StyleLoss:updateOutput self.G 2: 2.3049333095551
StyleLoss:updateGradInput self.gradInput 1: -2.0097735031754e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012022159353364
dG 1: -0.00016296507965308
dG 2: -3.6996837884939e-12
---
StyleLoss:updateOutput self.G 1: 794249.75
StyleLoss:updateOutput self.G 2: 0.071871250867844
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4356544347247e-05
dG 2: -3.1089063615153e-12
---
Iteration 141 / 2500
Content 1 loss: 465539.990234
Style 1 loss: 104512.367249
Style 2 loss: 84333369.140625
Style 3 loss: 108387503.906250
Style 4 loss: 6368560.546875
Style 5 loss: 238303.504944
Total loss: 199897789.456177
---
x1 value: -4.4162793159485
feval(x) grad value: 1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 529523328
StyleLoss:updateOutput self.G 2: 1.5066680908203
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011605201289058
dG 2: -3.3020617490331e-12
---
StyleLoss:updateOutput self.G 1: 5275935232
StyleLoss:updateOutput self.G 2: 30.023542404175
StyleLoss:updateGradInput self.gradInput 1: -5.668563840544e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8765778552042e-05
dG 1: -0.011709173209965
dG 2: -6.6632893647167e-11
---
StyleLoss:updateOutput self.G 1: 1823687680
StyleLoss:updateOutput self.G 2: 20.737592697144
StyleLoss:updateGradInput self.gradInput 1: -1.1068902239231e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2764003814664e-05
dG 1: -0.0030968501232564
dG 2: -3.5215049626336e-11
---
StyleLoss:updateOutput self.G 1: 101054776
StyleLoss:updateOutput self.G 2: 2.2941765785217
StyleLoss:updateGradInput self.gradInput 1: -2.0111297516223e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012028504716
dG 1: -0.00016304719611071
dG 2: -3.7015468815071e-12
---
StyleLoss:updateOutput self.G 1: 785752.5
StyleLoss:updateOutput self.G 2: 0.071102365851402
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4362405131105e-05
dG 2: -3.1094369700585e-12
---
Iteration 142 / 2500
Content 1 loss: 465162.500000
Style 1 loss: 104798.458099
Style 2 loss: 84411246.093750
Style 3 loss: 108489832.031250
Style 4 loss: 6370795.166016
Style 5 loss: 238369.491577
Total loss: 200080203.740692
---
x1 value: -4.4113073348999
feval(x) grad value: 9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 528757120
StyleLoss:updateOutput self.G 2: 1.5044881105423
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011615846306086
dG 2: -3.3050903593818e-12
---
StyleLoss:updateOutput self.G 1: 5266742784
StyleLoss:updateOutput self.G 2: 29.97123336792
StyleLoss:updateGradInput self.gradInput 1: -5.6686868532552e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8791955628549e-05
dG 1: -0.011715558357537
dG 2: -6.6669239573436e-11
---
StyleLoss:updateOutput self.G 1: 1816643072
StyleLoss:updateOutput self.G 2: 20.657495498657
StyleLoss:updateGradInput self.gradInput 1: -1.1071379368843e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2789287767373e-05
dG 1: -0.0030992950778455
dG 2: -3.5242846835315e-11
---
StyleLoss:updateOutput self.G 1: 100586360
StyleLoss:updateOutput self.G 2: 2.2835421562195
StyleLoss:updateGradInput self.gradInput 1: -2.0124751642925e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012034294195473
dG 1: -0.00016312826483045
dG 2: -3.7033882904769e-12
---
StyleLoss:updateOutput self.G 1: 777404.875
StyleLoss:updateOutput self.G 2: 0.070346973836422
StyleLoss:updateGradInput self.gradInput 1: -9.0489493231871e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4368167689536e-05
dG 2: -3.1099580376226e-12
---
Iteration 143 / 2500
Content 1 loss: 464791.210938
Style 1 loss: 105083.461761
Style 2 loss: 84488449.218750
Style 3 loss: 108591140.625000
Style 4 loss: 6373004.882812
Style 5 loss: 238434.288025
Total loss: 200260903.687286
---
x1 value: -4.4064030647278
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 527997280
StyleLoss:updateOutput self.G 2: 1.502326130867
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011626401683316
dG 2: -3.3080942499208e-12
---
StyleLoss:updateOutput self.G 1: 5257631232
StyleLoss:updateOutput self.G 2: 29.919380187988
StyleLoss:updateGradInput self.gradInput 1: -5.6688094218771e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8817401471315e-05
dG 1: -0.011721887625754
dG 2: -6.6705266310585e-11
---
StyleLoss:updateOutput self.G 1: 1809679232
StyleLoss:updateOutput self.G 2: 20.57830619812
StyleLoss:updateGradInput self.gradInput 1: -1.1073816530427e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2814171542414e-05
dG 1: -0.0031017113942653
dG 2: -3.5270324855174e-11
---
StyleLoss:updateOutput self.G 1: 100123440
StyleLoss:updateOutput self.G 2: 2.2730333805084
StyleLoss:updateGradInput self.gradInput 1: -2.0138088530075e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012039814464515
dG 1: -0.00016320844588336
dG 2: -3.7052084490841e-12
---
StyleLoss:updateOutput self.G 1: 769201.4375
StyleLoss:updateOutput self.G 2: 0.069604642689228
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4373835660517e-05
dG 2: -3.1104708652502e-12
---
Iteration 144 / 2500
Content 1 loss: 464426.416016
Style 1 loss: 105366.966248
Style 2 loss: 84565007.812500
Style 3 loss: 108691417.968750
Style 4 loss: 6375187.500000
Style 5 loss: 238497.985840
Total loss: 200439904.649353
---
x1 value: -4.4015555381775
feval(x) grad value: -8.8330647147598e-19
---
StyleLoss:updateOutput self.G 1: 527243264
StyleLoss:updateOutput self.G 2: 1.5001804828644
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011636877898127
dG 2: -3.311074721693e-12
---
StyleLoss:updateOutput self.G 1: 5248601600
StyleLoss:updateOutput self.G 2: 29.867992401123
StyleLoss:updateGradInput self.gradInput 1: -5.6689315464098e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8844939151895e-05
dG 1: -0.011728161014616
dG 2: -6.6740953041933e-11
---
StyleLoss:updateOutput self.G 1: 1802792448
StyleLoss:updateOutput self.G 2: 20.499990463257
StyleLoss:updateGradInput self.gradInput 1: -1.1076211059446e-08
StyleLoss:updateGradInput self.gradInput 2: -6.28380003036e-05
dG 1: -0.003104101633653
dG 2: -3.5297501033149e-11
---
StyleLoss:updateOutput self.G 1: 99665480
StyleLoss:updateOutput self.G 2: 2.2626366615295
StyleLoss:updateGradInput self.gradInput 1: -2.0151320612172e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012045402399963
dG 1: -0.00016328778292518
dG 2: -3.707009525733e-12
---
StyleLoss:updateOutput self.G 1: 761138.1875
StyleLoss:updateOutput self.G 2: 0.068875007331371
StyleLoss:updateGradInput self.gradInput 1: -9.0489493231871e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4379394492134e-05
dG 2: -3.1109745855795e-12
---
Iteration 145 / 2500
Content 1 loss: 464067.480469
Style 1 loss: 105648.159027
Style 2 loss: 84640880.859375
Style 3 loss: 108790722.656250
Style 4 loss: 6377348.144531
Style 5 loss: 238560.516357
Total loss: 200617227.816010
---
x1 value: -4.3967709541321
feval(x) grad value: -1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 526494720
StyleLoss:updateOutput self.G 2: 1.4980506896973
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011647278442979
dG 2: -3.3140343767835e-12
---
StyleLoss:updateOutput self.G 1: 5239647744
StyleLoss:updateOutput self.G 2: 29.817047119141
StyleLoss:updateGradInput self.gradInput 1: -5.6690518945857e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8870401365566e-05
dG 1: -0.011734379455447
dG 2: -6.6776348339737e-11
---
StyleLoss:updateOutput self.G 1: 1795982208
StyleLoss:updateOutput self.G 2: 20.422552108765
StyleLoss:updateGradInput self.gradInput 1: -1.1078568284972e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2859726313036e-05
dG 1: -0.0031064653303474
dG 2: -3.5324375369239e-11
---
StyleLoss:updateOutput self.G 1: 99212984
StyleLoss:updateOutput self.G 2: 2.2523636817932
StyleLoss:updateGradInput self.gradInput 1: -2.0164442560144e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012050702207489
dG 1: -0.00016336614498869
dG 2: -3.7087884846576e-12
---
StyleLoss:updateOutput self.G 1: 753206.5625
StyleLoss:updateOutput self.G 2: 0.068157263100147
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4384880564176e-05
dG 2: -3.1114702828128e-12
---
Iteration 146 / 2500
Content 1 loss: 463715.136719
Style 1 loss: 105928.161621
Style 2 loss: 84716121.093750
Style 3 loss: 108889031.250000
Style 4 loss: 6379483.154297
Style 5 loss: 238622.085571
Total loss: 200792900.881958
---
x1 value: -4.3920435905457
feval(x) grad value: -7.9497582432838e-18
---
StyleLoss:updateOutput self.G 1: 525751616
StyleLoss:updateOutput self.G 2: 1.4959362745285
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011657602153718
dG 2: -3.3169716973092e-12
---
StyleLoss:updateOutput self.G 1: 5230775808
StyleLoss:updateOutput self.G 2: 29.766555786133
StyleLoss:updateGradInput self.gradInput 1: -5.66917313094e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8895818104502e-05
dG 1: -0.011740542948246
dG 2: -6.6811417509527e-11
---
StyleLoss:updateOutput self.G 1: 1789247616
StyleLoss:updateOutput self.G 2: 20.34596824646
StyleLoss:updateGradInput self.gradInput 1: -1.1080885542469e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2882441852707e-05
dG 1: -0.0031088020186871
dG 2: -3.5350947863444e-11
---
StyleLoss:updateOutput self.G 1: 98765248
StyleLoss:updateOutput self.G 2: 2.2421989440918
StyleLoss:updateGradInput self.gradInput 1: -2.017746147942e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012057022831868
dG 1: -0.00016344370669685
dG 2: -3.7105496626666e-12
---
StyleLoss:updateOutput self.G 1: 745406.1875
StyleLoss:updateOutput self.G 2: 0.067451432347298
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.439026477281e-05
dG 2: -3.1119570895882e-12
---
Iteration 147 / 2500
Content 1 loss: 463368.408203
Style 1 loss: 106207.225800
Style 2 loss: 84790699.218750
Style 3 loss: 108986390.625000
Style 4 loss: 6381593.994141
Style 5 loss: 238682.556152
Total loss: 200966942.028046
---
x1 value: -4.3873777389526
feval(x) grad value: 1.3249596244959e-17
---
StyleLoss:updateOutput self.G 1: 525014464
StyleLoss:updateOutput self.G 2: 1.4938387870789
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.001166784320958
dG 2: -3.3198855990679e-12
---
StyleLoss:updateOutput self.G 1: 5221977088
StyleLoss:updateOutput self.G 2: 29.716484069824
StyleLoss:updateGradInput self.gradInput 1: -5.6692921468482e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8918937459821e-05
dG 1: -0.011746656149626
dG 2: -6.6846195245773e-11
---
StyleLoss:updateOutput self.G 1: 1782585344
StyleLoss:updateOutput self.G 2: 20.270215988159
StyleLoss:updateGradInput self.gradInput 1: -1.1083169937365e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2905601225793e-05
dG 1: -0.0031111142598093
dG 2: -3.5377235862999e-11
---
StyleLoss:updateOutput self.G 1: 98322520
StyleLoss:updateOutput self.G 2: 2.2321488857269
StyleLoss:updateGradInput self.gradInput 1: -2.0190372040929e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012062913447153
dG 1: -0.00016352040984202
dG 2: -3.7122904576747e-12
---
StyleLoss:updateOutput self.G 1: 737733.8125
StyleLoss:updateOutput self.G 2: 0.066757142543793
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4395561669953e-05
dG 2: -3.1124365237889e-12
---
Iteration 148 / 2500
Content 1 loss: 463027.880859
Style 1 loss: 106483.200073
Style 2 loss: 84864673.828125
Style 3 loss: 109082800.781250
Style 4 loss: 6383682.861328
Style 5 loss: 238742.019653
Total loss: 201139410.571289
---
x1 value: -4.3827676773071
feval(x) grad value: -9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 524282720
StyleLoss:updateOutput self.G 2: 1.4917569160461
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011678009759635
dG 2: -3.3227778167833e-12
---
StyleLoss:updateOutput self.G 1: 5213256704
StyleLoss:updateOutput self.G 2: 29.66685295105
StyleLoss:updateGradInput self.gradInput 1: -5.6694107186672e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8943280995009e-05
dG 1: -0.011752713471651
dG 2: -6.6880674609582e-11
---
StyleLoss:updateOutput self.G 1: 1775997952
StyleLoss:updateOutput self.G 2: 20.195308685303
StyleLoss:updateGradInput self.gradInput 1: -1.1085417916945e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2927960243542e-05
dG 1: -0.0031133994925767
dG 2: -3.540323242901e-11
---
StyleLoss:updateOutput self.G 1: 97884768
StyleLoss:updateOutput self.G 2: 2.2222101688385
StyleLoss:updateGradInput self.gradInput 1: -2.0203176021028e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012068331125192
dG 1: -0.00016359621076845
dG 2: -3.7140117370438e-12
---
StyleLoss:updateOutput self.G 1: 730190.5625
StyleLoss:updateOutput self.G 2: 0.066074572503567
StyleLoss:updateGradInput self.gradInput 1: -9.0489493231871e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4400771255605e-05
dG 2: -3.1129077180531e-12
---
Iteration 149 / 2500
Content 1 loss: 462692.382812
Style 1 loss: 106758.693695
Style 2 loss: 84938033.203125
Style 3 loss: 109178238.281250
Style 4 loss: 6385747.558594
Style 5 loss: 238800.453186
Total loss: 201310270.572662
---
x1 value: -4.3782176971436
feval(x) grad value: -2.1199353661062e-17
---
StyleLoss:updateOutput self.G 1: 523555712
StyleLoss:updateOutput self.G 2: 1.4896883964539
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011688109952956
dG 2: -3.3256518199021e-12
---
StyleLoss:updateOutput self.G 1: 5204608000
StyleLoss:updateOutput self.G 2: 29.617645263672
StyleLoss:updateGradInput self.gradInput 1: -5.6695284023078e-09
StyleLoss:updateGradInput self.gradInput 2: -2.8971664505661e-05
dG 1: -0.01175872143358
dG 2: -6.6914862539846e-11
---
StyleLoss:updateOutput self.G 1: 1769479552
StyleLoss:updateOutput self.G 2: 20.121185302734
StyleLoss:updateGradInput self.gradInput 1: -1.1087631257567e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2951512518339e-05
dG 1: -0.0031156614422798
dG 2: -3.5428944500371e-11
---
StyleLoss:updateOutput self.G 1: 97451576
StyleLoss:updateOutput self.G 2: 2.2123761177063
StyleLoss:updateGradInput self.gradInput 1: -2.0215864537931e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012073523248546
dG 1: -0.00016367124044336
dG 2: -3.7157152354972e-12
---
StyleLoss:updateOutput self.G 1: 722762.3125
StyleLoss:updateOutput self.G 2: 0.065402388572693
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4405897167744e-05
dG 2: -3.1133717565829e-12
---
Iteration 150 / 2500
Content 1 loss: 462362.304688
Style 1 loss: 107034.164429
Style 2 loss: 85010759.765625
Style 3 loss: 109272796.875000
Style 4 loss: 6387793.212891
Style 5 loss: 238857.994080
Total loss: 201479604.316711
---
x1 value: -4.3737215995789
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 522834784
StyleLoss:updateOutput self.G 2: 1.4876368045807
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.00116981274914
dG 2: -3.3285017537327e-12
---
StyleLoss:updateOutput self.G 1: 5196035072
StyleLoss:updateOutput self.G 2: 29.568859100342
