TF之DCGAN：基于TF利用DCGAN测试MNIST数据集并进行生成
测试结果
测试过程全记录
……开始测试
{'batch_size': <absl.flags._flag.Flag object at 0x000002A2FFDB1B38>,
'beta1': <absl.flags._flag.Flag object at 0x000002A2FE967DA0>,
'checkpoint_dir': <absl.flags._flag.Flag object at 0x000002A281135A20>,
'crop': <absl.flags._flag.BooleanFlag object at 0x000002A281135B70>,
'dataset': <absl.flags._flag.Flag object at 0x000002A281135908>,
'epoch': <absl.flags._flag.Flag object at 0x000002A2F7728048>,
'h': <tensorflow.python.platform.app._HelpFlag object at 0x000002A281135C50>,
'help': <tensorflow.python.platform.app._HelpFlag object at 0x000002A281135C50>,
'helpfull': <tensorflow.python.platform.app._HelpfullFlag object at 0x000002A281135CC0>,
'helpshort': <tensorflow.python.platform.app._HelpshortFlag object at 0x000002A281135D30>,
'input_fname_pattern': <absl.flags._flag.Flag object at 0x000002A281135978>,
'input_height': <absl.flags._flag.Flag object at 0x000002A2810ABCC0>,
'input_width': <absl.flags._flag.Flag object at 0x000002A281135780>,
'learning_rate': <absl.flags._flag.Flag object at 0x000002A2F92D7AC8>,
'output_height': <absl.flags._flag.Flag object at 0x000002A2811357F0>,
'output_width': <absl.flags._flag.Flag object at 0x000002A281135898>,
'sample_dir': <absl.flags._flag.Flag object at 0x000002A281135A90>,
'train': <absl.flags._flag.BooleanFlag object at 0x000002A281135AC8>,
'train_size': <absl.flags._flag.Flag object at 0x000002A2FE974400>,
'visualize': <absl.flags._flag.BooleanFlag object at 0x000002A281135BE0>}
2018-10-06 11:32:10.690386: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
data_MNIST\mnist
---------
Variables: name (type shape) [size]
---------
generator/g_h0_lin/Matrix:0 (float32_ref 110x1024) [112640, bytes: 450560]
generator/g_h0_lin/bias:0 (float32_ref 1024) [1024, bytes: 4096]
generator/g_bn0/beta:0 (float32_ref 1024) [1024, bytes: 4096]
generator/g_bn0/gamma:0 (float32_ref 1024) [1024, bytes: 4096]
generator/g_h1_lin/Matrix:0 (float32_ref 1034x6272) [6485248, bytes: 25940992]
generator/g_h1_lin/bias:0 (float32_ref 6272) [6272, bytes: 25088]
generator/g_bn1/beta:0 (float32_ref 6272) [6272, bytes: 25088]
generator/g_bn1/gamma:0 (float32_ref 6272) [6272, bytes: 25088]
generator/g_h2/w:0 (float32_ref 5x5x128x138) [441600, bytes: 1766400]
generator/g_h2/biases:0 (float32_ref 128) [128, bytes: 512]
generator/g_bn2/beta:0 (float32_ref 128) [128, bytes: 512]
generator/g_bn2/gamma:0 (float32_ref 128) [128, bytes: 512]
generator/g_h3/w:0 (float32_ref 5x5x1x138) [3450, bytes: 13800]
generator/g_h3/biases:0 (float32_ref 1) [1, bytes: 4]
discriminator/d_h0_conv/w:0 (float32_ref 5x5x11x11) [3025, bytes: 12100]
discriminator/d_h0_conv/biases:0 (float32_ref 11) [11, bytes: 44]
discriminator/d_h1_conv/w:0 (float32_ref 5x5x21x74) [38850, bytes: 155400]
discriminator/d_h1_conv/biases:0 (float32_ref 74) [74, bytes: 296]
discriminator/d_bn1/beta:0 (float32_ref 74) [74, bytes: 296]
discriminator/d_bn1/gamma:0 (float32_ref 74) [74, bytes: 296]
discriminator/d_h2_lin/Matrix:0 (float32_ref 3636x1024) [3723264, bytes: 14893056]
discriminator/d_h2_lin/bias:0 (float32_ref 1024) [1024, bytes: 4096]
discriminator/d_bn2/beta:0 (float32_ref 1024) [1024, bytes: 4096]
discriminator/d_bn2/gamma:0 (float32_ref 1024) [1024, bytes: 4096]
discriminator/d_h3_lin/Matrix:0 (float32_ref 1034x1) [1034, bytes: 4136]
discriminator/d_h3_lin/bias:0 (float32_ref 1) [1, bytes: 4]
Total size of variables: 10834690
Total bytes of variables: 43338760
[*] Reading checkpoints...
[*] Failed to find a checkpoint
[!] Load failed...