StyleLoss:updateGradInput self.gradInput 1: -5.66964519777e-09
StyleLoss:updateGradInput self.gradInput 2: -2.899990977312e-05
dG 1: -0.011764676310122
dG 2: -6.6948759036567e-11
---
StyleLoss:updateOutput self.G 1: 1763032960
StyleLoss:updateOutput self.G 2: 20.047876358032
StyleLoss:updateGradInput self.gradInput 1: -1.1089810847409e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2974722823128e-05
dG 1: -0.0031178994104266
dG 2: -3.5454392893763e-11
---
StyleLoss:updateOutput self.G 1: 97023112
StyleLoss:updateOutput self.G 2: 2.2026481628418
StyleLoss:updateGradInput self.gradInput 1: -2.0228482000562e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012078649160685
dG 1: -0.0001637454261072
dG 2: -3.7174000856732e-12
---
StyleLoss:updateOutput self.G 1: 715466.375
StyleLoss:updateOutput self.G 2: 0.064742185175419
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4410928492434e-05
dG 2: -3.1138273383358e-12
---
Iteration 151 / 2500
Content 1 loss: 462038.281250
Style 1 loss: 107306.579590
Style 2 loss: 85082882.812500
Style 3 loss: 109366429.687500
Style 4 loss: 6389814.697266
Style 5 loss: 238914.436340
Total loss: 201647386.494446
---
x1 value: -4.3692846298218
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 522119488
StyleLoss:updateOutput self.G 2: 1.4856017827988
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011708064703271
dG 2: -3.3313295698389e-12
---
StyleLoss:updateOutput self.G 1: 5187533312
StyleLoss:updateOutput self.G 2: 29.520486831665
StyleLoss:updateGradInput self.gradInput 1: -5.6697619932322e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9023416573182e-05
dG 1: -0.011770581826568
dG 2: -6.698235716085e-11
---
StyleLoss:updateOutput self.G 1: 1756657152
StyleLoss:updateOutput self.G 2: 19.975379943848
StyleLoss:updateGradInput self.gradInput 1: -1.1091959351006e-08
StyleLoss:updateGradInput self.gradInput 2: -6.2994848121889e-05
dG 1: -0.0031201120000333
dG 2: -3.5479556792506e-11
---
StyleLoss:updateOutput self.G 1: 96599248
StyleLoss:updateOutput self.G 2: 2.1930258274078
StyleLoss:updateGradInput self.gradInput 1: -2.0240952025574e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012083011097275
dG 1: -0.00016381884051953
dG 2: -3.7190662875719e-12
---
StyleLoss:updateOutput self.G 1: 708278.125
StyleLoss:updateOutput self.G 2: 0.064091719686985
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4415897971485e-05
dG 2: -3.1142770653969e-12
---
Iteration 152 / 2500
Content 1 loss: 461719.970703
Style 1 loss: 107576.843262
Style 2 loss: 85154408.203125
Style 3 loss: 109459148.437500
Style 4 loss: 6391817.138672
Style 5 loss: 238970.054626
Total loss: 201813640.647888
---
x1 value: -4.3649024963379
feval(x) grad value: 7.9497582432838e-18
---
StyleLoss:updateOutput self.G 1: 521409344
StyleLoss:updateOutput self.G 2: 1.4835813045502
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011717928573489
dG 2: -3.3341367861039e-12
---
StyleLoss:updateOutput self.G 1: 5179107328
StyleLoss:updateOutput self.G 2: 29.472532272339
StyleLoss:updateGradInput self.gradInput 1: -5.6698770123376e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9048238502583e-05
dG 1: -0.011776437051594
dG 2: -6.7015663851588e-11
---
StyleLoss:updateOutput self.G 1: 1750345856
StyleLoss:updateOutput self.G 2: 19.903612136841
StyleLoss:updateGradInput self.gradInput 1: -1.1094076768359e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3017236243468e-05
dG 1: -0.0031223017722368
dG 2: -3.5504450074386e-11
---
StyleLoss:updateOutput self.G 1: 96179928
StyleLoss:updateOutput self.G 2: 2.1835060119629
StyleLoss:updateGradInput self.gradInput 1: -2.0253372312595e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012088235234842
dG 1: -0.00016389148368035
dG 2: -3.7207151422358e-12
---
StyleLoss:updateOutput self.G 1: 701212.125
StyleLoss:updateOutput self.G 2: 0.063452325761318
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4420776501065e-05
dG 2: -3.1147179020002e-12
---
Iteration 153 / 2500
Content 1 loss: 461406.494141
Style 1 loss: 107845.962524
Style 2 loss: 85225335.937500
Style 3 loss: 109551000.000000
Style 4 loss: 6393794.677734
Style 5 loss: 239024.688721
Total loss: 201978407.760620
---
x1 value: -4.3605737686157
feval(x) grad value: 6.1831448867415e-18
---
StyleLoss:updateOutput self.G 1: 520703744
StyleLoss:updateOutput self.G 2: 1.4815737009048
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011727733071893
dG 2: -3.3369257877724e-12
---
StyleLoss:updateOutput self.G 1: 5170747904
StyleLoss:updateOutput self.G 2: 29.424961090088
StyleLoss:updateGradInput self.gradInput 1: -5.6699924755321e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9073493351461e-05
dG 1: -0.011782242916524
dG 2: -6.7048706864359e-11
---
StyleLoss:updateOutput self.G 1: 1744104064
StyleLoss:updateOutput self.G 2: 19.832635879517
StyleLoss:updateGradInput self.gradInput 1: -1.1096162211288e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3039224187378e-05
dG 1: -0.0031244673300534
dG 2: -3.5529086617192e-11
---
StyleLoss:updateOutput self.G 1: 95764800
StyleLoss:updateOutput self.G 2: 2.1740820407867
StyleLoss:updateGradInput self.gradInput 1: -2.0265659372853e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012093858822482
dG 1: -0.0001639633992454
dG 2: -3.7223475170267e-12
---
StyleLoss:updateOutput self.G 1: 694256.6875
StyleLoss:updateOutput self.G 2: 0.062822930514812
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4425571357133e-05
dG 2: -3.115152450231e-12
---
Iteration 154 / 2500
Content 1 loss: 461098.681641
Style 1 loss: 108115.242004
Style 2 loss: 85295689.453125
Style 3 loss: 109641960.937500
Style 4 loss: 6395756.103516
Style 5 loss: 239078.475952
Total loss: 202141698.893738
---
x1 value: -4.3563013076782
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 520003328
StyleLoss:updateOutput self.G 2: 1.4795805215836
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011737463064492
dG 2: -3.3396946232805e-12
---
StyleLoss:updateOutput self.G 1: 5162459648
StyleLoss:updateOutput self.G 2: 29.37779045105
StyleLoss:updateGradInput self.gradInput 1: -5.6701066064591e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9100618121447e-05
dG 1: -0.011788001284003
dG 2: -6.7081479260267e-11
---
StyleLoss:updateOutput self.G 1: 1737926400
StyleLoss:updateOutput self.G 2: 19.762384414673
StyleLoss:updateGradInput self.gradInput 1: -1.1098221008865e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3062361732591e-05
dG 1: -0.0031266117002815
dG 2: -3.5553466420923e-11
---
StyleLoss:updateOutput self.G 1: 95354152
StyleLoss:updateOutput self.G 2: 2.1647591590881
StyleLoss:updateGradInput self.gradInput 1: -2.0277852286199e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012099513696739
dG 1: -0.00016403451445512
dG 2: -3.723962110902e-12
---
StyleLoss:updateOutput self.G 1: 687417.5625
StyleLoss:updateOutput self.G 2: 0.06220406666398
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4430297091603e-05
dG 2: -3.1155796258869e-12
---
Iteration 155 / 2500
Content 1 loss: 460795.849609
Style 1 loss: 108382.186890
Style 2 loss: 85365474.609375
Style 3 loss: 109732078.125000
Style 4 loss: 6397695.556641
Style 5 loss: 239131.324768
Total loss: 202303557.652283
---
x1 value: -4.352080821991
feval(x) grad value: 7.9497582432838e-18
---
StyleLoss:updateOutput self.G 1: 519308640
StyleLoss:updateOutput self.G 2: 1.4776041507721
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011747116222978
dG 2: -3.342440690543e-12
---
StyleLoss:updateOutput self.G 1: 5154239488
StyleLoss:updateOutput self.G 2: 29.331018447876
StyleLoss:updateGradInput self.gradInput 1: -5.6702198492076e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9128101232345e-05
dG 1: -0.011793708428741
dG 2: -6.7113974100419e-11
---
StyleLoss:updateOutput self.G 1: 1731813504
StyleLoss:updateOutput self.G 2: 19.69287109375
StyleLoss:updateGradInput self.gradInput 1: -1.110024694384e-08
StyleLoss:updateGradInput self.gradInput 2: -6.308426236501e-05
dG 1: -0.0031287323217839
dG 2: -3.5577582546686e-11
---
StyleLoss:updateOutput self.G 1: 94947408
StyleLoss:updateOutput self.G 2: 2.1555254459381
StyleLoss:updateGradInput self.gradInput 1: -2.0289967039844e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012104245979572
dG 1: -0.00016410496027675
dG 2: -3.7255619596277e-12
---
StyleLoss:updateOutput self.G 1: 680683.75
StyleLoss:updateOutput self.G 2: 0.061594717204571
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4434950066498e-05
dG 2: -3.1160005131703e-12
---
Iteration 156 / 2500
Content 1 loss: 460497.998047
Style 1 loss: 108647.254944
Style 2 loss: 85434697.265625
Style 3 loss: 109821339.843750
Style 4 loss: 6399615.234375
Style 5 loss: 239183.349609
Total loss: 202463980.946350
---
x1 value: -4.3479127883911
feval(x) grad value: 4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 518619008
StyleLoss:updateOutput self.G 2: 1.4756417274475
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071979527827e-05
dG 1: -0.0011756698368117
dG 2: -3.3451670253259e-12
---
StyleLoss:updateOutput self.G 1: 5146086912
StyleLoss:updateOutput self.G 2: 29.284622192383
StyleLoss:updateGradInput self.gradInput 1: -5.6703322037777e-09
StyleLoss:updateGradInput self.gradInput 2: -2.915220829891e-05
dG 1: -0.011799372732639
dG 2: -6.7146198323709e-11
---
StyleLoss:updateOutput self.G 1: 1725762816
StyleLoss:updateOutput self.G 2: 19.624073028564
StyleLoss:updateGradInput self.gradInput 1: -1.1102247121642e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3105522713158e-05
dG 1: -0.0031308331526816
dG 2: -3.560145928061e-11
---
StyleLoss:updateOutput self.G 1: 94545024
StyleLoss:updateOutput self.G 2: 2.1463899612427
StyleLoss:updateGradInput self.gradInput 1: -2.030196277758e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012109431554563
dG 1: -0.00016417469305452
dG 2: -3.7271440274378e-12
---
StyleLoss:updateOutput self.G 1: 674056.1875
StyleLoss:updateOutput self.G 2: 0.060994997620583
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.44395157299e-05
dG 2: -3.1164146784002e-12
---
Iteration 157 / 2500
Content 1 loss: 460205.126953
Style 1 loss: 108910.835266
Style 2 loss: 85503369.140625
Style 3 loss: 109909804.687500
Style 4 loss: 6401517.333984
Style 5 loss: 239234.481812
Total loss: 202623041.606140
---
x1 value: -4.3438005447388
feval(x) grad value: -8.8330647147598e-19
---
StyleLoss:updateOutput self.G 1: 517933632
StyleLoss:updateOutput self.G 2: 1.4736915826797
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011766219977289
dG 2: -3.3478766633954e-12
---
StyleLoss:updateOutput self.G 1: 5138002944
StyleLoss:updateOutput self.G 2: 29.238622665405
StyleLoss:updateGradInput self.gradInput 1: -5.6704441142585e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9177375836298e-05
dG 1: -0.011804988607764
dG 2: -6.717815886903e-11
---
StyleLoss:updateOutput self.G 1: 1719774464
StyleLoss:updateOutput self.G 2: 19.555978775024
StyleLoss:updateGradInput self.gradInput 1: -1.1104217989555e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3126768509392e-05
dG 1: -0.0031329109333456
dG 2: -3.5625093153246e-11
---
StyleLoss:updateOutput self.G 1: 94146904
StyleLoss:updateOutput self.G 2: 2.1373517513275
StyleLoss:updateGradInput self.gradInput 1: -2.0313866144761e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001211478447658
dG 1: -0.00016424365458079
dG 2: -3.7287096153749e-12
---
StyleLoss:updateOutput self.G 1: 667540.0625
StyleLoss:updateOutput self.G 2: 0.060405354946852
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293673019856
dG 1: -3.4444019547664e-05
dG 2: -3.1168216878957e-12
---
Iteration 158 / 2500
Content 1 loss: 459916.308594
Style 1 loss: 109174.667358
Style 2 loss: 85571472.656250
Style 3 loss: 109997449.218750
Style 4 loss: 6403398.193359
Style 5 loss: 239284.744263
Total loss: 202780695.788574
---
x1 value: -4.3397359848022
feval(x) grad value: 2.6499192076328e-18
---
StyleLoss:updateOutput self.G 1: 517253056
StyleLoss:updateOutput self.G 2: 1.471755027771
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011775675229728
dG 2: -3.3505672195067e-12
---
StyleLoss:updateOutput self.G 1: 5129981440
StyleLoss:updateOutput self.G 2: 29.192966461182
StyleLoss:updateGradInput self.gradInput 1: -5.670555136561e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9205653845565e-05
dG 1: -0.011810560710728
dG 2: -6.7209869614171e-11
---
StyleLoss:updateOutput self.G 1: 1713848576
StyleLoss:updateOutput self.G 2: 19.488590240479
StyleLoss:updateGradInput self.gradInput 1: -1.1106160435759e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3149171182886e-05
dG 1: -0.0031349677592516
dG 2: -3.564848069515e-11
---
StyleLoss:updateOutput self.G 1: 93752504
StyleLoss:updateOutput self.G 2: 2.1283981800079
StyleLoss:updateGradInput self.gradInput 1: -2.0325666483245e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012120242899982
dG 1: -0.00016431193216704
dG 2: -3.7302604581624e-12
---
StyleLoss:updateOutput self.G 1: 661127.25
StyleLoss:updateOutput self.G 2: 0.05982506647706
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293673019856
dG 1: -3.4448446967872e-05
dG 2: -3.1172224090187e-12
---
Iteration 159 / 2500
Content 1 loss: 459633.203125
Style 1 loss: 109436.737061
Style 2 loss: 85639089.843750
Style 3 loss: 110084285.156250
Style 4 loss: 6405262.939453
Style 5 loss: 239334.182739
Total loss: 202937042.062378
---
x1 value: -4.3357253074646
feval(x) grad value: -1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 516576960
StyleLoss:updateOutput self.G 2: 1.4698314666748
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011785067617893
dG 2: -3.3532395610214e-12
---
StyleLoss:updateOutput self.G 1: 5122027008
StyleLoss:updateOutput self.G 2: 29.147705078125
StyleLoss:updateGradInput self.gradInput 1: -5.6706661588635e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9234584872029e-05
dG 1: -0.011816086247563
dG 2: -6.724130974245e-11
---
StyleLoss:updateOutput self.G 1: 1707981056
StyleLoss:updateOutput self.G 2: 19.421869277954
StyleLoss:updateGradInput self.gradInput 1: -1.1108078901145e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3172017689794e-05
dG 1: -0.0031370033975691
dG 2: -3.567163231466e-11
---
StyleLoss:updateOutput self.G 1: 93362624
StyleLoss:updateOutput self.G 2: 2.1195473670959
StyleLoss:updateGradInput self.gradInput 1: -2.0337374451174e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012125098874094
dG 1: -0.00016437943850178
dG 2: -3.7317930863534e-12
---
StyleLoss:updateOutput self.G 1: 654823.375
StyleLoss:updateOutput self.G 2: 0.059254627674818
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4452794352546e-05
dG 2: -3.1176157575669e-12
---
Iteration 160 / 2500
Content 1 loss: 459353.906250
Style 1 loss: 109697.753906
Style 2 loss: 85706115.234375
Style 3 loss: 110170324.218750
Style 4 loss: 6407106.445312
Style 5 loss: 239382.797241
Total loss: 203091980.355835
---
x1 value: -4.33176612854
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 515906624
StyleLoss:updateOutput self.G 2: 1.467924118042
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011794380843639
dG 2: -3.355889351131e-12
---
StyleLoss:updateOutput self.G 1: 5114136064
StyleLoss:updateOutput self.G 2: 29.102802276611
StyleLoss:updateGradInput self.gradInput 1: -5.6707758488983e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9259543225635e-05
dG 1: -0.011821568012238
dG 2: -6.7272507009442e-11
---
StyleLoss:updateOutput self.G 1: 1702176384
StyleLoss:updateOutput self.G 2: 19.355861663818
StyleLoss:updateGradInput self.gradInput 1: -1.110996450393e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3192674133461e-05
dG 1: -0.003139017848298
dG 2: -3.5694541072884e-11
---
StyleLoss:updateOutput self.G 1: 92976784
StyleLoss:updateOutput self.G 2: 2.1107876300812
StyleLoss:updateGradInput self.gradInput 1: -2.0348947415982e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012129661627114
dG 1: -0.00016444633365609
dG 2: -3.733310535714e-12
---
StyleLoss:updateOutput self.G 1: 648619
StyleLoss:updateOutput self.G 2: 0.058693207800388
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4457087167539e-05
dG 2: -3.1180036851042e-12
---
Iteration 161 / 2500
Content 1 loss: 459080.029297
Style 1 loss: 109955.543518
Style 2 loss: 85772630.859375
Style 3 loss: 110255554.687500
Style 4 loss: 6408932.373047
Style 5 loss: 239430.541992
Total loss: 203245584.034729
---
x1 value: -4.3278522491455
feval(x) grad value: 1.8549435900995e-17
---
StyleLoss:updateOutput self.G 1: 515240416
StyleLoss:updateOutput self.G 2: 1.4660286903381
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011803635861725
dG 2: -3.3585230950484e-12
---
StyleLoss:updateOutput self.G 1: 5106307584
StyleLoss:updateOutput self.G 2: 29.058254241943
StyleLoss:updateGradInput self.gradInput 1: -5.6708846507547e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9286728022271e-05
dG 1: -0.011827006936073
dG 2: -6.7303447537359e-11
---
StyleLoss:updateOutput self.G 1: 1696426240
StyleLoss:updateOutput self.G 2: 19.290475845337
StyleLoss:updateGradInput self.gradInput 1: -1.111183056679e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3213257817551e-05
dG 1: -0.0031410134397447
dG 2: -3.5717220847609e-11
---
StyleLoss:updateOutput self.G 1: 92594768
StyleLoss:updateOutput self.G 2: 2.1021151542664
StyleLoss:updateGradInput self.gradInput 1: -2.0360461761015e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012134992721258
dG 1: -0.00016451245755889
dG 2: -3.7348128062442e-12
---
StyleLoss:updateOutput self.G 1: 642511.375
StyleLoss:updateOutput self.G 2: 0.058140527456999
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4461296309019e-05
dG 2: -3.1183853242689e-12
---
Iteration 162 / 2500
Content 1 loss: 458810.058594
Style 1 loss: 110212.646484
Style 2 loss: 85838625.000000
Style 3 loss: 110340035.156250
Style 4 loss: 6410738.525391
Style 5 loss: 239477.577209
Total loss: 203397898.963928
---
x1 value: -4.3239960670471
feval(x) grad value: -2.6499192076328e-18
---
StyleLoss:updateOutput self.G 1: 514578688
StyleLoss:updateOutput self.G 2: 1.4641457796097
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011812830343843
dG 2: -3.3611388412097e-12
---
StyleLoss:updateOutput self.G 1: 5098540544
StyleLoss:updateOutput self.G 2: 29.014049530029
StyleLoss:updateGradInput self.gradInput 1: -5.6709938967003e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9310431273188e-05
dG 1: -0.011832401156425
dG 2: -6.7334152142884e-11
---
StyleLoss:updateOutput self.G 1: 1690737024
StyleLoss:updateOutput self.G 2: 19.225786209106
StyleLoss:updateGradInput self.gradInput 1: -1.1113665543405e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3233150285669e-05
dG 1: -0.0031429876107723
dG 2: -3.5739671638835e-11
---
StyleLoss:updateOutput self.G 1: 92217008
StyleLoss:updateOutput self.G 2: 2.0935392379761
StyleLoss:updateGradInput self.gradInput 1: -2.0371832221144e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012140259059379
dG 1: -0.0001645779266255
dG 2: -3.7362985969014e-12
---
StyleLoss:updateOutput self.G 1: 636504.0625
StyleLoss:updateOutput self.G 2: 0.057596921920776
StyleLoss:updateGradInput self.gradInput 1: -9.0489457704734e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.446543996688e-05
dG 2: -3.1187608919014e-12
---
Iteration 163 / 2500
Content 1 loss: 458545.068359
Style 1 loss: 110468.948364
Style 2 loss: 85904109.375000
Style 3 loss: 110423742.187500
Style 4 loss: 6412526.367188
Style 5 loss: 239523.811340
Total loss: 203548915.757751
---
x1 value: -4.3201818466187
feval(x) grad value: 1.3249596244959e-17
---
StyleLoss:updateOutput self.G 1: 513921856
StyleLoss:updateOutput self.G 2: 1.4622769355774
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011821954976767
dG 2: -3.3637352885724e-12
---
StyleLoss:updateOutput self.G 1: 5090834432
StyleLoss:updateOutput self.G 2: 28.97020149231
StyleLoss:updateGradInput self.gradInput 1: -5.6711013662891e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9335018552956e-05
dG 1: -0.011837755329907
dG 2: -6.7364613887122e-11
---
StyleLoss:updateOutput self.G 1: 1685101440
StyleLoss:updateOutput self.G 2: 19.161703109741
StyleLoss:updateGradInput self.gradInput 1: -1.1115481868273e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3251813116949e-05
dG 1: -0.0031449429225177
dG 2: -3.5761917732691e-11
---
StyleLoss:updateOutput self.G 1: 91842704
StyleLoss:updateOutput self.G 2: 2.0850412845612
StyleLoss:updateGradInput self.gradInput 1: -2.0383135179713e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012144852371421
dG 1: -0.00016464272630401
dG 2: -3.737769642409e-12
---
StyleLoss:updateOutput self.G 1: 630588.1875
StyleLoss:updateOutput self.G 2: 0.057061590254307
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.446952541708e-05
dG 2: -3.1191297374805e-12
---
Iteration 164 / 2500
Content 1 loss: 458283.544922
Style 1 loss: 110723.098755
Style 2 loss: 85969107.421875
Style 3 loss: 110506722.656250
Style 4 loss: 6414298.095703
Style 5 loss: 239569.335938
Total loss: 203698704.153442
---
x1 value: -4.3164191246033
feval(x) grad value: -7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 513268576
StyleLoss:updateOutput self.G 2: 1.4604177474976
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011831033043563
dG 2: -3.3663180749877e-12
---
StyleLoss:updateOutput self.G 1: 5083188224
StyleLoss:updateOutput self.G 2: 28.926689147949
StyleLoss:updateGradInput self.gradInput 1: -5.6712083917887e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9361572160269e-05
dG 1: -0.01184306666255
dG 2: -6.7394839708967e-11
---
StyleLoss:updateOutput self.G 1: 1679523840
StyleLoss:updateOutput self.G 2: 19.098274230957
StyleLoss:updateGradInput self.gradInput 1: -1.111726533054e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3272935221903e-05
dG 1: -0.003146878676489
dG 2: -3.5783924434707e-11
---
StyleLoss:updateOutput self.G 1: 91472328
StyleLoss:updateOutput self.G 2: 2.076632976532
StyleLoss:updateGradInput self.gradInput 1: -2.0394328004159e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012149518443039
dG 1: -0.00016470687114634
dG 2: -3.739226376448e-12
---
StyleLoss:updateOutput self.G 1: 624758.25
StyleLoss:updateOutput self.G 2: 0.056534040719271
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4473559935577e-05
dG 2: -3.1194940294105e-12
---
Iteration 165 / 2500
Content 1 loss: 458026.318359
Style 1 loss: 110977.684021
Style 2 loss: 86033607.421875
Style 3 loss: 110588941.406250
Style 4 loss: 6416052.978516
Style 5 loss: 239614.196777
Total loss: 203847220.005798
---
x1 value: -4.3127036094666
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 512619904
StyleLoss:updateOutput self.G 2: 1.4585721492767
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011840043589473
dG 2: -3.3688819962852e-12
---
StyleLoss:updateOutput self.G 1: 5075601920
StyleLoss:updateOutput self.G 2: 28.883516311646
StyleLoss:updateGradInput self.gradInput 1: -5.6713163054667e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9383962100837e-05
dG 1: -0.011848335154355
dG 2: -6.7424822669526e-11
---
StyleLoss:updateOutput self.G 1: 1674000128
StyleLoss:updateOutput self.G 2: 19.035469055176
StyleLoss:updateGradInput self.gradInput 1: -1.1119029252882e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3291590777226e-05
dG 1: -0.0031487953383476
dG 2: -3.5805726439353e-11
---
StyleLoss:updateOutput self.G 1: 91105680
StyleLoss:updateOutput self.G 2: 2.0683097839355
StyleLoss:updateGradInput self.gradInput 1: -2.0405426681691e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012154666183051
dG 1: -0.00016477040480822
dG 2: -3.7406679316565e-12
---
StyleLoss:updateOutput self.G 1: 619031.25
StyleLoss:updateOutput self.G 2: 0.056015815585852
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4477510780562e-05
dG 2: -3.1198520329678e-12
---
Iteration 166 / 2500
Content 1 loss: 457773.291016
Style 1 loss: 111230.792999
Style 2 loss: 86097615.234375
Style 3 loss: 110670457.031250
Style 4 loss: 6417790.283203
Style 5 loss: 239658.233643
Total loss: 203994524.866486
---
x1 value: -4.3090353012085
feval(x) grad value: 8.8330647147598e-19
---
StyleLoss:updateOutput self.G 1: 511975424
StyleLoss:updateOutput self.G 2: 1.4567385911942
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011848998256028
dG 2: -3.3714298713905e-12
---
StyleLoss:updateOutput self.G 1: 5068075520
StyleLoss:updateOutput self.G 2: 28.840686798096
StyleLoss:updateGradInput self.gradInput 1: -5.6714219986986e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9411225114018e-05
dG 1: -0.011853563599288
dG 2: -6.745458358548e-11
---
StyleLoss:updateOutput self.G 1: 1668531584
StyleLoss:updateOutput self.G 2: 18.973279953003
StyleLoss:updateGradInput self.gradInput 1: -1.1120770970763e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3313433201984e-05
dG 1: -0.003150693140924
dG 2: -3.58272994605e-11
---
StyleLoss:updateOutput self.G 1: 90742752
StyleLoss:updateOutput self.G 2: 2.0600697994232
StyleLoss:updateGradInput self.gradInput 1: -2.0416427659598e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012158782192273
dG 1: -0.00016483322542626
dG 2: -3.7420951753964e-12
---
StyleLoss:updateOutput self.G 1: 613388.3125
StyleLoss:updateOutput self.G 2: 0.055505186319351
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4481407055864e-05
dG 2: -3.1202046155143e-12
---
Iteration 167 / 2500
Content 1 loss: 457524.365234
Style 1 loss: 111482.952118
Style 2 loss: 86161142.578125
Style 3 loss: 110751210.937500
Style 4 loss: 6419511.474609
Style 5 loss: 239701.606750
Total loss: 204140573.914337
---
x1 value: -4.3054161071777
feval(x) grad value: -2.6499192076328e-18
---
StyleLoss:updateOutput self.G 1: 511335296
StyleLoss:updateOutput self.G 2: 1.4549171924591
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011857890058309
dG 2: -3.3739599655802e-12
---
StyleLoss:updateOutput self.G 1: 5060604416
StyleLoss:updateOutput self.G 2: 28.798173904419
StyleLoss:updateGradInput self.gradInput 1: -5.6715281360198e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9438386263791e-05
dG 1: -0.011858753859997
dG 2: -6.7484122456829e-11
---
StyleLoss:updateOutput self.G 1: 1663116160
StyleLoss:updateOutput self.G 2: 18.911697387695
StyleLoss:updateGradInput self.gradInput 1: -1.1122488707827e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3331543060485e-05
dG 1: -0.0031525725498796
dG 2: -3.5848667784277e-11
---
StyleLoss:updateOutput self.G 1: 90383240
StyleLoss:updateOutput self.G 2: 2.0519082546234
StyleLoss:updateGradInput self.gradInput 1: -2.0427330937878e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012162585335318
dG 1: -0.00016489553672727
dG 2: -3.7435076739867e-12
---
StyleLoss:updateOutput self.G 1: 607834
StyleLoss:updateOutput self.G 2: 0.055002588778734
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4485241485527e-05
dG 2: -3.1205515602095e-12
---
Iteration 168 / 2500
Content 1 loss: 457278.955078
Style 1 loss: 111733.795166
Style 2 loss: 86224201.171875
Style 3 loss: 110831285.156250
Style 4 loss: 6421217.285156
Style 5 loss: 239744.293213
Total loss: 204285460.656738
---
x1 value: -4.3018403053284
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 510700032
StyleLoss:updateOutput self.G 2: 1.4531096220016
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.001186671666801
dG 2: -3.3764714114926e-12
---
StyleLoss:updateOutput self.G 1: 5053193728
StyleLoss:updateOutput self.G 2: 28.756000518799
StyleLoss:updateGradInput self.gradInput 1: -5.6716320528949e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9463850296452e-05
dG 1: -0.011863901279867
dG 2: -6.7513418466891e-11
---
StyleLoss:updateOutput self.G 1: 1657754112
StyleLoss:updateOutput self.G 2: 18.850727081299
StyleLoss:updateGradInput self.gradInput 1: -1.1124182464073e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3350795244332e-05
dG 1: -0.0031544335652143
dG 2: -3.5869834880131e-11
---
StyleLoss:updateOutput self.G 1: 90027176
StyleLoss:updateOutput self.G 2: 2.0438244342804
StyleLoss:updateGradInput self.gradInput 1: -2.0438161385528e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012166011583759
dG 1: -0.00016495717864018
dG 2: -3.7449088968744e-12
---
StyleLoss:updateOutput self.G 1: 602376
StyleLoss:updateOutput self.G 2: 0.054508712142706
StyleLoss:updateGradInput self.gradInput 1: -9.0489493231871e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4489010431571e-05
dG 2: -3.1208930838938e-12
---
Iteration 169 / 2500
Content 1 loss: 457037.207031
Style 1 loss: 111983.390808
Style 2 loss: 86286773.437500
Style 3 loss: 110910632.812500
Style 4 loss: 6422905.517578
Style 5 loss: 239786.224365
Total loss: 204429118.589783
---
x1 value: -4.2983107566833
feval(x) grad value: -1.5016210015092e-17
---
StyleLoss:updateOutput self.G 1: 510068672
StyleLoss:updateOutput self.G 2: 1.4513130187988
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011875489726663
dG 2: -3.3789672448936e-12
---
StyleLoss:updateOutput self.G 1: 5045839360
StyleLoss:updateOutput self.G 2: 28.7141456604
StyleLoss:updateGradInput self.gradInput 1: -5.6717368579484e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9486051062122e-05
dG 1: -0.011869010515511
dG 2: -6.7542485493455e-11
---
StyleLoss:updateOutput self.G 1: 1652444800
StyleLoss:updateOutput self.G 2: 18.790351867676
StyleLoss:updateGradInput self.gradInput 1: -1.1125855792216e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3369028794114e-05
dG 1: -0.0031562759540975
dG 2: -3.5890790339721e-11
---
StyleLoss:updateOutput self.G 1: 89674680
StyleLoss:updateOutput self.G 2: 2.0358219146729
StyleLoss:updateGradInput self.gradInput 1: -2.0448881699053e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012170901754871
dG 1: -0.00016501823847648