Epoch: [ 0] [ 0/1093] time: 3.3617, d_loss: 1.79891801, g_loss: 0.73078763
Epoch: [ 0] [ 1/1093] time: 6.4123, d_loss: 1.46442509, g_loss: 0.61579478
Epoch: [ 0] [ 2/1093] time: 8.7562, d_loss: 1.49022853, g_loss: 0.67894053
Epoch: [ 0] [ 3/1093] time: 10.9214, d_loss: 1.40174472, g_loss: 0.66220653
Epoch: [ 0] [ 4/1093] time: 13.3050, d_loss: 1.40663481, g_loss: 0.69936526
Epoch: [ 0] [ 5/1093] time: 15.5709, d_loss: 1.38957083, g_loss: 0.68421012
Epoch: [ 0] [ 6/1093] time: 17.8600, d_loss: 1.39213061, g_loss: 0.68934584
Epoch: [ 0] [ 7/1093] time: 20.4708, d_loss: 1.39794362, g_loss: 0.69806755
Epoch: [ 0] [ 8/1093] time: 23.0654, d_loss: 1.43503237, g_loss: 0.70846951
Epoch: [ 0] [ 9/1093] time: 25.5358, d_loss: 1.39276147, g_loss: 0.70669782
Epoch: [ 0] [ 10/1093] time: 28.2617, d_loss: 1.42136300, g_loss: 0.70364445
Epoch: [ 0] [ 11/1093] time: 30.8038, d_loss: 1.40051103, g_loss: 0.70014894
Epoch: [ 0] [ 12/1093] time: 33.3130, d_loss: 1.37765169, g_loss: 0.70824486
Epoch: [ 0] [ 13/1093] time: 35.6096, d_loss: 1.38219857, g_loss: 0.69451976
Epoch: [ 0] [ 14/1093] time: 37.8537, d_loss: 1.36866033, g_loss: 0.70824432
Epoch: [ 0] [ 15/1093] time: 40.1426, d_loss: 1.36621869, g_loss: 0.69405836
Epoch: [ 0] [ 16/1093] time: 42.7074, d_loss: 1.37535453, g_loss: 0.69518888
Epoch: [ 0] [ 17/1093] time: 44.8565, d_loss: 1.36989605, g_loss: 0.69930756
Epoch: [ 0] [ 18/1093] time: 46.7869, d_loss: 1.36563087, g_loss: 0.69781649
Epoch: [ 0] [ 19/1093] time: 48.7288, d_loss: 1.36397326, g_loss: 0.70866680
Epoch: [ 0] [ 20/1093] time: 51.0654, d_loss: 1.38101411, g_loss: 0.69544500
Epoch: [ 0] [ 21/1093] time: 53.5399, d_loss: 1.46281934, g_loss: 0.70643008
Epoch: [ 0] [ 22/1093] time: 56.5684, d_loss: 1.43966162, g_loss: 0.71961737
Epoch: [ 0] [ 23/1093] time: 59.5954, d_loss: 1.42399430, g_loss: 0.72861439
Epoch: [ 0] [ 24/1093] time: 62.9032, d_loss: 1.41276562, g_loss: 0.70471978
Epoch: [ 0] [ 25/1093] time: 65.7187, d_loss: 1.48300290, g_loss: 0.71538234
Epoch: [ 0] [ 26/1093] time: 68.6204, d_loss: 1.39843416, g_loss: 0.68771482
Epoch: [ 0] [ 27/1093] time: 70.8153, d_loss: 1.42166626, g_loss: 0.69409549
Epoch: [ 0] [ 28/1093] time: 73.5776, d_loss: 1.39594829, g_loss: 0.68035471
Epoch: [ 0] [ 29/1093] time: 76.6749, d_loss: 1.39489424, g_loss: 0.69306409
Epoch: [ 0] [ 30/1093] time: 79.8282, d_loss: 1.41070235, g_loss: 0.68208236
Epoch: [ 0] [ 31/1093] time: 83.5562, d_loss: 1.39976072, g_loss: 0.69344074
Epoch: [ 0] [ 32/1093] time: 86.5431, d_loss: 1.39875138, g_loss: 0.69864786
Epoch: [ 0] [ 33/1093] time: 89.7386, d_loss: 1.39117682, g_loss: 0.68384939
Epoch: [ 0] [ 34/1093] time: 92.1129, d_loss: 1.39306462, g_loss: 0.68603516
Epoch: [ 0] [ 35/1093] time: 94.6717, d_loss: 1.39766645, g_loss: 0.67713618
Epoch: [ 0] [ 36/1093] time: 97.4150, d_loss: 1.39619994, g_loss: 0.68300879
Epoch: [ 0] [ 37/1093] time: 99.9408, d_loss: 1.39534819, g_loss: 0.69076747
Epoch: [ 0] [ 38/1093] time: 103.1213, d_loss: 1.39753985, g_loss: 0.68903100