dG 2: -3.7462949409317e-12
---
StyleLoss:updateOutput self.G 1: 596996
StyleLoss:updateOutput self.G 2: 0.054021861404181
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4492717531975e-05
dG 2: -3.1212287528865e-12
---
Iteration 170 / 2500
Content 1 loss: 456799.707031
Style 1 loss: 112231.052399
Style 2 loss: 86348876.953125
Style 3 loss: 110989289.062500
Style 4 loss: 6424577.636719
Style 5 loss: 239827.537537
Total loss: 204571601.949310
---
x1 value: -4.2948303222656
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 509441312
StyleLoss:updateOutput self.G 2: 1.4495279788971
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0011884204577655
dG 2: -3.3814476826238e-12
---
StyleLoss:updateOutput self.G 1: 5038540288
StyleLoss:updateOutput self.G 2: 28.672609329224
StyleLoss:updateGradInput self.gradInput 1: -5.6718389984667e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9512504625018e-05
dG 1: -0.01187408156693
dG 2: -6.7571337414307e-11
---
StyleLoss:updateOutput self.G 1: 1647184896
StyleLoss:updateOutput self.G 2: 18.730543136597
StyleLoss:updateGradInput self.gradInput 1: -1.1127506915898e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3389619754162e-05
dG 1: -0.0031581004150212
dG 2: -3.5911537632494e-11
---
StyleLoss:updateOutput self.G 1: 89325520
StyleLoss:updateOutput self.G 2: 2.0278949737549
StyleLoss:updateGradInput self.gradInput 1: -2.0459527405592e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012175276788184
dG 1: -0.00016507870168425
dG 2: -3.7476679745629e-12
---
StyleLoss:updateOutput self.G 1: 591705.75
StyleLoss:updateOutput self.G 2: 0.053543146699667
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4496377338655e-05
dG 2: -3.1215594345491e-12
---
Iteration 171 / 2500
Content 1 loss: 456565.087891
Style 1 loss: 112478.153229
Style 2 loss: 86410511.718750
Style 3 loss: 111067253.906250
Style 4 loss: 6426235.839844
Style 5 loss: 239868.141174
Total loss: 204712912.847137
---
x1 value: -4.2913889884949
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 508819200
StyleLoss:updateOutput self.G 2: 1.4477578401566
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.00118928484153
dG 2: -3.3839064363106e-12
---
StyleLoss:updateOutput self.G 1: 5031294976
StyleLoss:updateOutput self.G 2: 28.631383895874
StyleLoss:updateGradInput self.gradInput 1: -5.6719420271634e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9535838621086e-05
dG 1: -0.0118791135028
dG 2: -6.7599974229449e-11
---
StyleLoss:updateOutput self.G 1: 1641975296
StyleLoss:updateOutput self.G 2: 18.67130279541
StyleLoss:updateGradInput self.gradInput 1: -1.1129137611476e-08
StyleLoss:updateGradInput self.gradInput 2: -6.340865365928e-05
dG 1: -0.0031599088106304
dG 2: -3.5932094105684e-11
---
StyleLoss:updateOutput self.G 1: 88979560
StyleLoss:updateOutput self.G 2: 2.0200414657593
StyleLoss:updateGradInput self.gradInput 1: -2.0470068307077e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012179426994408
dG 1: -0.00016513864102308
dG 2: -3.7490279977681e-12
---
StyleLoss:updateOutput self.G 1: 586492.75
StyleLoss:updateOutput self.G 2: 0.053071439266205
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4499978937674e-05
dG 2: -3.1218846952008e-12
---
Iteration 172 / 2500
Content 1 loss: 456334.863281
Style 1 loss: 112722.473145
Style 2 loss: 86471718.750000
Style 3 loss: 111144585.937500
Style 4 loss: 6427879.394531
Style 5 loss: 239908.172607
Total loss: 204853149.591064
---
x1 value: -4.2879967689514
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 508200320
StyleLoss:updateOutput self.G 2: 1.4459971189499
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011901445686817
dG 2: -3.3863532637735e-12
---
StyleLoss:updateOutput self.G 1: 5024105472
StyleLoss:updateOutput self.G 2: 28.590467453003
StyleLoss:updateGradInput self.gradInput 1: -5.6720454999493e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9560731491074e-05
dG 1: -0.011884109117091
dG 2: -6.7628395938879e-11
---
StyleLoss:updateOutput self.G 1: 1636816512
StyleLoss:updateOutput self.G 2: 18.612644195557
StyleLoss:updateGradInput self.gradInput 1: -1.113074876713e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3428684370592e-05
dG 1: -0.0031616992782801
dG 2: -3.5952449350951e-11
---
StyleLoss:updateOutput self.G 1: 88636824
StyleLoss:updateOutput self.G 2: 2.0122604370117
StyleLoss:updateGradInput self.gradInput 1: -2.0480534601575e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001218415927724
dG 1: -0.00016519798373338
dG 2: -3.7503767452707e-12
---
StyleLoss:updateOutput self.G 1: 581352.375
StyleLoss:updateOutput self.G 2: 0.052606262266636
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4503518691054e-05
dG 2: -3.1222060527247e-12
---
Iteration 173 / 2500
Content 1 loss: 456107.275391
Style 1 loss: 112967.067719
Style 2 loss: 86532474.609375
Style 3 loss: 111221203.125000
Style 4 loss: 6429506.835938
Style 5 loss: 239947.586060
Total loss: 204992206.499481
---
x1 value: -4.2846474647522
feval(x) grad value: -9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 507586144
StyleLoss:updateOutput self.G 2: 1.4442496299744
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011909977765754
dG 2: -3.3887805755972e-12
---
StyleLoss:updateOutput self.G 1: 5016970752
StyleLoss:updateOutput self.G 2: 28.549865722656
StyleLoss:updateGradInput self.gradInput 1: -5.6721463081999e-09
StyleLoss:updateGradInput self.gradInput 2: -2.958508048323e-05
dG 1: -0.01188906468451
dG 2: -6.7656595603705e-11
---
StyleLoss:updateOutput self.G 1: 1631706240
StyleLoss:updateOutput self.G 2: 18.554533004761
StyleLoss:updateGradInput self.gradInput 1: -1.1132336830144e-08
StyleLoss:updateGradInput self.gradInput 2: -6.344671419356e-05
dG 1: -0.0031634727492929
dG 2: -3.597262071553e-11
---
StyleLoss:updateOutput self.G 1: 88297312
StyleLoss:updateOutput self.G 2: 2.0045528411865
StyleLoss:updateGradInput self.gradInput 1: -2.049091207823e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012188233085908
dG 1: -0.00016525680257473
dG 2: -3.7517107476237e-12
---
StyleLoss:updateOutput self.G 1: 576294.3125
StyleLoss:updateOutput self.G 2: 0.052148580551147
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4507011150708e-05
dG 2: -3.1225215555569e-12
---
Iteration 174 / 2500
Content 1 loss: 455883.203125
Style 1 loss: 113209.110260
Style 2 loss: 86592767.578125
Style 3 loss: 111297187.500000
Style 4 loss: 6431121.093750
Style 5 loss: 239986.404419
Total loss: 205130154.889679
---
x1 value: -4.2813405990601
feval(x) grad value: 1.5016210015092e-17
---
StyleLoss:updateOutput self.G 1: 506975744
StyleLoss:updateOutput self.G 2: 1.4425128698349
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011918458621949
dG 2: -3.3911935759523e-12
---
StyleLoss:updateOutput self.G 1: 5009891840
StyleLoss:updateOutput self.G 2: 28.509586334229
StyleLoss:updateGradInput self.gradInput 1: -5.6722466723613e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9610124329338e-05
dG 1: -0.011893982067704
dG 2: -6.7684580162819e-11
---
StyleLoss:updateOutput self.G 1: 1626646656
StyleLoss:updateOutput self.G 2: 18.496997833252
StyleLoss:updateGradInput self.gradInput 1: -1.1133910682304e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3464969571214e-05
dG 1: -0.003165228292346
dG 2: -3.5992583913291e-11
---
StyleLoss:updateOutput self.G 1: 87961328
StyleLoss:updateOutput self.G 2: 1.9969252347946
StyleLoss:updateGradInput self.gradInput 1: -2.0501181197119e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012192689609947
dG 1: -0.00016531499568373
dG 2: -3.7530317395507e-12
---
StyleLoss:updateOutput self.G 1: 571308.875
StyleLoss:updateOutput self.G 2: 0.051697455346584
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4510459954618e-05
dG 2: -3.1228331552613e-12
---
Iteration 175 / 2500
Content 1 loss: 455663.720703
Style 1 loss: 113450.008392
Style 2 loss: 86652603.515625
Style 3 loss: 111372480.468750
Style 4 loss: 6432718.505859
Style 5 loss: 240024.581909
Total loss: 205266940.801239
---
x1 value: -4.2780780792236
feval(x) grad value: -1.5899516486568e-17
---
StyleLoss:updateOutput self.G 1: 506370240
StyleLoss:updateOutput self.G 2: 1.440789937973
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011926871957257
dG 2: -3.3935872775087e-12
---
StyleLoss:updateOutput self.G 1: 5002863616
StyleLoss:updateOutput self.G 2: 28.46958732605
StyleLoss:updateGradInput self.gradInput 1: -5.6723483687904e-09
StyleLoss:updateGradInput self.gradInput 2: -2.963256338262e-05
dG 1: -0.01189886406064
dG 2: -6.7712384310692e-11
---
StyleLoss:updateOutput self.G 1: 1621631488
StyleLoss:updateOutput self.G 2: 18.439970016479
StyleLoss:updateGradInput self.gradInput 1: -1.1135461441825e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3482271798421e-05
dG 1: -0.0031669684685767
dG 2: -3.6012366699811e-11
---
StyleLoss:updateOutput self.G 1: 87628400
StyleLoss:updateOutput self.G 2: 1.9893667697906
StyleLoss:updateGradInput self.gradInput 1: -2.0511361498166e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012196660827613
dG 1: -0.00016537267947569
dG 2: -3.754341455775e-12
---
StyleLoss:updateOutput self.G 1: 566387.6875
StyleLoss:updateOutput self.G 2: 0.051252122968435
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4513850550866e-05
dG 2: -3.1231410686783e-12
---
Iteration 176 / 2500
Content 1 loss: 455445.996094
Style 1 loss: 113688.571930
Style 2 loss: 86712023.437500
Style 3 loss: 111447164.062500
Style 4 loss: 6434302.734375
Style 5 loss: 240062.324524
Total loss: 205402687.126923
---
x1 value: -4.2748575210571
feval(x) grad value: 0
---
StyleLoss:updateOutput self.G 1: 505768128
StyleLoss:updateOutput self.G 2: 1.4390766620636
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011935236398131
dG 2: -3.3959677517986e-12
---
StyleLoss:updateOutput self.G 1: 4995887104
StyleLoss:updateOutput self.G 2: 28.429883956909
StyleLoss:updateGradInput self.gradInput 1: -5.672449177041e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9655715479748e-05
dG 1: -0.011903711594641
dG 2: -6.7739952536172e-11
---
StyleLoss:updateOutput self.G 1: 1616666368
StyleLoss:updateOutput self.G 2: 18.383502960205
StyleLoss:updateGradInput self.gradInput 1: -1.113699266142e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3500636315439e-05
dG 1: -0.0031686916481704
dG 2: -3.603196907509e-11
---
StyleLoss:updateOutput self.G 1: 87298344
StyleLoss:updateOutput self.G 2: 1.9818737506866
StyleLoss:updateGradInput self.gradInput 1: -2.0521483179436e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012201464414829
dG 1: -0.00016542983939871
dG 2: -3.7556385952542e-12
---
StyleLoss:updateOutput self.G 1: 561549.375
StyleLoss:updateOutput self.G 2: 0.05081432685256
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4517190215411e-05
dG 2: -3.1234426937227e-12
---
Iteration 177 / 2500
Content 1 loss: 455232.470703
Style 1 loss: 113925.888062
Style 2 loss: 86771003.906250
Style 3 loss: 111521203.125000
Style 4 loss: 6435873.046875
Style 5 loss: 240099.380493
Total loss: 205537337.817383
---
x1 value: -4.2716794013977
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 505170624
StyleLoss:updateOutput self.G 2: 1.4373768568039
StyleLoss:updateGradInput self.gradInput 1: -2.8453295275455e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071977708838e-05
dG 1: -0.0011943536810577
dG 2: -3.3983293609707e-12
---
StyleLoss:updateOutput self.G 1: 4988962816
StyleLoss:updateOutput self.G 2: 28.390476226807
StyleLoss:updateGradInput self.gradInput 1: -5.672548653024e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9678951250389e-05
dG 1: -0.011908520944417
dG 2: -6.7767333411517e-11
---
StyleLoss:updateOutput self.G 1: 1611746688
StyleLoss:updateOutput self.G 2: 18.327564239502
StyleLoss:updateGradInput self.gradInput 1: -1.1138507005626e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3519197283313e-05
dG 1: -0.0031703992281109
dG 2: -3.6051380630786e-11
---
StyleLoss:updateOutput self.G 1: 86971744
StyleLoss:updateOutput self.G 2: 1.974459528923
StyleLoss:updateGradInput self.gradInput 1: -2.0531492950226e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012206179962959
dG 1: -0.00016548641724512
dG 2: -3.7569231579881e-12
---
StyleLoss:updateOutput self.G 1: 556775.1875
StyleLoss:updateOutput self.G 2: 0.050382290035486
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4520489862189e-05
dG 2: -3.1237417166818e-12
---
Iteration 178 / 2500
Content 1 loss: 455021.484375
Style 1 loss: 114161.510468
Style 2 loss: 86829568.359375
Style 3 loss: 111594597.656250
Style 4 loss: 6437427.978516
Style 5 loss: 240135.910034
Total loss: 205670912.899017
---
x1 value: -4.268542766571
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 504576128
StyleLoss:updateOutput self.G 2: 1.4356851577759
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011951796477661
dG 2: -3.4006794775998e-12
---
StyleLoss:updateOutput self.G 1: 4982087680
StyleLoss:updateOutput self.G 2: 28.351360321045
StyleLoss:updateGradInput self.gradInput 1: -5.6726454644718e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9702525353059e-05
dG 1: -0.011913298629224
dG 2: -6.7794506120045e-11
---
StyleLoss:updateOutput self.G 1: 1606872704
StyleLoss:updateOutput self.G 2: 18.272136688232
StyleLoss:updateGradInput self.gradInput 1: -1.1140002698085e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3536594097968e-05
dG 1: -0.0031720898114145
dG 2: -3.6070615244688e-11
---
StyleLoss:updateOutput self.G 1: 86647816
StyleLoss:updateOutput self.G 2: 1.9671051502228
StyleLoss:updateGradInput self.gradInput 1: -2.0541428114029e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012210293789394
dG 1: -0.00016554252943024
dG 2: -3.7581968787004e-12
---
StyleLoss:updateOutput self.G 1: 552070.6875
StyleLoss:updateOutput self.G 2: 0.0499565936625
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4523734939285e-05
dG 2: -3.1240353186301e-12
---
Iteration 179 / 2500
Content 1 loss: 454813.330078
Style 1 loss: 114397.247314
Style 2 loss: 86887722.656250
Style 3 loss: 111667382.812500
Style 4 loss: 6438971.191406
Style 5 loss: 240171.913147
Total loss: 205803459.150696
---
x1 value: -4.2654461860657
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 503986048
StyleLoss:updateOutput self.G 2: 1.4340063333511
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0011959994444624
dG 2: -3.4030122469941e-12
---
StyleLoss:updateOutput self.G 1: 4975262720
StyleLoss:updateOutput self.G 2: 28.312520980835
StyleLoss:updateGradInput self.gradInput 1: -5.6727444963656e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9727270884905e-05
dG 1: -0.011918038129807
dG 2: -6.7821477600649e-11
---
StyleLoss:updateOutput self.G 1: 1602043776
StyleLoss:updateOutput self.G 2: 18.217231750488
StyleLoss:updateGradInput self.gradInput 1: -1.1141478850618e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3553401560057e-05
dG 1: -0.0031737657263875
dG 2: -3.6089665977901e-11
---
StyleLoss:updateOutput self.G 1: 86326960
StyleLoss:updateOutput self.G 2: 1.9598207473755
StyleLoss:updateGradInput self.gradInput 1: -2.0551278012704e-08
StyleLoss:updateGradInput self.gradInput 2: -0.000122146186186
dG 1: -0.00016559805953875
dG 2: -3.7594584563483e-12
---
StyleLoss:updateOutput self.G 1: 547434.4375
StyleLoss:updateOutput self.G 2: 0.049537055194378
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4526936360635e-05
dG 2: -3.1243250174506e-12
---
Iteration 180 / 2500
Content 1 loss: 454608.349609
Style 1 loss: 114631.954193
Style 2 loss: 86945466.796875
Style 3 loss: 111739570.312500
Style 4 loss: 6440499.023438
Style 5 loss: 240207.366943
Total loss: 205934983.803558
---
x1 value: -4.2623929977417
feval(x) grad value: 1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 503399712
StyleLoss:updateOutput self.G 2: 1.4323379993439
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011968140024692
dG 2: -3.405329837558e-12
---
StyleLoss:updateOutput self.G 1: 4968488448
StyleLoss:updateOutput self.G 2: 28.273963928223
StyleLoss:updateGradInput self.gradInput 1: -5.6728435282594e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9750161047559e-05
dG 1: -0.011922744102776
dG 2: -6.7848268670012e-11
---
StyleLoss:updateOutput self.G 1: 1597260288
StyleLoss:updateOutput self.G 2: 18.16283416748
StyleLoss:updateGradInput self.gradInput 1: -1.114293901594e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3569903431926e-05
dG 1: -0.0031754253432155
dG 2: -3.6108539769319e-11
---
StyleLoss:updateOutput self.G 1: 86009032
StyleLoss:updateOutput self.G 2: 1.9526036977768
StyleLoss:updateGradInput self.gradInput 1: -2.0561035540823e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012218554911669
dG 1: -0.00016565316764172
dG 2: -3.7607083246127e-12
---
StyleLoss:updateOutput self.G 1: 542861.375
StyleLoss:updateOutput self.G 2: 0.049123246222734
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4530090488261e-05
dG 2: -3.1246105963029e-12
---
Iteration 181 / 2500
Content 1 loss: 454406.152344
Style 1 loss: 114864.292145
Style 2 loss: 87002794.921875
Style 3 loss: 111811125.000000
Style 4 loss: 6442016.601562
Style 5 loss: 240242.362976
Total loss: 206065449.330902
---
x1 value: -4.2593784332275
feval(x) grad value: 1.943274071811e-17
---
StyleLoss:updateOutput self.G 1: 502817280
StyleLoss:updateOutput self.G 2: 1.430680513382
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011976233217865
dG 2: -3.4076328998128e-12
---
StyleLoss:updateOutput self.G 1: 4961761792
StyleLoss:updateOutput self.G 2: 28.235689163208
StyleLoss:updateGradInput self.gradInput 1: -5.6729385633503e-09
StyleLoss:updateGradInput self.gradInput 2: -2.977623444167e-05
dG 1: -0.011927418410778
dG 2: -6.7874851572558e-11
---
StyleLoss:updateOutput self.G 1: 1592520320
StyleLoss:updateOutput self.G 2: 18.108938217163
StyleLoss:updateGradInput self.gradInput 1: -1.1144376976802e-08
StyleLoss:updateGradInput self.gradInput 2: -6.35880351183e-05
dG 1: -0.0031770707573742
dG 2: -3.6127247027284e-11
---
StyleLoss:updateOutput self.G 1: 85693736
StyleLoss:updateOutput self.G 2: 1.9454456567764
StyleLoss:updateGradInput self.gradInput 1: -2.0570704251099e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012222537770867
dG 1: -0.00016570776642766
dG 2: -3.7619486518981e-12
---
StyleLoss:updateOutput self.G 1: 538348.6875
StyleLoss:updateOutput self.G 2: 0.048714887350798
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4533211874077e-05
dG 2: -3.1248927057081e-12
---
Iteration 182 / 2500
Content 1 loss: 454206.152344
Style 1 loss: 115096.183777
Style 2 loss: 87059718.750000
Style 3 loss: 111882082.031250
Style 4 loss: 6443520.996094
Style 5 loss: 240276.855469
Total loss: 206194900.968933
---
x1 value: -4.2564034461975
feval(x) grad value: -1.8549435900995e-17
---
StyleLoss:updateOutput self.G 1: 502237504
StyleLoss:updateOutput self.G 2: 1.4290311336517
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0011984286829829
dG 2: -3.4099242526842e-12
---
StyleLoss:updateOutput self.G 1: 4955086336
StyleLoss:updateOutput self.G 2: 28.197702407837
StyleLoss:updateGradInput self.gradInput 1: -5.6730358188872e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9799914045725e-05
dG 1: -0.011932054534554
dG 2: -6.7901226308287e-11
---
StyleLoss:updateOutput self.G 1: 1587824768
StyleLoss:updateOutput self.G 2: 18.055547714233
StyleLoss:updateGradInput self.gradInput 1: -1.1145801614987e-08
StyleLoss:updateGradInput self.gradInput 2: -6.360508268699e-05
dG 1: -0.0031787003390491
dG 2: -3.6145773874008e-11
---
StyleLoss:updateOutput self.G 1: 85381696
StyleLoss:updateOutput self.G 2: 1.9383614063263
StyleLoss:updateGradInput self.gradInput 1: -2.0580289472605e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012226599210408
dG 1: -0.00016576181224082
dG 2: -3.7631755350764e-12
---
StyleLoss:updateOutput self.G 1: 533906.875
StyleLoss:updateOutput self.G 2: 0.048312962055206
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4536271414254e-05
dG 2: -3.1251702614643e-12
---
Iteration 183 / 2500
Content 1 loss: 454010.302734
Style 1 loss: 115327.400208
Style 2 loss: 87116226.562500
Style 3 loss: 111952441.406250
Style 4 loss: 6445009.277344
Style 5 loss: 240310.798645
Total loss: 206323325.747681
---
x1 value: -4.2534699440002
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 501662016
StyleLoss:updateOutput self.G 2: 1.4273936748505
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0011992284562439
dG 2: -3.4121995593633e-12
---
StyleLoss:updateOutput self.G 1: 4948458496
StyleLoss:updateOutput self.G 2: 28.159984588623
StyleLoss:updateGradInput self.gradInput 1: -5.6731317421566e-09
StyleLoss:updateGradInput self.gradInput 2: -2.982243495353e-05
dG 1: -0.011936658062041
dG 2: -6.7927441449456e-11
---
StyleLoss:updateOutput self.G 1: 1583171456
StyleLoss:updateOutput self.G 2: 18.002624511719
StyleLoss:updateGradInput self.gradInput 1: -1.1147205825068e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3622952438891e-05
dG 1: -0.0031803150195628
dG 2: -3.6164137656725e-11
---
StyleLoss:updateOutput self.G 1: 85072248
StyleLoss:updateOutput self.G 2: 1.9313362836838
StyleLoss:updateGradInput self.gradInput 1: -2.0589787652625e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001223087310791
dG 1: -0.00016581537784077
dG 2: -3.7643924435948e-12
---
StyleLoss:updateOutput self.G 1: 529518.125
StyleLoss:updateOutput self.G 2: 0.047915823757648
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4539312764537e-05
dG 2: -3.1254443477735e-12
---
Iteration 184 / 2500
Content 1 loss: 453816.015625
Style 1 loss: 115557.586670
Style 2 loss: 87172335.937500
Style 3 loss: 112022226.562500
Style 4 loss: 6446488.037109
Style 5 loss: 240344.329834
Total loss: 206450768.469238
---
x1 value: -4.2505741119385
feval(x) grad value: -8.8330647147598e-19
---
StyleLoss:updateOutput self.G 1: 501089088
StyleLoss:updateOutput self.G 2: 1.4257633686066
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.0012000242713839
dG 2: -3.4144644577017e-12
---
StyleLoss:updateOutput self.G 1: 4941876736
StyleLoss:updateOutput self.G 2: 28.122535705566
StyleLoss:updateGradInput self.gradInput 1: -5.6732272213367e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9846927645849e-05
dG 1: -0.01194122992456
dG 2: -6.7953455362701e-11
---
StyleLoss:updateOutput self.G 1: 1578559872
StyleLoss:updateOutput self.G 2: 17.950187683105
StyleLoss:updateGradInput self.gradInput 1: -1.1148597600652e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3640865846537e-05
dG 1: -0.0031819152645767
dG 2: -3.6182338375434e-11
---
StyleLoss:updateOutput self.G 1: 84765584
StyleLoss:updateOutput self.G 2: 1.9243742227554
StyleLoss:updateGradInput self.gradInput 1: -2.0599221883799e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012234185123816
dG 1: -0.00016586852143519
dG 2: -3.7655980764106e-12
---
StyleLoss:updateOutput self.G 1: 525195.875
StyleLoss:updateOutput self.G 2: 0.047524701803923
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.454229226918e-05
dG 2: -3.1257145309549e-12
---
Iteration 185 / 2500
Content 1 loss: 453624.804688
Style 1 loss: 115787.590027
Style 2 loss: 87228058.593750
Style 3 loss: 112091425.781250
Style 4 loss: 6447951.416016
Style 5 loss: 240377.334595
Total loss: 206577225.520325
---
x1 value: -4.2477178573608
feval(x) grad value: 7.0664517718078e-18
---
StyleLoss:updateOutput self.G 1: 500520960
StyleLoss:updateOutput self.G 2: 1.4241468906403
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0012008138000965
dG 2: -3.4167100572413e-12
---
StyleLoss:updateOutput self.G 1: 4935345152
StyleLoss:updateOutput self.G 2: 28.085359573364
StyleLoss:updateGradInput self.gradInput 1: -5.6733222564276e-09
StyleLoss:updateGradInput self.gradInput 2: -2.98709855997e-05
dG 1: -0.011945768259466
dG 2: -6.7979288864706e-11
---
StyleLoss:updateOutput self.G 1: 1573989504
StyleLoss:updateOutput self.G 2: 17.898218154907
StyleLoss:updateGradInput self.gradInput 1: -1.1149968059954e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3657498685643e-05
dG 1: -0.0031835017725825
dG 2: -3.6200379499585e-11
---
StyleLoss:updateOutput self.G 1: 84461928
StyleLoss:updateOutput self.G 2: 1.9174807071686
StyleLoss:updateGradInput self.gradInput 1: -2.0608569073488e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012238022463862
dG 1: -0.00016592112660874
dG 2: -3.766791999843e-12
---
StyleLoss:updateOutput self.G 1: 520935.21875
StyleLoss:updateOutput self.G 2: 0.047139160335064
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4545231756056e-05
dG 2: -3.1259803773276e-12
---
Iteration 186 / 2500
Content 1 loss: 453436.279297
Style 1 loss: 116014.755249
Style 2 loss: 87283400.390625
Style 3 loss: 112160074.218750
Style 4 loss: 6449402.343750
Style 5 loss: 240409.881592
Total loss: 206702737.869263
---
x1 value: -4.2448983192444
feval(x) grad value: -1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 499955552
StyleLoss:updateOutput self.G 2: 1.4225380420685
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0012015992542729
dG 2: -3.4189450315997e-12
---
StyleLoss:updateOutput self.G 1: 4928856064
StyleLoss:updateOutput self.G 2: 28.04843711853
StyleLoss:updateGradInput self.gradInput 1: -5.6734159592509e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9895420084358e-05
dG 1: -0.011950274929404
dG 2: -6.8004921138787e-11
---
StyleLoss:updateOutput self.G 1: 1569461248
StyleLoss:updateOutput self.G 2: 17.846723556519
StyleLoss:updateGradInput self.gradInput 1: -1.1151321643865e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3674087869003e-05
dG 1: -0.0031850731465966
dG 2: -3.621824368194e-11
---
StyleLoss:updateOutput self.G 1: 84160968
StyleLoss:updateOutput self.G 2: 1.9106481075287
StyleLoss:updateGradInput self.gradInput 1: -2.0617818563551e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012242527736817
dG 1: -0.00016597323701717
dG 2: -3.7679755149345e-12
---
StyleLoss:updateOutput self.G 1: 516726.625
StyleLoss:updateOutput self.G 2: 0.046758327633142
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4548138501123e-05
dG 2: -3.1262438384555e-12
---
Iteration 187 / 2500
Content 1 loss: 453250.048828
Style 1 loss: 116241.794586
Style 2 loss: 87338343.750000
Style 3 loss: 112228125.000000
Style 4 loss: 6450840.087891
Style 5 loss: 240442.016602
Total loss: 206827242.697906
---
x1 value: -4.2421159744263
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 499393472
StyleLoss:updateOutput self.G 2: 1.4209386110306
StyleLoss:updateGradInput self.gradInput 1: -2.8453290834562e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0012023800518364
dG 2: -3.4211674292128e-12
---
StyleLoss:updateOutput self.G 1: 4922414592
StyleLoss:updateOutput self.G 2: 28.011783599854
StyleLoss:updateGradInput self.gradInput 1: -5.6735109943418e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9921973691671e-05
dG 1: -0.011954749003053
dG 2: -6.8030386879414e-11
---
StyleLoss:updateOutput self.G 1: 1564972160
StyleLoss:updateOutput self.G 2: 17.795680999756
StyleLoss:updateGradInput self.gradInput 1: -1.1152661016922e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3691521063447e-05
dG 1: -0.003186630550772
dG 2: -3.6235951739183e-11
---
StyleLoss:updateOutput self.G 1: 83862504
StyleLoss:updateOutput self.G 2: 1.9038723707199
StyleLoss:updateGradInput self.gradInput 1: -2.0627007657481e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012246383994352
dG 1: -0.00016602493997198
dG 2: -3.769149055366e-12
---
StyleLoss:updateOutput self.G 1: 512592.09375
StyleLoss:updateOutput self.G 2: 0.046384204179049
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4550990676507e-05
dG 2: -3.1265014448917e-12
---
Iteration 188 / 2500
Content 1 loss: 453066.406250
Style 1 loss: 116467.712402
Style 2 loss: 87392923.828125
Style 3 loss: 112295660.156250
Style 4 loss: 6452266.113281
Style 5 loss: 240473.602295
Total loss: 206950857.818604
---
x1 value: -4.2393741607666
feval(x) grad value: 7.9497582432838e-18
---
StyleLoss:updateOutput self.G 1: 498835168
StyleLoss:updateOutput self.G 2: 1.4193501472473
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.001203155843541
dG 2: -3.4233744311551e-12
---
StyleLoss:updateOutput self.G 1: 4916018688
StyleLoss:updateOutput self.G 2: 27.975381851196
StyleLoss:updateGradInput self.gradInput 1: -5.6736033648974e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9945167625556e-05
dG 1: -0.011959192343056
dG 2: -6.8055679147694e-11
---
StyleLoss:updateOutput self.G 1: 1560524032
StyleLoss:updateOutput self.G 2: 17.745101928711
StyleLoss:updateGradInput self.gradInput 1: -1.1153987067303e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3708386733197e-05
dG 1: -0.00318817445077
dG 2: -3.625350714076e-11
---
StyleLoss:updateOutput self.G 1: 83566976
StyleLoss:updateOutput self.G 2: 1.8971627950668
StyleLoss:updateGradInput self.gradInput 1: -2.0636106157212e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012250227155164
dG 1: -0.00016607614816166
dG 2: -3.7703117537757e-12
---
StyleLoss:updateOutput self.G 1: 508505.75
StyleLoss:updateOutput self.G 2: 0.046014428138733
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4553813748062e-05
dG 2: -3.1267573166044e-12
---
Iteration 189 / 2500
Content 1 loss: 452885.253906
Style 1 loss: 116692.417145
Style 2 loss: 87447140.625000
Style 3 loss: 112362597.656250
Style 4 loss: 6453677.490234
Style 5 loss: 240504.776001
Total loss: 207073498.218536
---
x1 value: -4.236665725708
feval(x) grad value: -9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 498280288
StyleLoss:updateOutput self.G 2: 1.4177714586258
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071974070859e-05
dG 1: -0.0012039266293868
dG 2: -3.4255675553096e-12
---
StyleLoss:updateOutput self.G 1: 4909667840
StyleLoss:updateOutput self.G 2: 27.93924331665