Epoch: [ 0] [ 39/1093] time: 105.8520, d_loss: 1.41161013, g_loss: 0.69302136
Epoch: [ 0] [ 40/1093] time: 108.9503, d_loss: 1.38997078, g_loss: 0.68370312
Epoch: [ 0] [ 41/1093] time: 112.2070, d_loss: 1.39786303, g_loss: 0.69124269
Epoch: [ 0] [ 42/1093] time: 115.2431, d_loss: 1.38943410, g_loss: 0.69021893
Epoch: [ 0] [ 43/1093] time: 118.6511, d_loss: 1.38621378, g_loss: 0.68407494
Epoch: [ 0] [ 44/1093] time: 122.0462, d_loss: 1.39240563, g_loss: 0.69688046
Epoch: [ 0] [ 45/1093] time: 125.3139, d_loss: 1.39452100, g_loss: 0.69252259
Epoch: [ 0] [ 46/1093] time: 129.0117, d_loss: 1.39167857, g_loss: 0.68246353
Epoch: [ 0] [ 47/1093] time: 132.8489, d_loss: 1.39049268, g_loss: 0.69009811
Epoch: [ 0] [ 48/1093] time: 136.4826, d_loss: 1.39105415, g_loss: 0.69570535
Epoch: [ 0] [ 49/1093] time: 139.8832, d_loss: 1.38744533, g_loss: 0.68307704
Epoch: [ 0] [ 50/1093] time: 142.6343, d_loss: 1.39128542, g_loss: 0.68657452
Epoch: [ 0] [ 51/1093] time: 145.0365, d_loss: 1.39720774, g_loss: 0.68289292
Epoch: [ 0] [ 52/1093] time: 148.8226, d_loss: 1.40998244, g_loss: 0.69946194
Epoch: [ 0] [ 53/1093] time: 151.4981, d_loss: 1.42358077, g_loss: 0.69425476
Epoch: [ 0] [ 54/1093] time: 154.4366, d_loss: 1.40655017, g_loss: 0.69315112
Epoch: [ 0] [ 55/1093] time: 157.9840, d_loss: 1.39314961, g_loss: 0.67903620
Epoch: [ 0] [ 56/1093] time: 160.5293, d_loss: 1.39538550, g_loss: 0.68701828
Epoch: [ 0] [ 57/1093] time: 162.8455, d_loss: 1.40030372, g_loss: 0.68119174
Epoch: [ 0] [ 58/1093] time: 165.5109, d_loss: 1.39839721, g_loss: 0.68374062
Epoch: [ 0] [ 59/1093] time: 168.1250, d_loss: 1.40220833, g_loss: 0.67849696
Epoch: [ 0] [ 60/1093] time: 170.4443, d_loss: 1.40346980, g_loss: 0.68534362
Epoch: [ 0] [ 61/1093] time: 172.5757, d_loss: 1.40919614, g_loss: 0.68264174
Epoch: [ 0] [ 62/1093] time: 175.3375, d_loss: 1.41680074, g_loss: 0.69107366
Epoch: [ 0] [ 63/1093] time: 178.1931, d_loss: 1.42677331, g_loss: 0.68684256
Epoch: [ 0] [ 64/1093] time: 180.9363, d_loss: 1.41873085, g_loss: 0.68174267
Epoch: [ 0] [ 65/1093] time: 183.4142, d_loss: 1.41352820, g_loss: 0.69168335
Epoch: [ 0] [ 66/1093] time: 186.2004, d_loss: 1.40492952, g_loss: 0.68485790
Epoch: [ 0] [ 67/1093] time: 188.9013, d_loss: 1.41416049, g_loss: 0.69247150
Epoch: [ 0] [ 68/1093] time: 191.3907, d_loss: 1.44085050, g_loss: 0.70080090
Epoch: [ 0] [ 69/1093] time: 193.6596, d_loss: 1.42936659, g_loss: 0.70780182
Epoch: [ 0] [ 70/1093] time: 196.2392, d_loss: 1.39855242, g_loss: 0.68066621
Epoch: [ 0] [ 71/1093] time: 198.6732, d_loss: 1.39962685, g_loss: 0.68119228
Epoch: [ 0] [ 72/1093] time: 201.1359, d_loss: 1.39792156, g_loss: 0.68046838
Epoch: [ 0] [ 73/1093] time: 203.9913, d_loss: 1.40156364, g_loss: 0.68185544
Epoch: [ 0] [ 74/1093] time: 206.5057, d_loss: 1.40137339, g_loss: 0.68439347
Epoch: [ 0] [ 75/1093] time: 208.9730, d_loss: 1.39628625, g_loss: 0.68880224
Epoch: [ 0] [ 76/1093] time: 212.1802, d_loss: 1.39695120, g_loss: 0.69053137
Epoch: [ 0] [ 77/1093] time: 215.1069, d_loss: 1.39827728, g_loss: 0.67404974