StyleLoss:updateGradInput self.gradInput 1: -5.6736970677207e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9966859074193e-05
dG 1: -0.01196360308677
dG 2: -6.8080784065838e-11
---
StyleLoss:updateOutput self.G 1: 1556115712
StyleLoss:updateOutput self.G 2: 17.694972991943
StyleLoss:updateGradInput self.gradInput 1: -1.1155293577758e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3723819039296e-05
dG 1: -0.0031897039152682
dG 2: -3.6270906417224e-11
---
StyleLoss:updateOutput self.G 1: 83273688
StyleLoss:updateOutput self.G 2: 1.8905049562454
StyleLoss:updateGradInput self.gradInput 1: -2.06451282736e-08
StyleLoss:updateGradInput self.gradInput 2: -0.0001225450396305
dG 1: -0.00016612693434581
dG 2: -3.7714640438447e-12
---
StyleLoss:updateOutput self.G 1: 504472.28125
StyleLoss:updateOutput self.G 2: 0.045649435371161
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.455659316387e-05
dG 2: -3.1270084178275e-12
---
Iteration 190 / 2500
Content 1 loss: 452705.859375
Style 1 loss: 116916.080475
Style 2 loss: 87500976.562500
Style 3 loss: 112429019.531250
Style 4 loss: 6455081.542969
Style 5 loss: 240535.514832
Total loss: 207195235.091400
---
x1 value: -4.2339954376221
feval(x) grad value: -1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 497729024
StyleLoss:updateOutput self.G 2: 1.4162031412125
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.0012046924093738
dG 2: -3.4277468016763e-12
---
StyleLoss:updateOutput self.G 1: 4903361536
StyleLoss:updateOutput self.G 2: 27.903352737427
StyleLoss:updateGradInput self.gradInput 1: -5.6737885500979e-09
StyleLoss:updateGradInput self.gradInput 2: -2.9991879273439e-05
dG 1: -0.011967984028161
dG 2: -6.8105715511635e-11
---
StyleLoss:updateOutput self.G 1: 1551745408
StyleLoss:updateOutput self.G 2: 17.645278930664
StyleLoss:updateGradInput self.gradInput 1: -1.1156587653716e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3741485064384e-05
dG 1: -0.0031912212725729
dG 2: -3.6288149568575e-11
---
StyleLoss:updateOutput self.G 1: 82983296
StyleLoss:updateOutput self.G 2: 1.8839122056961
StyleLoss:updateGradInput self.gradInput 1: -2.0654095322925e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012258844799362
dG 1: -0.00016617719666101
dG 2: -3.7726067929345e-12
---
StyleLoss:updateOutput self.G 1: 500503.71875
StyleLoss:updateOutput self.G 2: 0.045290317386389
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4559343475848e-05
dG 2: -3.1272571338059e-12
---
Iteration 191 / 2500
Content 1 loss: 452529.492188
Style 1 loss: 117138.290405
Style 2 loss: 87554437.500000
Style 3 loss: 112494890.625000
Style 4 loss: 6456468.017578
Style 5 loss: 240565.773010
Total loss: 207316029.698181
---
x1 value: -4.2313594818115
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 497181120
StyleLoss:updateOutput self.G 2: 1.4146440029144
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071975889849e-05
dG 1: -0.0012054537655786
dG 2: -3.4299126039361e-12
---
StyleLoss:updateOutput self.G 1: 4897100288
StyleLoss:updateOutput self.G 2: 27.867723464966
StyleLoss:updateGradInput self.gradInput 1: -5.6738795883859e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0013412469998e-05
dG 1: -0.011972334235907
dG 2: -6.813046654619e-11
---
StyleLoss:updateOutput self.G 1: 1547416576
StyleLoss:updateOutput self.G 2: 17.596050262451
StyleLoss:updateGradInput self.gradInput 1: -1.1157863077926e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3757121097296e-05
dG 1: -0.0031927227973938
dG 2: -3.630522965592e-11
---
StyleLoss:updateOutput self.G 1: 82695368
StyleLoss:updateOutput self.G 2: 1.8773760795593
StyleLoss:updateGradInput self.gradInput 1: -2.0662950461769e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012262367818039
dG 1: -0.00016622712428216
dG 2: -3.7737382663217e-12
---
StyleLoss:updateOutput self.G 1: 496575.65625
StyleLoss:updateOutput self.G 2: 0.044934872537851
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4562050132081e-05
dG 2: -3.1275023803373e-12
---
Iteration 192 / 2500
Content 1 loss: 452355.273438
Style 1 loss: 117360.054016
Style 2 loss: 87607523.437500
Style 3 loss: 112560210.937500
Style 4 loss: 6457847.167969
Style 5 loss: 240595.733643
Total loss: 207435892.604065
---
x1 value: -4.2287626266479
feval(x) grad value: -5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 496637088
StyleLoss:updateOutput self.G 2: 1.4130960702896
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0012062095338479
dG 2: -3.4320632273654e-12
---
StyleLoss:updateOutput self.G 1: 4890881024
StyleLoss:updateOutput self.G 2: 27.832330703735
StyleLoss:updateGradInput self.gradInput 1: -5.6739710707632e-09
StyleLoss:updateGradInput self.gradInput 2: -3.003563870152e-05
dG 1: -0.01197665464133
dG 2: -6.8155044108398e-11
---
StyleLoss:updateOutput self.G 1: 1543121280
StyleLoss:updateOutput self.G 2: 17.547212600708
StyleLoss:updateGradInput self.gradInput 1: -1.1159128732174e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3774721638765e-05
dG 1: -0.0031942131463438
dG 2: -3.6322174434833e-11
---
StyleLoss:updateOutput self.G 1: 82409656
StyleLoss:updateOutput self.G 2: 1.8708894252777
StyleLoss:updateGradInput self.gradInput 1: -2.0671766520763e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012265819532331
dG 1: -0.00016627655713819
dG 2: -3.7748623671341e-12
---
StyleLoss:updateOutput self.G 1: 492707.125
StyleLoss:updateOutput self.G 2: 0.044584807008505
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4564724046504e-05
dG 2: -3.1277439405814e-12
---
Iteration 193 / 2500
Content 1 loss: 452182.568359
Style 1 loss: 117580.078125
Style 2 loss: 87660263.671875
Style 3 loss: 112625050.781250
Style 4 loss: 6459212.402344
Style 5 loss: 240625.190735
Total loss: 207554914.692688
---
x1 value: -4.2262001037598
feval(x) grad value: 8.8330647147598e-18
---
StyleLoss:updateOutput self.G 1: 496095968
StyleLoss:updateOutput self.G 2: 1.4115562438965
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0012069613439962
dG 2: -3.4342025750922e-12
---
StyleLoss:updateOutput self.G 1: 4884704256
StyleLoss:updateOutput self.G 2: 27.797180175781
StyleLoss:updateGradInput self.gradInput 1: -5.6740625531404e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0056942705414e-05
dG 1: -0.011980945244431
dG 2: -6.817946901494e-11
---
StyleLoss:updateOutput self.G 1: 1538865792
StyleLoss:updateOutput self.G 2: 17.498821258545
StyleLoss:updateGradInput self.gradInput 1: -1.1160377511032e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3790386775509e-05
dG 1: -0.0031956902239472
dG 2: -3.6338973496974e-11
---
StyleLoss:updateOutput self.G 1: 82126456
StyleLoss:updateOutput self.G 2: 1.8644603490829
StyleLoss:updateGradInput self.gradInput 1: -2.0680495538272e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012270540173631
dG 1: -0.00016632562619634
dG 2: -3.7759760596057e-12
---
StyleLoss:updateOutput self.G 1: 488885.46875
StyleLoss:updateOutput self.G 2: 0.044238992035389
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4567361581139e-05
dG 2: -3.1279824650593e-12
---
Iteration 194 / 2500
Content 1 loss: 452013.037109
Style 1 loss: 117799.942017
Style 2 loss: 87712658.203125
Style 3 loss: 112689339.843750
Style 4 loss: 6460567.382812
Style 5 loss: 240654.327393
Total loss: 207673032.736206
---
x1 value: -4.2236700057983
feval(x) grad value: -1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 495558560
StyleLoss:updateOutput self.G 2: 1.4100270271301
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012077081482857
dG 2: -3.4363267439885e-12
---
StyleLoss:updateOutput self.G 1: 4878569472
StyleLoss:updateOutput self.G 2: 27.762271881104
StyleLoss:updateGradInput self.gradInput 1: -5.6741518150716e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0082343073445e-05
dG 1: -0.01198520604521
dG 2: -6.8203720449134e-11
---
StyleLoss:updateOutput self.G 1: 1534647168
StyleLoss:updateOutput self.G 2: 17.450847625732
StyleLoss:updateGradInput self.gradInput 1: -1.1161612079036e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3806983234826e-05
dG 1: -0.0031971542630345
dG 2: -3.6355626842344e-11
---
StyleLoss:updateOutput self.G 1: 81845624
StyleLoss:updateOutput self.G 2: 1.8580846786499
StyleLoss:updateGradInput self.gradInput 1: -2.0689160606935e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012273533502594
dG 1: -0.00016637430235278
dG 2: -3.7770797774173e-12
---
StyleLoss:updateOutput self.G 1: 485119.09375
StyleLoss:updateOutput self.G 2: 0.043898168951273
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4569959098008e-05
dG 2: -3.1282175200903e-12
---
Iteration 195 / 2500
Content 1 loss: 451844.726562
Style 1 loss: 118017.425537
Style 2 loss: 87764689.453125
Style 3 loss: 112753136.718750
Style 4 loss: 6461912.109375
Style 5 loss: 240683.006287
Total loss: 207790283.439636
---
x1 value: -4.2211799621582
feval(x) grad value: 1.8549435900995e-17
---
StyleLoss:updateOutput self.G 1: 495024352
StyleLoss:updateOutput self.G 2: 1.4085071086884
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012084502959624
dG 2: -3.4384392035014e-12
---
StyleLoss:updateOutput self.G 1: 4872476160
StyleLoss:updateOutput self.G 2: 27.727592468262
StyleLoss:updateGradInput self.gradInput 1: -5.6742419651812e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0105096811894e-05
dG 1: -0.011989439837635
dG 2: -6.8227805349874e-11
---
StyleLoss:updateOutput self.G 1: 1530463104
StyleLoss:updateOutput self.G 2: 17.403266906738
StyleLoss:updateGradInput self.gradInput 1: -1.116283510072e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3822357333265e-05
dG 1: -0.0031986064277589
dG 2: -3.6372131001494e-11
---
StyleLoss:updateOutput self.G 1: 81567272
StyleLoss:updateOutput self.G 2: 1.8517651557922
StyleLoss:updateGradInput self.gradInput 1: -2.069774573954e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012277443602215
dG 1: -0.00016642249829601
dG 2: -3.7781748216115e-12
---
StyleLoss:updateOutput self.G 1: 481400.6875
StyleLoss:updateOutput self.G 2: 0.043561689555645
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4572527511045e-05
dG 2: -3.1284504067169e-12
---
Iteration 196 / 2500
Content 1 loss: 451679.589844
Style 1 loss: 118233.467102
Style 2 loss: 87816375.000000
Style 3 loss: 112816429.687500
Style 4 loss: 6463244.384766
Style 5 loss: 240711.273193
Total loss: 207906673.402405
---
x1 value: -4.2187170982361
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 494493280
StyleLoss:updateOutput self.G 2: 1.406996011734
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012091880198568
dG 2: -3.4405382189073e-12
---
StyleLoss:updateOutput self.G 1: 4866424320
StyleLoss:updateOutput self.G 2: 27.693155288696
StyleLoss:updateGradInput self.gradInput 1: -5.6743307830232e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0130313461996e-05
dG 1: -0.011993643827736
dG 2: -6.8251723717161e-11
---
StyleLoss:updateOutput self.G 1: 1526315008
StyleLoss:updateOutput self.G 2: 17.356100082397
StyleLoss:updateGradInput self.gradInput 1: -1.1164041247014e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3837243942544e-05
dG 1: -0.0032000455539674
dG 2: -3.638850332166e-11
---
StyleLoss:updateOutput self.G 1: 81291496
StyleLoss:updateOutput self.G 2: 1.8455048799515
StyleLoss:updateGradInput self.gradInput 1: -2.0706277581439e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012280713417567
dG 1: -0.00016647025768179
dG 2: -3.7792585901031e-12
---
StyleLoss:updateOutput self.G 1: 477734
StyleLoss:updateOutput self.G 2: 0.043229907751083
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4575055906316e-05
dG 2: -3.1286791733753e-12
---
Iteration 197 / 2500
Content 1 loss: 451516.357422
Style 1 loss: 118449.291229
Style 2 loss: 87867732.421875
Style 3 loss: 112879218.750000
Style 4 loss: 6464561.279297
Style 5 loss: 240739.151001
Total loss: 208022217.250824
---
x1 value: -4.2162976264954
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 493965056
StyleLoss:updateOutput self.G 2: 1.4054931402206
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012099219020456
dG 2: -3.4426259586107e-12
---
StyleLoss:updateOutput self.G 1: 4860412416
StyleLoss:updateOutput self.G 2: 27.658945083618
StyleLoss:updateGradInput self.gradInput 1: -5.6744196008651e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0152255931171e-05
dG 1: -0.011997818946838
dG 2: -6.8275496367676e-11
---
StyleLoss:updateOutput self.G 1: 1522203520
StyleLoss:updateOutput self.G 2: 17.309345245361
StyleLoss:updateGradInput self.gradInput 1: -1.1165234070631e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3851482991595e-05
dG 1: -0.003201472107321
dG 2: -3.6404726455608e-11
---
StyleLoss:updateOutput self.G 1: 81017832
StyleLoss:updateOutput self.G 2: 1.8392916917801
StyleLoss:updateGradInput self.gradInput 1: -2.0714709947356e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012284058902878
dG 1: -0.00016651766782161
dG 2: -3.7803349860199e-12
---
StyleLoss:updateOutput self.G 1: 474113.46875
StyleLoss:updateOutput self.G 2: 0.042902283370495
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4577555197757e-05
dG 2: -3.1289051211081e-12
---
Iteration 198 / 2500
Content 1 loss: 451354.687500
Style 1 loss: 118663.890839
Style 2 loss: 87918755.859375
Style 3 loss: 112941503.906250
Style 4 loss: 6465873.046875
Style 5 loss: 240766.708374
Total loss: 208136918.099213
---
x1 value: -4.2139000892639
feval(x) grad value: 2.6499192076328e-18
---
StyleLoss:updateOutput self.G 1: 493439936
StyleLoss:updateOutput self.G 2: 1.4039989709854
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012106514768675
dG 2: -3.4447019889305e-12
---
StyleLoss:updateOutput self.G 1: 4854441472
StyleLoss:updateOutput self.G 2: 27.624963760376
StyleLoss:updateGradInput self.gradInput 1: -5.6745079746179e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0174251151038e-05
dG 1: -0.012001967988908
dG 2: -6.8299102484737e-11
---
StyleLoss:updateOutput self.G 1: 1518124928
StyleLoss:updateOutput self.G 2: 17.262971878052
StyleLoss:updateGradInput self.gradInput 1: -1.1166410907038e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3867053540889e-05
dG 1: -0.0032028874848038
dG 2: -3.6420817750571e-11
---
StyleLoss:updateOutput self.G 1: 80746448
StyleLoss:updateOutput self.G 2: 1.8331309556961
StyleLoss:updateGradInput self.gradInput 1: -2.0723106786136e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012288044672459
dG 1: -0.00016656465595588
dG 2: -3.7814022746385e-12
---
StyleLoss:updateOutput self.G 1: 470536.78125
StyleLoss:updateOutput self.G 2: 0.042578641325235
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4580021747388e-05
dG 2: -3.129128683596e-12
---
Iteration 199 / 2500
Content 1 loss: 451195.996094
Style 1 loss: 118878.250122
Style 2 loss: 87969451.171875
Style 3 loss: 113003332.031250
Style 4 loss: 6467170.166016
Style 5 loss: 240793.876648
Total loss: 208250821.492004
---
x1 value: -4.2115488052368
feval(x) grad value: 6.1831448867415e-18
---
StyleLoss:updateOutput self.G 1: 492918368
StyleLoss:updateOutput self.G 2: 1.4025151729584
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071966794902e-05
dG 1: -0.0012113761622459
dG 2: -3.4467632741009e-12
---
StyleLoss:updateOutput self.G 1: 4848510976
StyleLoss:updateOutput self.G 2: 27.591220855713
StyleLoss:updateGradInput self.gradInput 1: -5.6745963483706e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0199054890545e-05
dG 1: -0.012006087228656
dG 2: -6.832253512945e-11
---
StyleLoss:updateOutput self.G 1: 1514082816
StyleLoss:updateOutput self.G 2: 17.217004776001
StyleLoss:updateGradInput self.gradInput 1: -1.1167577973481e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3883730035741e-05
dG 1: -0.0032042905222625
dG 2: -3.6436773737103e-11
---
StyleLoss:updateOutput self.G 1: 80477848
StyleLoss:updateOutput self.G 2: 1.8270328044891
StyleLoss:updateGradInput self.gradInput 1: -2.0731393490792e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012291327584535
dG 1: -0.00016661119298078
dG 2: -3.7824578538737e-12
---
StyleLoss:updateOutput self.G 1: 467020.9375
StyleLoss:updateOutput self.G 2: 0.042260497808456
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4582451917231e-05
dG 2: -3.1293487766371e-12
---
Iteration 200 / 2500
Content 1 loss: 451038.964844
Style 1 loss: 119091.304779
Style 2 loss: 88019794.921875
Style 3 loss: 113064621.093750
Style 4 loss: 6468457.763672
Style 5 loss: 240820.564270
Total loss: 208363824.613190
---
x1 value: -4.2092189788818
feval(x) grad value: -1.5016210015092e-17
---
StyleLoss:updateOutput self.G 1: 492399168
StyleLoss:updateOutput self.G 2: 1.4010376930237
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197225187e-05
dG 1: -0.0012120974715799
dG 2: -3.4488158856538e-12
---
StyleLoss:updateOutput self.G 1: 4842621440
StyleLoss:updateOutput self.G 2: 27.55770111084
StyleLoss:updateGradInput self.gradInput 1: -5.6746825016774e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0223247449612e-05
dG 1: -0.012010179460049
dG 2: -6.8345815118498e-11
---
StyleLoss:updateOutput self.G 1: 1510073344
StyleLoss:updateOutput self.G 2: 17.171417236328
StyleLoss:updateGradInput self.gradInput 1: -1.1168728164535e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3900741224643e-05
dG 1: -0.0032056816853583
dG 2: -3.6452590945757e-11
---
StyleLoss:updateOutput self.G 1: 80210920
StyleLoss:updateOutput self.G 2: 1.8209725618362
StyleLoss:updateGradInput self.gradInput 1: -2.0739628681099e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012295304622967
dG 1: -0.00016665740986355
dG 2: -3.7835077952575e-12
---
StyleLoss:updateOutput self.G 1: 463533.40625
StyleLoss:updateOutput self.G 2: 0.041944891214371
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4584860259201e-05
dG 2: -3.1295664844333e-12
---
Iteration 201 / 2500
Content 1 loss: 450884.082031
Style 1 loss: 119303.615570
Style 2 loss: 88069804.687500
Style 3 loss: 113125511.718750
Style 4 loss: 6469736.572266
Style 5 loss: 240847.091675
Total loss: 208476087.767792
---
x1 value: -4.2069306373596
feval(x) grad value: 9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 491883552
StyleLoss:updateOutput self.G 2: 1.3995707035065
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.0012128137750551
dG 2: -3.4508544025785e-12
---
StyleLoss:updateOutput self.G 1: 4836769792
StyleLoss:updateOutput self.G 2: 27.524404525757
StyleLoss:updateGradInput self.gradInput 1: -5.6747695431625e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0244889785536e-05
dG 1: -0.012014243751764
dG 2: -6.8368956329667e-11
---
StyleLoss:updateOutput self.G 1: 1506096896
StyleLoss:updateOutput self.G 2: 17.12619972229
StyleLoss:updateGradInput self.gradInput 1: -1.1169869473804e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3915700593498e-05
dG 1: -0.0032070619054139
dG 2: -3.6468283254321e-11
---
StyleLoss:updateOutput self.G 1: 79946960
StyleLoss:updateOutput self.G 2: 1.8149808645248
StyleLoss:updateGradInput self.gradInput 1: -2.0747785711706e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012298941146582
dG 1: -0.00016670308832545
dG 2: -3.7845460272579e-12
---
StyleLoss:updateOutput self.G 1: 460111.0625
StyleLoss:updateOutput self.G 2: 0.04163521900773
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4587228583405e-05
dG 2: -3.1297802891017e-12
---
Iteration 202 / 2500
Content 1 loss: 450731.103516
Style 1 loss: 119513.763428
Style 2 loss: 88119503.906250
Style 3 loss: 113185875.000000
Style 4 loss: 6471000.000000
Style 5 loss: 240873.069763
Total loss: 208587496.842957
---
x1 value: -4.2046689987183
feval(x) grad value: 0
---
StyleLoss:updateOutput self.G 1: 491370944
StyleLoss:updateOutput self.G 2: 1.3981120586395
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012135261204094
dG 2: -3.4528807764389e-12
---
StyleLoss:updateOutput self.G 1: 4830955520
StyleLoss:updateOutput self.G 2: 27.491317749023
StyleLoss:updateGradInput self.gradInput 1: -5.6748570287368e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0263992812252e-05
dG 1: -0.012018281966448
dG 2: -6.8391931007383e-11
---
StyleLoss:updateOutput self.G 1: 1502154496
StyleLoss:updateOutput self.G 2: 17.081369400024
StyleLoss:updateGradInput self.gradInput 1: -1.1170993907683e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3928797317203e-05
dG 1: -0.003208430018276
dG 2: -3.6483840254453e-11
---
StyleLoss:updateOutput self.G 1: 79684520
StyleLoss:updateOutput self.G 2: 1.8090223073959
StyleLoss:updateGradInput self.gradInput 1: -2.0755878793466e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012302721734159
dG 1: -0.00016674856306054
dG 2: -3.7855777540452e-12
---
StyleLoss:updateOutput self.G 1: 456718.96875
StyleLoss:updateOutput self.G 2: 0.041328277438879
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4589567803778e-05
dG 2: -3.1299921422062e-12
---
Iteration 203 / 2500
Content 1 loss: 450579.345703
Style 1 loss: 119723.419189
Style 2 loss: 88168880.859375
Style 3 loss: 113245804.687500
Style 4 loss: 6472259.033203
Style 5 loss: 240898.818970
Total loss: 208698146.163940
---
x1 value: -4.2024412155151
feval(x) grad value: 3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 490860928
StyleLoss:updateOutput self.G 2: 1.3966608047485
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.001214234624058
dG 2: -3.4548969587989e-12
---
StyleLoss:updateOutput self.G 1: 4825180160
StyleLoss:updateOutput self.G 2: 27.458452224731
StyleLoss:updateGradInput self.gradInput 1: -5.6749418497759e-09
StyleLoss:updateGradInput self.gradInput 2: -3.028366700164e-05
dG 1: -0.012022294104099
dG 2: -6.8414766907221e-11
---
StyleLoss:updateOutput self.G 1: 1498244864
StyleLoss:updateOutput self.G 2: 17.036903381348
StyleLoss:updateGradInput self.gradInput 1: -1.1172106795243e-08
StyleLoss:updateGradInput self.gradInput 2: -6.394182855729e-05
dG 1: -0.0032097862567753
dG 2: -3.6499261946155e-11
---
StyleLoss:updateOutput self.G 1: 79424856
StyleLoss:updateOutput self.G 2: 1.8031277656555
StyleLoss:updateGradInput self.gradInput 1: -2.0763897268239e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012305908603594
dG 1: -0.00016679354303051
dG 2: -3.7865986388108e-12
---
StyleLoss:updateOutput self.G 1: 453377.90625
StyleLoss:updateOutput self.G 2: 0.041025936603546
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4591870644363e-05
dG 2: -3.1302007427042e-12
---
Iteration 204 / 2500
Content 1 loss: 450430.468750
Style 1 loss: 119931.747437
Style 2 loss: 88217947.265625
Style 3 loss: 113305242.187500
Style 4 loss: 6473503.417969
Style 5 loss: 240924.179077
Total loss: 208807979.266357
---
x1 value: -4.2002449035645
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 490354144
StyleLoss:updateOutput self.G 2: 1.3952189683914
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012149387039244
dG 2: -3.4569001307327e-12
---
StyleLoss:updateOutput self.G 1: 4819441664
StyleLoss:updateOutput self.G 2: 27.425792694092
StyleLoss:updateGradInput self.gradInput 1: -5.6750275589934e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0309342037071e-05
dG 1: -0.012026282027364
dG 2: -6.8437457090287e-11
---
StyleLoss:updateOutput self.G 1: 1494367488
StyleLoss:updateOutput self.G 2: 16.992818832397
StyleLoss:updateGradInput self.gradInput 1: -1.1173205471948e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3958977989387e-05
dG 1: -0.0032111320178956
dG 2: -3.6514569146107e-11
---
StyleLoss:updateOutput self.G 1: 79166840
StyleLoss:updateOutput self.G 2: 1.797269821167
StyleLoss:updateGradInput self.gradInput 1: -2.0771858899593e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012309341400396
dG 1: -0.00016683823196217
dG 2: -3.7876138857251e-12
---
StyleLoss:updateOutput self.G 1: 450074.9375
StyleLoss:updateOutput self.G 2: 0.040727064013481
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4594158933032e-05
dG 2: -3.1304071747978e-12
---
Iteration 205 / 2500
Content 1 loss: 450282.958984
Style 1 loss: 120139.297485
Style 2 loss: 88266714.843750
Style 3 loss: 113364257.812500
Style 4 loss: 6474741.210938
Style 5 loss: 240949.218750
Total loss: 208917085.342407
---
x1 value: -4.1980781555176
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 489850464
StyleLoss:updateOutput self.G 2: 1.3937857151031
StyleLoss:updateGradInput self.gradInput 1: -2.8453288614116e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012156384764239
dG 2: -3.4588915932832e-12
---
StyleLoss:updateOutput self.G 1: 4813741056
StyleLoss:updateOutput self.G 2: 27.393356323242
StyleLoss:updateGradInput self.gradInput 1: -5.6751119359433e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0331359084812e-05
dG 1: -0.012030238285661
dG 2: -6.8459987678793e-11
---
StyleLoss:updateOutput self.G 1: 1490522880
StyleLoss:updateOutput self.G 2: 16.949102401733
StyleLoss:updateGradInput self.gradInput 1: -1.1174291714156e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3972926000133e-05
dG 1: -0.0032124656718224
dG 2: -3.6529741037628e-11
---
StyleLoss:updateOutput self.G 1: 78911080
StyleLoss:updateOutput self.G 2: 1.7914634943008
StyleLoss:updateGradInput self.gradInput 1: -2.077974059489e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012312656326685
dG 1: -0.00016688255709596
dG 2: -3.7886191579795e-12
---
StyleLoss:updateOutput self.G 1: 446816.78125
StyleLoss:updateOutput self.G 2: 0.040432225912809
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293673019856
dG 1: -3.4596399927977e-05
dG 2: -3.1306105711254e-12
---
Iteration 206 / 2500
Content 1 loss: 450137.500000
Style 1 loss: 120346.389771
Style 2 loss: 88315154.296875
Style 3 loss: 113422804.687500
Style 4 loss: 6475968.017578
Style 5 loss: 240973.960876
Total loss: 209025384.852600
---
x1 value: -4.1959452629089
feval(x) grad value: 1.1482983302007e-17
---
StyleLoss:updateOutput self.G 1: 489349600
StyleLoss:updateOutput self.G 2: 1.3923606872559
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012163342908025
dG 2: -3.4608713464501e-12
---
StyleLoss:updateOutput self.G 1: 4808077312
StyleLoss:updateOutput self.G 2: 27.361122131348
StyleLoss:updateGradInput self.gradInput 1: -5.6751976451608e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0352368412423e-05
dG 1: -0.012034175917506
dG 2: -6.8482372550527e-11
---
StyleLoss:updateOutput self.G 1: 1486707840
StyleLoss:updateOutput self.G 2: 16.905717849731
StyleLoss:updateGradInput self.gradInput 1: -1.1175364633687e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3985717133619e-05
dG 1: -0.0032137897796929
dG 2: -3.6544791498505e-11
---
StyleLoss:updateOutput self.G 1: 78657392
StyleLoss:updateOutput self.G 2: 1.7857044935226
StyleLoss:updateGradInput self.gradInput 1: -2.078755834134e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012315694766585
dG 1: -0.00016692650387995
dG 2: -3.7896161902973e-12
---
StyleLoss:updateOutput self.G 1: 443597.15625
StyleLoss:updateOutput self.G 2: 0.040140870958567
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293690482154
dG 1: -3.4598633646965e-05
dG 2: -3.1308115822082e-12
---
Iteration 207 / 2500
Content 1 loss: 449993.750000
Style 1 loss: 120551.811218
Style 2 loss: 88363300.781250
Style 3 loss: 113480941.406250
Style 4 loss: 6477186.035156
Style 5 loss: 240998.405457
Total loss: 209132972.189331
---
x1 value: -4.1938409805298
feval(x) grad value: 1.2366289773483e-17
---
StyleLoss:updateOutput self.G 1: 488850944
StyleLoss:updateOutput self.G 2: 1.390941619873
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012170270783827
dG 2: -3.4628428596806e-12
---
StyleLoss:updateOutput self.G 1: 4802448896
StyleLoss:updateOutput self.G 2: 27.329097747803
StyleLoss:updateGradInput self.gradInput 1: -5.675280689843e-09
StyleLoss:updateGradInput self.gradInput 2: -3.03715296468e-05
dG 1: -0.012038084678352
dG 2: -6.8504625583277e-11
---
StyleLoss:updateOutput self.G 1: 1482925056
StyleLoss:updateOutput self.G 2: 16.862705230713
StyleLoss:updateGradInput self.gradInput 1: -1.1176426006898e-08
StyleLoss:updateGradInput self.gradInput 2: -6.3998122641351e-05
dG 1: -0.0032151029445231
dG 2: -3.6559717059292e-11
---
StyleLoss:updateOutput self.G 1: 78405960
StyleLoss:updateOutput self.G 2: 1.7799959182739
StyleLoss:updateGradInput self.gradInput 1: -2.0795297928089e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012319316738285
dG 1: -0.0001669700286584
dG 2: -3.7906058500403e-12
---
StyleLoss:updateOutput self.G 1: 440426.84375
StyleLoss:updateOutput self.G 2: 0.039854004979134
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.460081279627e-05
dG 2: -3.1310095575249e-12
---
Iteration 208 / 2500
Content 1 loss: 449851.904297
Style 1 loss: 120757.896423
Style 2 loss: 88411136.718750
Style 3 loss: 113538621.093750
Style 4 loss: 6478394.531250
Style 5 loss: 241022.415161
Total loss: 209239784.559631
---
x1 value: -4.1917676925659
feval(x) grad value: -9.7163703590551e-18
---
StyleLoss:updateOutput self.G 1: 488355968
StyleLoss:updateOutput self.G 2: 1.3895334005356
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012177147436887
dG 2: -3.4647991940806e-12
---
StyleLoss:updateOutput self.G 1: 4796859392
StyleLoss:updateOutput self.G 2: 27.297285079956
StyleLoss:updateGradInput self.gradInput 1: -5.6753655108821e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0392158805626e-05
dG 1: -0.012041967362165
dG 2: -6.8526725960361e-11
---
StyleLoss:updateOutput self.G 1: 1479173760
StyleLoss:updateOutput self.G 2: 16.820045471191
StyleLoss:updateGradInput self.gradInput 1: -1.1177474945612e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4011277572718e-05
dG 1: -0.0032164044678211
dG 2: -3.6574521189436e-11
---
StyleLoss:updateOutput self.G 1: 78156872
StyleLoss:updateOutput self.G 2: 1.7743412256241
StyleLoss:updateGradInput self.gradInput 1: -2.0802971789635e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012322139809839
dG 1: -0.00016701316053513