Epoch: [ 0] [ 78/1093] time: 217.8231, d_loss: 1.39441288, g_loss: 0.68811285
Epoch: [ 0] [ 79/1093] time: 220.8017, d_loss: 1.39862061, g_loss: 0.68243313
Epoch: [ 0] [ 80/1093] time: 223.6711, d_loss: 1.39560962, g_loss: 0.68420863
Epoch: [ 0] [ 81/1093] time: 226.1243, d_loss: 1.39474165, g_loss: 0.68446684
Epoch: [ 0] [ 82/1093] time: 228.9125, d_loss: 1.39735079, g_loss: 0.68914992
Epoch: [ 0] [ 83/1093] time: 231.7087, d_loss: 1.40495729, g_loss: 0.67565703
Epoch: [ 0] [ 84/1093] time: 234.3499, d_loss: 1.40376186, g_loss: 0.68402076
Epoch: [ 0] [ 85/1093] time: 236.8927, d_loss: 1.39633703, g_loss: 0.67996454
Epoch: [ 0] [ 86/1093] time: 239.8556, d_loss: 1.40431571, g_loss: 0.68185967
Epoch: [ 0] [ 87/1093] time: 242.7527, d_loss: 1.40456629, g_loss: 0.68880403
Epoch: [ 0] [ 88/1093] time: 245.2765, d_loss: 1.39363539, g_loss: 0.68647277
Epoch: [ 0] [ 89/1093] time: 247.9097, d_loss: 1.39768720, g_loss: 0.68281728
Epoch: [ 0] [ 90/1093] time: 250.6797, d_loss: 1.40258384, g_loss: 0.69015211
Epoch: [ 0] [ 91/1093] time: 252.9605, d_loss: 1.41010988, g_loss: 0.69163489
Epoch: [ 0] [ 92/1093] time: 255.8331, d_loss: 1.39705300, g_loss: 0.67692769
Epoch: [ 0] [ 93/1093] time: 258.7976, d_loss: 1.41552734, g_loss: 0.69169050
Epoch: [ 0] [ 94/1093] time: 262.1104, d_loss: 1.39865696, g_loss: 0.68793559
Epoch: [ 0] [ 95/1093] time: 265.0370, d_loss: 1.40191650, g_loss: 0.68027002
Epoch: [ 0] [ 96/1093] time: 267.7568, d_loss: 1.40628874, g_loss: 0.67845261
Epoch: [ 0] [ 97/1093] time: 270.7154, d_loss: 1.40095508, g_loss: 0.68664324
Epoch: [ 0] [ 98/1093] time: 273.6299, d_loss: 1.41269326, g_loss: 0.68330830
Epoch: [ 0] [ 99/1093] time: 276.4041, d_loss: 1.41343331, g_loss: 0.69674391
[Sample] d_loss: 1.39404178, g_loss: 0.71861243
Epoch: [ 0] [ 100/1093] time: 279.9370, d_loss: 1.39926529, g_loss: 0.69326425
Epoch: [ 0] [ 101/1093] time: 282.8589, d_loss: 1.39894390, g_loss: 0.68361241
Epoch: [ 0] [ 102/1093] time: 285.4811, d_loss: 1.39818084, g_loss: 0.69090337
Epoch: [ 0] [ 103/1093] time: 287.6454, d_loss: 1.39627695, g_loss: 0.67909706
Epoch: [ 0] [ 104/1093] time: 290.3276, d_loss: 1.39514160, g_loss: 0.68727589
Epoch: [ 0] [ 105/1093] time: 293.5694, d_loss: 1.40148556, g_loss: 0.68616998
Epoch: [ 0] [ 106/1093] time: 296.7065, d_loss: 1.39823532, g_loss: 0.68184149
Epoch: [ 0] [ 107/1093] time: 299.5040, d_loss: 1.40077090, g_loss: 0.67544007
Epoch: [ 0] [ 108/1093] time: 302.5080, d_loss: 1.40159750, g_loss: 0.68739390
Epoch: [ 0] [ 109/1093] time: 305.3266, d_loss: 1.40064311, g_loss: 0.68674183
Epoch: [ 0] [ 110/1093] time: 308.2463, d_loss: 1.40190828, g_loss: 0.68489563
Epoch: [ 0] [ 111/1093] time: 311.1315, d_loss: 1.40030766, g_loss: 0.68323624
Epoch: [ 0] [ 112/1093] time: 313.6623, d_loss: 1.40522921, g_loss: 0.68465257
Epoch: [ 0] [ 113/1093] time: 315.8854, d_loss: 1.40230381, g_loss: 0.68633473
Epoch: [ 0] [ 114/1093] time: 318.7970, d_loss: 1.39801478, g_loss: 0.68570250
Epoch: [ 0] [ 115/1093] time: 321.6567, d_loss: 1.39233088, g_loss: 0.69425821
Epoch: [ 0] [ 116/1093] time: 324.3372, d_loss: 1.39432418, g_loss: 0.69107527
Epoch: [ 0] [ 117/1093] time: 326.8445, d_loss: 1.39130545, g_loss: 0.68290126
Epoch: [ 0] [ 118/1093] time: 329.1802, d_loss: 1.39673066, g_loss: 0.68661714
Epoch: [ 0] [ 119/1093] time: 332.0277, d_loss: 1.39699149, g_loss: 0.67931700
Epoch: [ 0] [ 120/1093] time: 334.8419, d_loss: 1.39705801, g_loss: 0.68852103
Epoch: [ 0] [ 121/1093] time: 337.6835, d_loss: 1.39927506, g_loss: 0.68318164
Epoch: [ 0] [ 122/1093] time: 340.3911, d_loss: 1.40209258, g_loss: 0.68643534
Epoch: [ 0] [ 123/1093] time: 343.0330, d_loss: 1.40112543, g_loss: 0.69041389
Epoch: [ 0] [ 124/1093] time: 345.8064, d_loss: 1.40143585, g_loss: 0.69084817
Epoch: [ 0] [ 125/1093] time: 348.9863, d_loss: 1.40324247, g_loss: 0.70193779
Epoch: [ 0] [ 126/1093] time: 351.8812, d_loss: 1.39955139, g_loss: 0.68675363
Epoch: [ 0] [ 127/1093] time: 354.9174, d_loss: 1.40862107, g_loss: 0.69824570
Epoch: [ 0] [ 128/1093] time: 357.7363, d_loss: 1.39578080, g_loss: 0.69549251
Epoch: [ 0] [ 129/1093] time: 360.4571, d_loss: 1.38922095, g_loss: 0.68794793
Epoch: [ 0] [ 130/1093] time: 364.3229, d_loss: 1.38788533, g_loss: 0.68935359
Epoch: [ 0] [ 131/1093] time: 367.4653, d_loss: 1.39498520, g_loss: 0.69769442
Epoch: [ 0] [ 132/1093] time: 370.4092, d_loss: 1.39342451, g_loss: 0.69023544
Epoch: [ 0] [ 133/1093] time: 373.3060, d_loss: 1.39430809, g_loss: 0.68838501
Epoch: [ 0] [ 134/1093] time: 376.2512, d_loss: 1.39541030, g_loss: 0.68803596
Epoch: [ 0] [ 135/1093] time: 378.7966, d_loss: 1.39376295, g_loss: 0.68914735
Epoch: [ 0] [ 136/1093] time: 382.1250, d_loss: 1.39497781, g_loss: 0.68631697
Epoch: [ 0] [ 137/1093] time: 385.8740, d_loss: 1.39770007, g_loss: 0.68428373
Epoch: [ 0] [ 138/1093] time: 389.2484, d_loss: 1.39804626, g_loss: 0.68340981
Epoch: [ 0] [ 139/1093] time: 392.4917, d_loss: 1.39873266, g_loss: 0.68392915
Epoch: [ 0] [ 140/1093] time: 396.0942, d_loss: 1.39161348, g_loss: 0.68423885
Epoch: [ 0] [ 141/1093] time: 400.1480, d_loss: 1.39738464, g_loss: 0.68055761
Epoch: [ 0] [ 142/1093] time: 403.5110, d_loss: 1.40433574, g_loss: 0.69463068
Epoch: [ 0] [ 143/1093] time: 406.9601, d_loss: 1.39804697, g_loss: 0.68737072
Epoch: [ 0] [ 144/1093] time: 409.8348, d_loss: 1.40197229, g_loss: 0.68496108
Epoch: [ 0] [ 145/1093] time: 412.4818, d_loss: 1.39235330, g_loss: 0.68628120
Epoch: [ 0] [ 146/1093] time: 415.1208, d_loss: 1.39973962, g_loss: 0.68124145
Epoch: [ 0] [ 147/1093] time: 417.7478, d_loss: 1.40434837, g_loss: 0.68295306
Epoch: [ 0] [ 148/1093] time: 420.3447, d_loss: 1.40103769, g_loss: 0.68351567
Epoch: [ 0] [ 149/1093] time: 423.0078, d_loss: 1.39869475, g_loss: 0.68811202
Epoch: [ 0] [ 150/1093] time: 425.6769, d_loss: 1.39448631, g_loss: 0.68543053
Epoch: [ 0] [ 151/1093] time: 428.3400, d_loss: 1.40038538, g_loss: 0.68374884
Epoch: [ 0] [ 152/1093] time: 430.9299, d_loss: 1.39607131, g_loss: 0.68607354
Epoch: [ 0] [ 153/1093] time: 433.5649, d_loss: 1.39525807, g_loss: 0.68367970
Epoch: [ 0] [ 154/1093] time: 436.1999, d_loss: 1.39335251, g_loss: 0.68305784
Epoch: [ 0] [ 155/1093] time: 438.8159, d_loss: 1.39594364, g_loss: 0.68011355
Epoch: [ 0] [ 156/1093] time: 441.4248, d_loss: 1.39486098, g_loss: 0.68195969
Epoch: [ 0] [ 157/1093] time: 443.7410, d_loss: 1.39789844, g_loss: 0.68565917
Epoch: [ 0] [ 158/1093] time: 445.9338, d_loss: 1.39793515, g_loss: 0.68732595
Epoch: [ 0] [ 159/1093] time: 448.5688, d_loss: 1.39299226, g_loss: 0.68871325
Epoch: [ 0] [ 160/1093] time: 451.2530, d_loss: 1.39738810, g_loss: 0.68969297
Epoch: [ 0] [ 161/1093] time: 453.8419, d_loss: 1.39137244, g_loss: 0.68470633
Epoch: [ 0] [ 162/1093] time: 456.4117, d_loss: 1.39432180, g_loss: 0.68399483
Epoch: [ 0] [ 163/1093] time: 459.0126, d_loss: 1.40734315, g_loss: 0.69874048
Epoch: [ 0] [ 164/1093] time: 461.6236, d_loss: 1.39966369, g_loss: 0.69043005
Epoch: [ 0] [ 165/1093] time: 464.2415, d_loss: 1.39662552, g_loss: 0.68589425
Epoch: [ 0] [ 166/1093] time: 466.8354, d_loss: 1.39980149, g_loss: 0.68546188
Epoch: [ 0] [ 167/1093] time: 469.4444, d_loss: 1.40122700, g_loss: 0.68189311
Epoch: [ 0] [ 168/1093] time: 472.0543, d_loss: 1.39967716, g_loss: 0.68801445
Epoch: [ 0] [ 169/1093] time: 474.7645, d_loss: 1.39334583, g_loss: 0.68692666
Epoch: [ 0] [ 170/1093] time: 477.8457, d_loss: 1.39654422, g_loss: 0.68602318
Epoch: [ 0] [ 171/1093] time: 481.1655, d_loss: 1.39272141, g_loss: 0.68408179
Epoch: [ 0] [ 172/1093] time: 484.7581, d_loss: 1.39280033, g_loss: 0.68730307
Epoch: [ 0] [ 173/1093] time: 488.6535, d_loss: 1.39038730, g_loss: 0.68888724
Epoch: [ 0] [ 174/1093] time: 491.6414, d_loss: 1.39102936, g_loss: 0.68783641
Epoch: [ 0] [ 175/1093] time: 494.4589, d_loss: 1.39796853, g_loss: 0.68792200
Epoch: [ 0] [ 176/1093] time: 497.3025, d_loss: 1.39714956, g_loss: 0.69051802
Epoch: [ 0] [ 177/1093] time: 500.4178, d_loss: 1.39695573, g_loss: 0.68818700
Epoch: [ 0] [ 178/1093] time: 503.3967, d_loss: 1.39812803, g_loss: 0.68710601
Epoch: [ 0] [ 179/1093] time: 505.8005, d_loss: 1.39953709, g_loss: 0.68752533
Epoch: [ 0] [ 180/1093] time: 507.9758, d_loss: 1.39834785, g_loss: 0.68958521
Epoch: [ 0] [ 181/1093] time: 510.6733, d_loss: 1.39791799, g_loss: 0.68757778
Epoch: [ 0] [ 182/1093] time: 513.5364, d_loss: 1.40238488, g_loss: 0.68668699
Epoch: [ 0] [ 183/1093] time: 516.1351, d_loss: 1.41374350, g_loss: 0.70073003
Epoch: [ 0] [ 184/1093] time: 518.9440, d_loss: 1.40326631, g_loss: 0.69215822
Epoch: [ 0] [ 185/1093] time: 521.8700, d_loss: 1.39988256, g_loss: 0.69369042
Epoch: [ 0] [ 186/1093] time: 524.7111, d_loss: 1.39754939, g_loss: 0.68646109
Epoch: [ 0] [ 187/1093] time: 527.7868, d_loss: 1.39260387, g_loss: 0.68642735
Epoch: [ 0] [ 188/1093] time: 530.4987, d_loss: 1.39920259, g_loss: 0.68960005
Epoch: [ 0] [ 189/1093] time: 533.4526, d_loss: 1.39917362, g_loss: 0.68342292
Epoch: [ 0] [ 190/1093] time: 535.9742, d_loss: 1.39696872, g_loss: 0.67972469
Epoch: [ 0] [ 191/1093] time: 538.4506, d_loss: 1.39499533, g_loss: 0.68089843
Epoch: [ 0] [ 192/1093] time: 541.1816, d_loss: 1.39483309, g_loss: 0.68199342
Epoch: [ 0] [ 193/1093] time: 544.6827, d_loss: 1.39154720, g_loss: 0.69034952
Epoch: [ 0] [ 194/1093] time: 548.6390, d_loss: 1.38941956, g_loss: 0.68652773
Epoch: [ 0] [ 195/1093] time: 551.9678, d_loss: 1.39027929, g_loss: 0.69264108
Epoch: [ 0] [ 196/1093] time: 555.3258, d_loss: 1.39162266, g_loss: 0.68833613
Epoch: [ 0] [ 197/1093] time: 558.5404, d_loss: 1.40050042, g_loss: 0.68856359
Epoch: [ 0] [ 198/1093] time: 561.3181, d_loss: 1.39854860, g_loss: 0.69332385
Epoch: [ 0] [ 199/1093] time: 563.8952, d_loss: 1.40790129, g_loss: 0.69219285
[Sample] d_loss: 1.39614487, g_loss: 0.70220172
Epoch: [ 0] [ 200/1093] time: 566.5791, d_loss: 1.39575028, g_loss: 0.68371403
Epoch: [ 0] [ 201/1093] time: 568.9093, d_loss: 1.39769495, g_loss: 0.68171024
Epoch: [ 0] [ 202/1093] time: 571.4728, d_loss: 1.40282321, g_loss: 0.67665672
Epoch: [ 0] [ 203/1093] time: 574.0684, d_loss: 1.40040171, g_loss: 0.68347836
Epoch: [ 0] [ 204/1093] time: 576.6086, d_loss: 1.40370631, g_loss: 0.67588425
Epoch: [ 0] [ 205/1093] time: 579.1860, d_loss: 1.40058494, g_loss: 0.67948377
Epoch: [ 0] [ 206/1093] time: 581.7698, d_loss: 1.40094650, g_loss: 0.68511415
Epoch: [ 0] [ 207/1093] time: 584.3541, d_loss: 1.39703560, g_loss: 0.68563807
Epoch: [ 0] [ 208/1093] time: 586.9515, d_loss: 1.39535570, g_loss: 0.69189703
Epoch: [ 0] [ 209/1093] time: 589.5623, d_loss: 1.39087117, g_loss: 0.68965638
Epoch: [ 0] [ 210/1093] time: 592.1490, d_loss: 1.39308906, g_loss: 0.68321383
Epoch: [ 0] [ 211/1093] time: 594.4484, d_loss: 1.39570045, g_loss: 0.69051659
Epoch: [ 0] [ 212/1093] time: 596.5448, d_loss: 1.39528632, g_loss: 0.68971121
Epoch: [ 0] [ 213/1093] time: 599.1007, d_loss: 1.39448357, g_loss: 0.69083250
Epoch: [ 0] [ 214/1093] time: 601.7536, d_loss: 1.39387453, g_loss: 0.68718964
Epoch: [ 0] [ 215/1093] time: 604.4539, d_loss: 1.39647603, g_loss: 0.68563658
Epoch: [ 0] [ 216/1093] time: 607.2213, d_loss: 1.39913750, g_loss: 0.68327057
Epoch: [ 0] [ 217/1093] time: 610.1400, d_loss: 1.40189719, g_loss: 0.69179547
Epoch: [ 0] [ 218/1093] time: 612.6343, d_loss: 1.39645267, g_loss: 0.68683052
Epoch: [ 0] [ 219/1093] time: 615.6275, d_loss: 1.39639115, g_loss: 0.68856508
Epoch: [ 0] [ 220/1093] time: 618.3878, d_loss: 1.39463687, g_loss: 0.68864584
Epoch: [ 0] [ 221/1093] time: 621.0520, d_loss: 1.39847159, g_loss: 0.68282092
Epoch: [ 0] [ 222/1093] time: 623.7526, d_loss: 1.39314377, g_loss: 0.68356240
Epoch: [ 0] [ 223/1093] time: 626.4487, d_loss: 1.39463484, g_loss: 0.69035685
Epoch: [ 0] [ 224/1093] time: 629.1620, d_loss: 1.39414811, g_loss: 0.68301636
Epoch: [ 0] [ 225/1093] time: 632.0214, d_loss: 1.39459169, g_loss: 0.69005007
Epoch: [ 0] [ 226/1093] time: 634.7832, d_loss: 1.39441466, g_loss: 0.69165003
Epoch: [ 0] [ 227/1093] time: 637.5516, d_loss: 1.39813066, g_loss: 0.68712354
Epoch: [ 0] [ 228/1093] time: 640.5293, d_loss: 1.39411283, g_loss: 0.68395543
Epoch: [ 0] [ 229/1093] time: 643.4174, d_loss: 1.40235329, g_loss: 0.68202847
Epoch: [ 0] [ 230/1093] time: 646.5419, d_loss: 1.40095723, g_loss: 0.69028801
Epoch: [ 0] [ 231/1093] time: 649.5546, d_loss: 1.40048647, g_loss: 0.69087422
Epoch: [ 0] [ 232/1093] time: 652.4536, d_loss: 1.39910281, g_loss: 0.68609065
Epoch: [ 0] [ 233/1093] time: 655.9317, d_loss: 1.39534748, g_loss: 0.68967736
Epoch: [ 0] [ 234/1093] time: 659.1659, d_loss: 1.39413166, g_loss: 0.69093692
Epoch: [ 0] [ 235/1093] time: 661.9449, d_loss: 1.39398015, g_loss: 0.69134909
Epoch: [ 0] [ 236/1093] time: 664.5506, d_loss: 1.39143503, g_loss: 0.68897390
Epoch: [ 0] [ 237/1093] time: 667.1299, d_loss: 1.39115989, g_loss: 0.68559802
Epoch: [ 0] [ 238/1093] time: 669.7336, d_loss: 1.39464033, g_loss: 0.68045032
Epoch: [ 0] [ 239/1093] time: 672.3397, d_loss: 1.39721715, g_loss: 0.67857778
Epoch: [ 0] [ 240/1093] time: 674.9554, d_loss: 1.39918387, g_loss: 0.68415666
Epoch: [ 0] [ 241/1093] time: 677.5424, d_loss: 1.40068483, g_loss: 0.67729497
Epoch: [ 0] [ 242/1093] time: 680.3176, d_loss: 1.40033579, g_loss: 0.68007886
Epoch: [ 0] [ 243/1093] time: 683.1003, d_loss: 1.40282607, g_loss: 0.67449147
Epoch: [ 0] [ 244/1093] time: 685.9413, d_loss: 1.40199137, g_loss: 0.68486238
Epoch: [ 0] [ 245/1093] time: 688.9759, d_loss: 1.39704895, g_loss: 0.68006516
Epoch: [ 0] [ 246/1093] time: 691.5751, d_loss: 1.39895606, g_loss: 0.68230271
Epoch: [ 0] [ 247/1093] time: 694.1042, d_loss: 1.40424132, g_loss: 0.68961239
Epoch: [ 0] [ 248/1093] time: 697.0065, d_loss: 1.39859080, g_loss: 0.68636566
Epoch: [ 0] [ 249/1093] time: 700.2469, d_loss: 1.39554536, g_loss: 0.68678790
Epoch: [ 0] [ 250/1093] time: 703.3883, d_loss: 1.39600241, g_loss: 0.68959928
Epoch: [ 0] [ 251/1093] time: 706.6261, d_loss: 1.39202178, g_loss: 0.68523437
Epoch: [ 0] [ 252/1093] time: 709.8028, d_loss: 1.39269078, g_loss: 0.69164592
Epoch: [ 0] [ 253/1093] time: 712.8928, d_loss: 1.39278984, g_loss: 0.68435776
Epoch: [ 0] [ 254/1093] time: 716.1929, d_loss: 1.39673376, g_loss: 0.68279207
Epoch: [ 0] [ 255/1093] time: 719.2671, d_loss: 1.39254975, g_loss: 0.68860251
Epoch: [ 0] [ 256/1093] time: 722.0466, d_loss: 1.39158249, g_loss: 0.68481952
Epoch: [ 0] [ 257/1093] time: 724.3691, d_loss: 1.39530706, g_loss: 0.68592030
Epoch: [ 0] [ 258/1093] time: 727.1177, d_loss: 1.39800179, g_loss: 0.68057692
Epoch: [ 0] [ 259/1093] time: 729.8695, d_loss: 1.39328969, g_loss: 0.68579948
Epoch: [ 0] [ 260/1093] time: 732.5402, d_loss: 1.39761782, g_loss: 0.67799205
Epoch: [ 0] [ 261/1093] time: 735.0255, d_loss: 1.39888024, g_loss: 0.68628734
Epoch: [ 0] [ 262/1093] time: 737.4265, d_loss: 1.39544094, g_loss: 0.68937206
Epoch: [ 0] [ 263/1093] time: 742.7211, d_loss: 1.39959955, g_loss: 0.68415856
Epoch: [ 0] [ 264/1093] time: 744.8159, d_loss: 1.40043366, g_loss: 0.67980087
Epoch: [ 0] [ 265/1093] time: 748.0739, d_loss: 1.39664960, g_loss: 0.68485308
Epoch: [ 0] [ 266/1093] time: 750.0854, d_loss: 1.40160191, g_loss: 0.68533683
Epoch: [ 0] [ 267/1093] time: 752.2763, d_loss: 1.39481544, g_loss: 0.68714094