dG 2: -3.7915842340808e-12
---
StyleLoss:updateOutput self.G 1: 437288.125
StyleLoss:updateOutput self.G 2: 0.039569977670908
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293678840622
dG 1: -3.4602984669618e-05
dG 2: -3.1312064486394e-12
---
Iteration 209 / 2500
Content 1 loss: 449712.109375
Style 1 loss: 120962.219238
Style 2 loss: 88458667.968750
Style 3 loss: 113595843.750000
Style 4 loss: 6479589.111328
Style 5 loss: 241046.195984
Total loss: 209345821.354675
---
x1 value: -4.189724445343
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 487863040
StyleLoss:updateOutput self.G 2: 1.3881310224533
StyleLoss:updateGradInput self.gradInput 1: -2.845328639367e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.001218399615027
dG 2: -3.466747722225e-12
---
StyleLoss:updateOutput self.G 1: 4791301632
StyleLoss:updateOutput self.G 2: 27.265655517578
StyleLoss:updateGradInput self.gradInput 1: -5.6754472232967e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0414928914979e-05
dG 1: -0.012045829556882
dG 2: -6.8548687559566e-11
---
StyleLoss:updateOutput self.G 1: 1475451776
StyleLoss:updateOutput self.G 2: 16.777719497681
StyleLoss:updateGradInput self.gradInput 1: -1.1178511449828e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4026127802208e-05
dG 1: -0.0032176959794015
dG 2: -3.6589210827831e-11
---
StyleLoss:updateOutput self.G 1: 77909632
StyleLoss:updateOutput self.G 2: 1.768728852272
StyleLoss:updateGradInput self.gradInput 1: -2.0810569267837e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012324909039307
dG 1: -0.0001670560304774
dG 2: -3.7925565465891e-12
---
StyleLoss:updateOutput self.G 1: 434191.875
StyleLoss:updateOutput self.G 2: 0.039289798587561
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4605116525199e-05
dG 2: -3.1313990029452e-12
---
Iteration 210 / 2500
Content 1 loss: 449573.486328
Style 1 loss: 121166.095734
Style 2 loss: 88505935.546875
Style 3 loss: 113652656.250000
Style 4 loss: 6480778.564453
Style 5 loss: 241069.633484
Total loss: 209451179.576874
---
x1 value: -4.1877088546753
feval(x) grad value: -3.5332258859039e-18
---
StyleLoss:updateOutput self.G 1: 487373664
StyleLoss:updateOutput self.G 2: 1.3867381811142
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.0012190795969218
dG 2: -3.468682589422e-12
---
StyleLoss:updateOutput self.G 1: 4785779712
StyleLoss:updateOutput self.G 2: 27.234237670898
StyleLoss:updateGradInput self.gradInput 1: -5.6755316002466e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0439396141446e-05
dG 1: -0.012049663811922
dG 2: -6.8570524258682e-11
---
StyleLoss:updateOutput self.G 1: 1471761408
StyleLoss:updateOutput self.G 2: 16.73575592041
StyleLoss:updateGradInput self.gradInput 1: -1.1179537295902e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4040505094454e-05
dG 1: -0.0032189772464335
dG 2: -3.6603775566135e-11
---
StyleLoss:updateOutput self.G 1: 77664216
StyleLoss:updateOutput self.G 2: 1.7631567716599
StyleLoss:updateGradInput self.gradInput 1: -2.0818131218903e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012327801960055
dG 1: -0.00016709849296603
dG 2: -3.7935219202034e-12
---
StyleLoss:updateOutput self.G 1: 431129.5
StyleLoss:updateOutput self.G 2: 0.039012696594
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4607233828865e-05
dG 2: -3.1315904730489e-12
---
Iteration 211 / 2500
Content 1 loss: 449437.304688
Style 1 loss: 121367.820740
Style 2 loss: 88552898.437500
Style 3 loss: 113709023.437500
Style 4 loss: 6481957.031250
Style 5 loss: 241092.842102
Total loss: 209555776.873779
---
x1 value: -4.1857252120972
feval(x) grad value: 5.2998384152655e-18
---
StyleLoss:updateOutput self.G 1: 486886592
StyleLoss:updateOutput self.G 2: 1.3853526115417
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012197563191876
dG 2: -3.4706079156399e-12
---
StyleLoss:updateOutput self.G 1: 4780293120
StyleLoss:updateOutput self.G 2: 27.203010559082
StyleLoss:updateGradInput self.gradInput 1: -5.6756146449288e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0460940251942e-05
dG 1: -0.01205347571522
dG 2: -6.8592215241026e-11
---
StyleLoss:updateOutput self.G 1: 1468098432
StyleLoss:updateOutput self.G 2: 16.694108963013
StyleLoss:updateGradInput self.gradInput 1: -1.1180548931122e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4054089307319e-05
dG 1: -0.0032202478032559
dG 2: -3.6618229282137e-11
---
StyleLoss:updateOutput self.G 1: 77421056
StyleLoss:updateOutput self.G 2: 1.7576369047165
StyleLoss:updateGradInput self.gradInput 1: -2.0825606128483e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012330937897786
dG 1: -0.00016714062076062
dG 2: -3.7944781865196e-12
---
StyleLoss:updateOutput self.G 1: 428110.96875
StyleLoss:updateOutput self.G 2: 0.038739539682865
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4609314752743e-05
dG 2: -3.1317791242269e-12
---
Iteration 212 / 2500
Content 1 loss: 449302.832031
Style 1 loss: 121569.168091
Style 2 loss: 88599568.359375
Style 3 loss: 113764992.187500
Style 4 loss: 6483126.708984
Style 5 loss: 241115.684509
Total loss: 209659674.940491
---
x1 value: -4.1837668418884
feval(x) grad value: 1.766612942952e-18
---
StyleLoss:updateOutput self.G 1: 486402432
StyleLoss:updateOutput self.G 2: 1.3839750289917
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012204288505018
dG 2: -3.4725217493148e-12
---
StyleLoss:updateOutput self.G 1: 4774841856
StyleLoss:updateOutput self.G 2: 27.171989440918
StyleLoss:updateGradInput self.gradInput 1: -5.6756959132542e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0481462090393e-05
dG 1: -0.012057263404131
dG 2: -6.8613760506597e-11
---
StyleLoss:updateOutput self.G 1: 1464467968
StyleLoss:updateOutput self.G 2: 16.652820587158
StyleLoss:updateGradInput self.gradInput 1: -1.1181547243666e-08
StyleLoss:updateGradInput self.gradInput 2: -6.406848115148e-05
dG 1: -0.0032215076498687
dG 2: -3.6632554628602e-11
---
StyleLoss:updateOutput self.G 1: 77179848
StyleLoss:updateOutput self.G 2: 1.7521606683731
StyleLoss:updateGradInput self.gradInput 1: -2.0833034852785e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012334441998973
dG 1: -0.00016718241386116
dG 2: -3.7954266465801e-12
---
StyleLoss:updateOutput self.G 1: 425121.15625
StyleLoss:updateOutput self.G 2: 0.03846899420023
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4611381124705e-05
dG 2: -3.131965823841e-12
---
Iteration 213 / 2500
Content 1 loss: 449169.921875
Style 1 loss: 121769.393921
Style 2 loss: 88645945.312500
Style 3 loss: 113820515.625000
Style 4 loss: 6484285.400391
Style 5 loss: 241138.298035
Total loss: 209762823.951721
---
x1 value: -4.1818423271179
feval(x) grad value: -4.4165323573799e-18
---
StyleLoss:updateOutput self.G 1: 485920544
StyleLoss:updateOutput self.G 2: 1.3826036453247
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.0012210984714329
dG 2: -3.4744269093723e-12
---
StyleLoss:updateOutput self.G 1: 4769424384
StyleLoss:updateOutput self.G 2: 27.141160964966
StyleLoss:updateGradInput self.gradInput 1: -5.6757789579365e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0502018489642e-05
dG 1: -0.012061026878655
dG 2: -6.8635173933185e-11
---
StyleLoss:updateOutput self.G 1: 1460864512
StyleLoss:updateOutput self.G 2: 16.611845016479
StyleLoss:updateGradInput self.gradInput 1: -1.1182538450782e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4081192249432e-05
dG 1: -0.0032227588817477
dG 2: -3.6646782830552e-11
---
StyleLoss:updateOutput self.G 1: 76940792
StyleLoss:updateOutput self.G 2: 1.746733546257
StyleLoss:updateGradInput self.gradInput 1: -2.0840381864673e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012337765656412
dG 1: -0.00016722384316381
dG 2: -3.7963664330232e-12
---
StyleLoss:updateOutput self.G 1: 422177.9375
StyleLoss:updateOutput self.G 2: 0.038202662020922
StyleLoss:updateGradInput self.gradInput 1: -9.0489471915589e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4613407478901e-05
dG 2: -3.1321503550508e-12
---
Iteration 214 / 2500
Content 1 loss: 449039.355469
Style 1 loss: 121968.647003
Style 2 loss: 88692041.015625
Style 3 loss: 113875640.625000
Style 4 loss: 6485436.035156
Style 5 loss: 241160.568237
Total loss: 209865286.246490
---
x1 value: -4.1799416542053
feval(x) grad value: -1.0599676830531e-17
---
StyleLoss:updateOutput self.G 1: 485441472
StyleLoss:updateOutput self.G 2: 1.3812408447266
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012217639014125
dG 2: -3.4763203600463e-12
---
StyleLoss:updateOutput self.G 1: 4764037632
StyleLoss:updateOutput self.G 2: 27.110511779785
StyleLoss:updateGradInput self.gradInput 1: -5.6758588939942e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0521332519129e-05
dG 1: -0.012064768001437
dG 2: -6.8656469398576e-11
---
StyleLoss:updateOutput self.G 1: 1457290368
StyleLoss:updateOutput self.G 2: 16.571203231812
StyleLoss:updateGradInput self.gradInput 1: -1.1183513670687e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4094201661646e-05
dG 1: -0.0032239987049252
dG 2: -3.6660875724071e-11
---
StyleLoss:updateOutput self.G 1: 76703096
StyleLoss:updateOutput self.G 2: 1.7413377761841
StyleLoss:updateGradInput self.gradInput 1: -2.0847677362212e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012341281399131
dG 1: -0.00016726493777242
dG 2: -3.7973001479341e-12
---
StyleLoss:updateOutput self.G 1: 419254.875
StyleLoss:updateOutput self.G 2: 0.037938162684441
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4615426557139e-05
dG 2: -3.1323322841753e-12
---
Iteration 215 / 2500
Content 1 loss: 448909.277344
Style 1 loss: 122168.792725
Style 2 loss: 88737873.046875
Style 3 loss: 113930367.187500
Style 4 loss: 6486580.078125
Style 5 loss: 241182.655334
Total loss: 209967081.037903
---
x1 value: -4.178071975708
feval(x) grad value: -2.0316047189586e-17
---
StyleLoss:updateOutput self.G 1: 484964672
StyleLoss:updateOutput self.G 2: 1.3798842430115
StyleLoss:updateGradInput self.gradInput 1: -2.8453281952778e-09
StyleLoss:updateGradInput self.gradInput 2: -1.707197043288e-05
dG 1: -0.0012224263045937
dG 2: -3.478205137103e-12
---
StyleLoss:updateOutput self.G 1: 4758687232
StyleLoss:updateOutput self.G 2: 27.080062866211
StyleLoss:updateGradInput self.gradInput 1: -5.6759383859628e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0540675652446e-05
dG 1: -0.012068484909832
dG 2: -6.8677612208301e-11
---
StyleLoss:updateOutput self.G 1: 1453744256
StyleLoss:updateOutput self.G 2: 16.530883789062
StyleLoss:updateGradInput self.gradInput 1: -1.1184479120629e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4106970967259e-05
dG 1: -0.0032252292148769
dG 2: -3.6674871473075e-11
---
StyleLoss:updateOutput self.G 1: 76467528
StyleLoss:updateOutput self.G 2: 1.7359894514084
StyleLoss:updateGradInput self.gradInput 1: -2.0854896476408e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012344056449365
dG 1: -0.00016730579955038
dG 2: -3.7982277913129e-12
---
StyleLoss:updateOutput self.G 1: 416380.34375
StyleLoss:updateOutput self.G 2: 0.037678048014641
StyleLoss:updateGradInput self.gradInput 1: -9.0489486126444e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4617416531546e-05
dG 2: -3.1325118280551e-12
---
Iteration 216 / 2500
Content 1 loss: 448781.445312
Style 1 loss: 122367.324829
Style 2 loss: 88783423.828125
Style 3 loss: 113984695.312500
Style 4 loss: 6487716.064453
Style 5 loss: 241204.399109
Total loss: 210068188.374329
---
x1 value: -4.1762275695801
feval(x) grad value: 6.1831448867415e-18
---
StyleLoss:updateOutput self.G 1: 484491264
StyleLoss:updateOutput self.G 2: 1.378536939621
StyleLoss:updateGradInput self.gradInput 1: -2.8453279732332e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071966794902e-05
dG 1: -0.0012230841675773
dG 2: -3.4800769037335e-12
---
StyleLoss:updateOutput self.G 1: 4753369600
StyleLoss:updateOutput self.G 2: 27.049800872803
StyleLoss:updateGradInput self.gradInput 1: -5.6760200983774e-09
StyleLoss:updateGradInput self.gradInput 2: -3.0559549486497e-05
dG 1: -0.012072178535163
dG 2: -6.8698650934618e-11
---
StyleLoss:updateOutput self.G 1: 1450225024
StyleLoss:updateOutput self.G 2: 16.490863800049
StyleLoss:updateGradInput self.gradInput 1: -1.1185432136074e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4119565649889e-05
dG 1: -0.0032264499459416
dG 2: -3.6688756199776e-11
---
StyleLoss:updateOutput self.G 1: 76233728
StyleLoss:updateOutput self.G 2: 1.7306814193726
StyleLoss:updateGradInput self.gradInput 1: -2.086208361618e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012347115261946
dG 1: -0.00016734626842663
dG 2: -3.7991463273934e-12
---
StyleLoss:updateOutput self.G 1: 413536.6875
StyleLoss:updateOutput self.G 2: 0.037420727312565
StyleLoss:updateGradInput self.gradInput 1: -9.0489464810162e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293684661388
dG 1: -3.4619384678081e-05
dG 2: -3.1326896372114e-12
---
Iteration 217 / 2500
Content 1 loss: 448654.541016
Style 1 loss: 122564.678192
Style 2 loss: 88828675.781250
Style 3 loss: 114038625.000000
Style 4 loss: 6488841.796875
Style 5 loss: 241225.868225
Total loss: 210168587.665558
---
x1 value: -4.1744146347046
feval(x) grad value: -6.1831448867415e-18
---
StyleLoss:updateOutput self.G 1: 484020256
StyleLoss:updateOutput self.G 2: 1.3771970272064
StyleLoss:updateGradInput self.gradInput 1: -2.8453284173224e-09
StyleLoss:updateGradInput self.gradInput 2: -1.7071968613891e-05
dG 1: -0.001223738421686
dG 2: -3.4819384788637e-12
---
StyleLoss:updateOutput self.G 1: 4748084736
StyleLoss:updateOutput self.G 2: 27.019727706909
StyleLoss:updateGradInput self.gradInput 1: -5.6761004785244e-09
StyleLoss:updateGradInput self.gradInput 2: -3.05766807287e-05
dG 1: -0.01207584887743
dG 2: -6.8719523127481e-11
---
StyleLoss:updateOutput self.G 1: 1446734080
StyleLoss:updateOutput self.G 2: 16.451169967651
StyleLoss:updateGradInput self.gradInput 1: -1.118637271702e-08
StyleLoss:updateGradInput self.gradInput 2: -6.4131585531868e-05
dG 1: -0.0032276613637805
dG 2: -3.6702533373623e-11
---
StyleLoss:updateOutput self.G 1: 76001680
StyleLoss:updateOutput self.G 2: 1.725413441658
StyleLoss:updateGradInput self.gradInput 1: -2.0869185490824e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00012350127508398
dG 1: -0.00016738644626457
dG 2: -3.8000592256227e-12
---
StyleLoss:updateOutput self.G 1: 410721.6875
StyleLoss:updateOutput self.G 2: 0.037165995687246
StyleLoss:updateGradInput self.gradInput 1: -9.0489479021016e-08
StyleLoss:updateGradInput self.gradInput 2: -0.00054293696302921
dG 1: -3.4621323720785e-05
dG 2: -3.1328657116442e-12
---
Iteration 218 / 2500
Content 1 loss: 448529.980469
Style 1 loss: 122761.344910
Style 2 loss: 88873664.062500
Style 3 loss: 114092167.968750
Style 4 loss: 6489961.669922
Style 5 loss: 241247.154236
Total loss: 210268332.180786
---
x1 value: -4.1726250648499
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment