diff --git a/OAR.2071925.stderr b/OAR.2071925.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a9c628a29c58ebc65df754dd5dfbbd99e2282b5f
--- /dev/null
+++ b/OAR.2071925.stderr
@@ -0,0 +1,2 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071925.stdout b/OAR.2071925.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..af0b94e171570c9bc101981af319553b1f2a6858
--- /dev/null
+++ b/OAR.2071925.stdout
@@ -0,0 +1,614 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='VAE_bs_64_ls_30', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=30, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=60, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=30, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 780735
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last (iter 129)'
+0/69092	Loss: 102.534
+3200/69092	Loss: 102.036
+6400/69092	Loss: 102.218
+9600/69092	Loss: 102.707
+12800/69092	Loss: 100.736
+16000/69092	Loss: 101.408
+19200/69092	Loss: 101.575
+22400/69092	Loss: 99.826
+25600/69092	Loss: 101.678
+28800/69092	Loss: 102.767
+32000/69092	Loss: 103.212
+35200/69092	Loss: 101.544
+38400/69092	Loss: 101.354
+41600/69092	Loss: 100.512
+44800/69092	Loss: 101.251
+48000/69092	Loss: 101.995
+51200/69092	Loss: 101.104
+54400/69092	Loss: 102.314
+57600/69092	Loss: 103.081
+60800/69092	Loss: 102.314
+64000/69092	Loss: 100.943
+67200/69092	Loss: 102.164
+Training time 0:13:38.847035
+Epoch: 1 Average loss: 101.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 130)
+0/69092	Loss: 114.800
+3200/69092	Loss: 101.073
+6400/69092	Loss: 100.484
+9600/69092	Loss: 100.862
+12800/69092	Loss: 101.996
+16000/69092	Loss: 101.816
+19200/69092	Loss: 99.611
+22400/69092	Loss: 102.735
+25600/69092	Loss: 100.626
+28800/69092	Loss: 101.978
+32000/69092	Loss: 103.225
+35200/69092	Loss: 103.234
+38400/69092	Loss: 102.373
+41600/69092	Loss: 102.292
+44800/69092	Loss: 101.657
+48000/69092	Loss: 102.683
+51200/69092	Loss: 101.117
+54400/69092	Loss: 101.758
+57600/69092	Loss: 100.509
+60800/69092	Loss: 103.382
+64000/69092	Loss: 101.072
+67200/69092	Loss: 102.621
+Training time 0:13:40.612847
+Epoch: 2 Average loss: 101.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 131)
+0/69092	Loss: 90.926
+3200/69092	Loss: 101.620
+6400/69092	Loss: 102.379
+9600/69092	Loss: 101.165
+12800/69092	Loss: 101.947
+16000/69092	Loss: 101.924
+19200/69092	Loss: 101.611
+22400/69092	Loss: 102.199
+25600/69092	Loss: 101.403
+28800/69092	Loss: 102.176
+32000/69092	Loss: 102.298
+35200/69092	Loss: 100.362
+38400/69092	Loss: 101.987
+41600/69092	Loss: 101.600
+44800/69092	Loss: 100.519
+48000/69092	Loss: 102.598
+51200/69092	Loss: 103.294
+54400/69092	Loss: 102.111
+57600/69092	Loss: 102.187
+60800/69092	Loss: 100.776
+64000/69092	Loss: 100.429
+67200/69092	Loss: 100.845
+Training time 0:13:42.175355
+Epoch: 3 Average loss: 101.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 132)
+0/69092	Loss: 93.964
+3200/69092	Loss: 101.516
+6400/69092	Loss: 102.362
+9600/69092	Loss: 101.001
+12800/69092	Loss: 100.701
+16000/69092	Loss: 101.798
+19200/69092	Loss: 100.819
+22400/69092	Loss: 102.256
+25600/69092	Loss: 101.712
+28800/69092	Loss: 101.544
+32000/69092	Loss: 103.227
+35200/69092	Loss: 101.216
+38400/69092	Loss: 101.431
+41600/69092	Loss: 101.230
+44800/69092	Loss: 100.323
+48000/69092	Loss: 102.344
+51200/69092	Loss: 100.128
+54400/69092	Loss: 100.639
+57600/69092	Loss: 102.672
+60800/69092	Loss: 101.396
+64000/69092	Loss: 102.506
+67200/69092	Loss: 102.220
+Training time 0:13:39.965118
+Epoch: 4 Average loss: 101.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 133)
+0/69092	Loss: 94.169
+3200/69092	Loss: 101.753
+6400/69092	Loss: 101.400
+9600/69092	Loss: 99.887
+12800/69092	Loss: 102.732
+16000/69092	Loss: 101.759
+19200/69092	Loss: 101.569
+22400/69092	Loss: 101.869
+25600/69092	Loss: 101.560
+28800/69092	Loss: 103.078
+32000/69092	Loss: 101.424
+35200/69092	Loss: 100.131
+38400/69092	Loss: 103.394
+41600/69092	Loss: 101.449
+44800/69092	Loss: 100.854
+48000/69092	Loss: 102.384
+51200/69092	Loss: 102.121
+54400/69092	Loss: 100.495
+57600/69092	Loss: 100.939
+60800/69092	Loss: 100.973
+64000/69092	Loss: 100.886
+67200/69092	Loss: 101.098
+Training time 0:13:39.968470
+Epoch: 5 Average loss: 101.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 134)
+0/69092	Loss: 102.490
+3200/69092	Loss: 101.323
+6400/69092	Loss: 100.960
+9600/69092	Loss: 101.437
+12800/69092	Loss: 103.048
+16000/69092	Loss: 100.110
+19200/69092	Loss: 102.289
+22400/69092	Loss: 101.156
+25600/69092	Loss: 102.418
+28800/69092	Loss: 102.892
+32000/69092	Loss: 101.713
+35200/69092	Loss: 102.122
+38400/69092	Loss: 101.573
+41600/69092	Loss: 102.055
+44800/69092	Loss: 101.294
+48000/69092	Loss: 101.903
+51200/69092	Loss: 101.024
+54400/69092	Loss: 101.170
+57600/69092	Loss: 101.105
+60800/69092	Loss: 99.360
+64000/69092	Loss: 100.887
+67200/69092	Loss: 100.272
+Training time 0:13:41.708014
+Epoch: 6 Average loss: 101.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 135)
+0/69092	Loss: 103.209
+3200/69092	Loss: 101.513
+6400/69092	Loss: 99.168
+9600/69092	Loss: 100.131
+12800/69092	Loss: 101.549
+16000/69092	Loss: 101.060
+19200/69092	Loss: 102.095
+22400/69092	Loss: 101.854
+25600/69092	Loss: 100.587
+28800/69092	Loss: 101.554
+32000/69092	Loss: 100.996
+35200/69092	Loss: 101.225
+38400/69092	Loss: 103.453
+41600/69092	Loss: 101.601
+44800/69092	Loss: 101.659
+48000/69092	Loss: 100.187
+51200/69092	Loss: 101.299
+54400/69092	Loss: 102.864
+57600/69092	Loss: 101.159
+60800/69092	Loss: 102.019
+64000/69092	Loss: 100.970
+67200/69092	Loss: 101.300
+Training time 0:13:32.946165
+Epoch: 7 Average loss: 101.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 136)
+0/69092	Loss: 101.395
+3200/69092	Loss: 100.712
+6400/69092	Loss: 103.126
+9600/69092	Loss: 102.173
+12800/69092	Loss: 99.536
+16000/69092	Loss: 101.181
+19200/69092	Loss: 100.161
+22400/69092	Loss: 100.936
+25600/69092	Loss: 100.097
+28800/69092	Loss: 101.380
+32000/69092	Loss: 101.109
+35200/69092	Loss: 101.755
+38400/69092	Loss: 100.048
+41600/69092	Loss: 102.796
+44800/69092	Loss: 101.363
+48000/69092	Loss: 102.326
+51200/69092	Loss: 102.086
+54400/69092	Loss: 102.963
+57600/69092	Loss: 103.234
+60800/69092	Loss: 101.840
+64000/69092	Loss: 100.346
+67200/69092	Loss: 100.669
+Training time 0:13:37.533460
+Epoch: 8 Average loss: 101.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 137)
+0/69092	Loss: 97.749
+3200/69092	Loss: 101.572
+6400/69092	Loss: 102.015
+9600/69092	Loss: 100.706
+12800/69092	Loss: 100.540
+16000/69092	Loss: 101.968
+19200/69092	Loss: 100.329
+22400/69092	Loss: 102.381
+25600/69092	Loss: 101.223
+28800/69092	Loss: 101.436
+32000/69092	Loss: 101.072
+35200/69092	Loss: 100.891
+38400/69092	Loss: 100.335
+41600/69092	Loss: 100.955
+44800/69092	Loss: 101.962
+48000/69092	Loss: 101.707
+51200/69092	Loss: 101.662
+54400/69092	Loss: 101.518
+57600/69092	Loss: 101.136
+60800/69092	Loss: 99.977
+64000/69092	Loss: 100.367
+67200/69092	Loss: 102.240
+Training time 0:13:37.159430
+Epoch: 9 Average loss: 101.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 138)
+0/69092	Loss: 96.843
+3200/69092	Loss: 100.628
+6400/69092	Loss: 98.623
+9600/69092	Loss: 101.173
+12800/69092	Loss: 101.865
+16000/69092	Loss: 100.244
+19200/69092	Loss: 103.324
+22400/69092	Loss: 100.510
+25600/69092	Loss: 100.481
+28800/69092	Loss: 100.251
+32000/69092	Loss: 100.785
+35200/69092	Loss: 102.649
+38400/69092	Loss: 100.703
+41600/69092	Loss: 101.355
+44800/69092	Loss: 102.376
+48000/69092	Loss: 103.408
+51200/69092	Loss: 101.330
+54400/69092	Loss: 101.807
+57600/69092	Loss: 101.790
+60800/69092	Loss: 101.363
+64000/69092	Loss: 102.553
+67200/69092	Loss: 100.505
+Training time 0:13:45.293890
+Epoch: 10 Average loss: 101.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 139)
+0/69092	Loss: 112.161
+3200/69092	Loss: 101.777
+6400/69092	Loss: 100.855
+9600/69092	Loss: 101.773
+12800/69092	Loss: 102.093
+16000/69092	Loss: 100.143
+19200/69092	Loss: 100.434
+22400/69092	Loss: 102.122
+25600/69092	Loss: 102.210
+28800/69092	Loss: 99.864
+32000/69092	Loss: 102.064
+35200/69092	Loss: 101.566
+38400/69092	Loss: 101.978
+41600/69092	Loss: 100.993
+44800/69092	Loss: 101.276
+48000/69092	Loss: 102.266
+51200/69092	Loss: 102.357
+54400/69092	Loss: 101.238
+57600/69092	Loss: 98.933
+60800/69092	Loss: 100.897
+64000/69092	Loss: 100.563
+67200/69092	Loss: 102.239
+Training time 0:13:47.168059
+Epoch: 11 Average loss: 101.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 140)
+0/69092	Loss: 110.515
+3200/69092	Loss: 101.177
+6400/69092	Loss: 100.226
+9600/69092	Loss: 101.056
+12800/69092	Loss: 101.302
+16000/69092	Loss: 99.309
+19200/69092	Loss: 101.269
+22400/69092	Loss: 102.534
+25600/69092	Loss: 101.872
+28800/69092	Loss: 101.718
+32000/69092	Loss: 102.067
+35200/69092	Loss: 102.550
+38400/69092	Loss: 101.435
+41600/69092	Loss: 101.267
+44800/69092	Loss: 100.383
+48000/69092	Loss: 100.301
+51200/69092	Loss: 99.972
+54400/69092	Loss: 102.224
+57600/69092	Loss: 102.747
+60800/69092	Loss: 100.852
+64000/69092	Loss: 100.935
+67200/69092	Loss: 100.921
+Training time 0:13:35.979609
+Epoch: 12 Average loss: 101.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 141)
+0/69092	Loss: 104.926
+3200/69092	Loss: 101.516
+6400/69092	Loss: 102.450
+9600/69092	Loss: 101.628
+12800/69092	Loss: 100.340
+16000/69092	Loss: 102.149
+19200/69092	Loss: 100.950
+22400/69092	Loss: 100.328
+25600/69092	Loss: 102.320
+28800/69092	Loss: 101.453
+32000/69092	Loss: 100.098
+35200/69092	Loss: 101.167
+38400/69092	Loss: 102.012
+41600/69092	Loss: 101.536
+44800/69092	Loss: 102.023
+48000/69092	Loss: 99.752
+51200/69092	Loss: 99.400
+54400/69092	Loss: 100.739
+57600/69092	Loss: 99.739
+60800/69092	Loss: 100.977
+64000/69092	Loss: 101.560
+67200/69092	Loss: 102.735
+Training time 0:13:36.534861
+Epoch: 13 Average loss: 101.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 142)
+0/69092	Loss: 101.172
+3200/69092	Loss: 101.438
+6400/69092	Loss: 102.836
+9600/69092	Loss: 100.026
+12800/69092	Loss: 101.309
+16000/69092	Loss: 101.171
+19200/69092	Loss: 100.645
+22400/69092	Loss: 100.532
+25600/69092	Loss: 100.822
+28800/69092	Loss: 100.009
+32000/69092	Loss: 101.301
+35200/69092	Loss: 100.742
+38400/69092	Loss: 101.677
+41600/69092	Loss: 101.701
+44800/69092	Loss: 103.015
+48000/69092	Loss: 102.149
+51200/69092	Loss: 100.553
+54400/69092	Loss: 101.219
+57600/69092	Loss: 101.769
+60800/69092	Loss: 100.160
+64000/69092	Loss: 102.333
+67200/69092	Loss: 101.800
+Training time 0:13:37.293015
+Epoch: 14 Average loss: 101.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 143)
+0/69092	Loss: 108.805
+3200/69092	Loss: 100.707
+6400/69092	Loss: 100.088
+9600/69092	Loss: 101.559
+12800/69092	Loss: 101.380
+16000/69092	Loss: 101.018
+19200/69092	Loss: 100.826
+22400/69092	Loss: 101.537
+25600/69092	Loss: 100.539
+28800/69092	Loss: 100.839
+32000/69092	Loss: 100.947
+35200/69092	Loss: 102.349
+38400/69092	Loss: 100.047
+41600/69092	Loss: 101.840
+44800/69092	Loss: 100.186
+48000/69092	Loss: 102.917
+51200/69092	Loss: 101.335
+54400/69092	Loss: 101.732
+57600/69092	Loss: 99.359
+60800/69092	Loss: 99.792
+64000/69092	Loss: 101.038
+67200/69092	Loss: 100.563
+Training time 0:13:38.617665
+Epoch: 15 Average loss: 101.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 144)
+0/69092	Loss: 103.428
+3200/69092	Loss: 102.019
+6400/69092	Loss: 101.325
+9600/69092	Loss: 102.409
+12800/69092	Loss: 100.924
+16000/69092	Loss: 101.393
+19200/69092	Loss: 99.708
+22400/69092	Loss: 101.004
+25600/69092	Loss: 100.803
+28800/69092	Loss: 102.168
+32000/69092	Loss: 98.200
+35200/69092	Loss: 102.215
+38400/69092	Loss: 102.296
+41600/69092	Loss: 101.760
+44800/69092	Loss: 100.265
+48000/69092	Loss: 99.268
+51200/69092	Loss: 100.277
+54400/69092	Loss: 102.682
+57600/69092	Loss: 101.112
+60800/69092	Loss: 101.129
+64000/69092	Loss: 101.590
+67200/69092	Loss: 100.514
+Training time 0:13:36.266593
+Epoch: 16 Average loss: 101.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 145)
+0/69092	Loss: 102.075
+3200/69092	Loss: 101.324
+6400/69092	Loss: 100.904
+9600/69092	Loss: 100.849
+12800/69092	Loss: 101.884
+16000/69092	Loss: 100.862
+19200/69092	Loss: 101.149
+22400/69092	Loss: 101.627
+25600/69092	Loss: 100.603
+28800/69092	Loss: 100.834
+32000/69092	Loss: 101.490
+35200/69092	Loss: 99.884
+38400/69092	Loss: 102.170
+41600/69092	Loss: 100.476
+44800/69092	Loss: 100.072
+48000/69092	Loss: 100.504
+51200/69092	Loss: 101.009
+54400/69092	Loss: 99.449
+57600/69092	Loss: 102.071
+60800/69092	Loss: 101.257
+64000/69092	Loss: 101.457
+67200/69092	Loss: 100.634
+Training time 0:13:44.392443
+Epoch: 17 Average loss: 101.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 146)
+0/69092	Loss: 102.443
+3200/69092	Loss: 101.318
+6400/69092	Loss: 103.426
+9600/69092	Loss: 102.822
+12800/69092	Loss: 101.628
+16000/69092	Loss: 101.508
+19200/69092	Loss: 101.354
+22400/69092	Loss: 101.734
+25600/69092	Loss: 101.245
+28800/69092	Loss: 99.157
+32000/69092	Loss: 101.736
+35200/69092	Loss: 101.405
+38400/69092	Loss: 99.550
+41600/69092	Loss: 100.731
+44800/69092	Loss: 102.071
+48000/69092	Loss: 101.316
+51200/69092	Loss: 101.294
+54400/69092	Loss: 100.452
+57600/69092	Loss: 100.354
+60800/69092	Loss: 101.136
+64000/69092	Loss: 100.233
+67200/69092	Loss: 101.333
+Training time 0:13:40.917111
+Epoch: 18 Average loss: 101.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 147)
+0/69092	Loss: 96.744
+3200/69092	Loss: 101.016
+6400/69092	Loss: 100.818
+9600/69092	Loss: 100.498
+12800/69092	Loss: 101.251
+16000/69092	Loss: 100.795
+19200/69092	Loss: 101.181
+22400/69092	Loss: 102.624
+25600/69092	Loss: 100.103
+28800/69092	Loss: 102.347
+32000/69092	Loss: 98.818
+35200/69092	Loss: 102.360
+38400/69092	Loss: 102.031
+41600/69092	Loss: 100.385
+44800/69092	Loss: 100.641
+48000/69092	Loss: 101.366
+51200/69092	Loss: 101.084
+54400/69092	Loss: 100.710
+57600/69092	Loss: 101.880
+60800/69092	Loss: 100.524
+64000/69092	Loss: 100.779
+67200/69092	Loss: 101.739
+Training time 0:13:39.137368
+Epoch: 19 Average loss: 101.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 148)
+0/69092	Loss: 110.795
+3200/69092	Loss: 100.172
+6400/69092	Loss: 100.835
+9600/69092	Loss: 102.914
+12800/69092	Loss: 100.496
+16000/69092	Loss: 99.775
+19200/69092	Loss: 101.589
+22400/69092	Loss: 101.415
+25600/69092	Loss: 100.814
+28800/69092	Loss: 101.546
+32000/69092	Loss: 100.133
+35200/69092	Loss: 100.845
+38400/69092	Loss: 101.924
+41600/69092	Loss: 102.358
+44800/69092	Loss: 102.181
+48000/69092	Loss: 99.168
+51200/69092	Loss: 102.921
+54400/69092	Loss: 99.917
+57600/69092	Loss: 99.900
+60800/69092	Loss: 99.359
+64000/69092	Loss: 102.033
+67200/69092	Loss: 101.576
+Training time 0:13:41.223759
+Epoch: 20 Average loss: 101.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 149)
+0/69092	Loss: 95.958
+3200/69092	Loss: 99.846
+6400/69092	Loss: 101.695
+9600/69092	Loss: 101.363
+12800/69092	Loss: 101.017
+16000/69092	Loss: 101.406
+19200/69092	Loss: 100.208
+22400/69092	Loss: 100.811
+25600/69092	Loss: 102.059
+28800/69092	Loss: 100.063
+32000/69092	Loss: 101.056
+35200/69092	Loss: 99.961
+38400/69092	Loss: 101.395
+41600/69092	Loss: 100.612
+44800/69092	Loss: 101.276
+48000/69092	Loss: 100.546
+51200/69092	Loss: 101.843
+54400/69092	Loss: 101.545
+57600/69092	Loss: 101.428
+60800/69092	Loss: 102.501
+64000/69092	Loss: 102.094
+67200/69092	Loss: 102.237
+Training time 0:13:38.211588
+Epoch: 21 Average loss: 101.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 150)
+0/69092	Loss: 97.744
+3200/69092	Loss: 98.888
+6400/69092	Loss: 100.604
+9600/69092	Loss: 100.722
+12800/69092	Loss: 100.720
+16000/69092	Loss: 101.149
+19200/69092	Loss: 100.248
+22400/69092	Loss: 100.703
+25600/69092	Loss: 101.915
+28800/69092	Loss: 103.134
+32000/69092	Loss: 102.218
+35200/69092	Loss: 100.886
+38400/69092	Loss: 100.174
+41600/69092	Loss: 102.200
+44800/69092	Loss: 100.549
+48000/69092	Loss: 101.682
+51200/69092	Loss: 101.382
+54400/69092	Loss: 100.393
+57600/69092	Loss: 99.708
+60800/69092	Loss: 99.162
+64000/69092	Loss: 101.203
+67200/69092	Loss: 101.223
+Training time 0:13:38.859805
+Epoch: 22 Average loss: 100.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 151)
+0/69092	Loss: 104.809
+3200/69092	Loss: 100.932
+6400/69092	Loss: 101.622
+9600/69092	Loss: 101.292
+12800/69092	Loss: 102.105
+16000/69092	Loss: 100.229
+19200/69092	Loss: 99.238
+22400/69092	Loss: 100.010
+25600/69092	Loss: 99.492
+28800/69092	Loss: 102.281
+32000/69092	Loss: 101.187
+35200/69092	Loss: 101.881
+38400/69092	Loss: 101.507
+41600/69092	Loss: 99.676
+44800/69092	Loss: 100.538
+48000/69092	Loss: 99.951
+51200/69092	Loss: 103.184
diff --git a/OAR.2071926.stderr b/OAR.2071926.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..3fa38d97833abb3d5f736549b02733f2cf4af075
--- /dev/null
+++ b/OAR.2071926.stderr
@@ -0,0 +1,8 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071926.stdout b/OAR.2071926.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..60f9a19ef929affaa4ce598008f60b7bfd567872
--- /dev/null
+++ b/OAR.2071926.stdout
@@ -0,0 +1,1050 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='VAE_bs_64_ls_40', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=40, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=80, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=40, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 788435
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last (iter 239)'
+0/69092	Loss: 107.115
+3200/69092	Loss: 96.144
+6400/69092	Loss: 94.953
+9600/69092	Loss: 93.092
+12800/69092	Loss: 94.239
+16000/69092	Loss: 95.661
+19200/69092	Loss: 96.719
+22400/69092	Loss: 93.757
+25600/69092	Loss: 95.639
+28800/69092	Loss: 94.715
+32000/69092	Loss: 94.777
+35200/69092	Loss: 94.920
+38400/69092	Loss: 95.831
+41600/69092	Loss: 93.925
+44800/69092	Loss: 95.380
+48000/69092	Loss: 94.872
+51200/69092	Loss: 94.707
+54400/69092	Loss: 96.006
+57600/69092	Loss: 93.720
+60800/69092	Loss: 95.304
+64000/69092	Loss: 94.826
+67200/69092	Loss: 94.861
+Training time 0:07:50.791595
+Epoch: 1 Average loss: 94.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 240)
+0/69092	Loss: 88.184
+3200/69092	Loss: 95.239
+6400/69092	Loss: 95.823
+9600/69092	Loss: 96.482
+12800/69092	Loss: 94.365
+16000/69092	Loss: 94.666
+19200/69092	Loss: 94.810
+22400/69092	Loss: 94.448
+25600/69092	Loss: 94.133
+28800/69092	Loss: 93.688
+32000/69092	Loss: 95.754
+35200/69092	Loss: 93.416
+38400/69092	Loss: 95.240
+41600/69092	Loss: 95.343
+44800/69092	Loss: 94.340
+48000/69092	Loss: 95.801
+51200/69092	Loss: 93.977
+54400/69092	Loss: 94.068
+57600/69092	Loss: 95.123
+60800/69092	Loss: 94.618
+64000/69092	Loss: 94.918
+67200/69092	Loss: 94.817
+Training time 0:07:41.487764
+Epoch: 2 Average loss: 94.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 241)
+0/69092	Loss: 91.296
+3200/69092	Loss: 93.777
+6400/69092	Loss: 94.320
+9600/69092	Loss: 94.114
+12800/69092	Loss: 94.358
+16000/69092	Loss: 95.152
+19200/69092	Loss: 93.773
+22400/69092	Loss: 96.712
+25600/69092	Loss: 94.708
+28800/69092	Loss: 93.869
+32000/69092	Loss: 94.225
+35200/69092	Loss: 94.478
+38400/69092	Loss: 94.703
+41600/69092	Loss: 93.975
+44800/69092	Loss: 96.143
+48000/69092	Loss: 96.074
+51200/69092	Loss: 95.269
+54400/69092	Loss: 95.887
+57600/69092	Loss: 94.271
+60800/69092	Loss: 95.953
+64000/69092	Loss: 95.280
+67200/69092	Loss: 94.895
+Training time 0:07:36.187335
+Epoch: 3 Average loss: 94.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 242)
+0/69092	Loss: 95.492
+3200/69092	Loss: 93.854
+6400/69092	Loss: 93.991
+9600/69092	Loss: 95.113
+12800/69092	Loss: 94.993
+16000/69092	Loss: 94.576
+19200/69092	Loss: 96.490
+22400/69092	Loss: 94.842
+25600/69092	Loss: 93.689
+28800/69092	Loss: 94.116
+32000/69092	Loss: 96.230
+35200/69092	Loss: 95.289
+38400/69092	Loss: 95.706
+41600/69092	Loss: 95.148
+44800/69092	Loss: 95.772
+48000/69092	Loss: 95.783
+51200/69092	Loss: 94.778
+54400/69092	Loss: 95.549
+57600/69092	Loss: 93.751
+60800/69092	Loss: 95.438
+64000/69092	Loss: 92.468
+67200/69092	Loss: 94.668
+Training time 0:07:34.470143
+Epoch: 4 Average loss: 94.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 243)
+0/69092	Loss: 96.341
+3200/69092	Loss: 94.349
+6400/69092	Loss: 94.858
+9600/69092	Loss: 94.632
+12800/69092	Loss: 94.771
+16000/69092	Loss: 95.489
+19200/69092	Loss: 94.117
+22400/69092	Loss: 95.811
+25600/69092	Loss: 95.329
+28800/69092	Loss: 94.223
+32000/69092	Loss: 95.555
+35200/69092	Loss: 95.143
+38400/69092	Loss: 93.479
+41600/69092	Loss: 95.180
+44800/69092	Loss: 95.523
+48000/69092	Loss: 95.209
+51200/69092	Loss: 94.912
+54400/69092	Loss: 94.412
+57600/69092	Loss: 93.693
+60800/69092	Loss: 94.666
+64000/69092	Loss: 94.290
+67200/69092	Loss: 94.244
+Training time 0:07:31.288607
+Epoch: 5 Average loss: 94.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 244)
+0/69092	Loss: 100.813
+3200/69092	Loss: 94.317
+6400/69092	Loss: 94.578
+9600/69092	Loss: 95.588
+12800/69092	Loss: 93.439
+16000/69092	Loss: 96.193
+19200/69092	Loss: 94.873
+22400/69092	Loss: 94.870
+25600/69092	Loss: 94.276
+28800/69092	Loss: 94.297
+32000/69092	Loss: 94.598
+35200/69092	Loss: 92.408
+38400/69092	Loss: 95.609
+41600/69092	Loss: 94.230
+44800/69092	Loss: 95.950
+48000/69092	Loss: 95.544
+51200/69092	Loss: 97.070
+54400/69092	Loss: 93.768
+57600/69092	Loss: 95.706
+60800/69092	Loss: 94.584
+64000/69092	Loss: 94.515
+67200/69092	Loss: 93.712
+Training time 0:07:40.407501
+Epoch: 6 Average loss: 94.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 245)
+0/69092	Loss: 84.678
+3200/69092	Loss: 94.838
+6400/69092	Loss: 93.629
+9600/69092	Loss: 96.019
+12800/69092	Loss: 94.610
+16000/69092	Loss: 95.538
+19200/69092	Loss: 94.371
+22400/69092	Loss: 95.503
+25600/69092	Loss: 95.000
+28800/69092	Loss: 94.244
+32000/69092	Loss: 94.539
+35200/69092	Loss: 94.524
+38400/69092	Loss: 94.806
+41600/69092	Loss: 94.387
+44800/69092	Loss: 93.409
+48000/69092	Loss: 93.685
+51200/69092	Loss: 94.124
+54400/69092	Loss: 95.382
+57600/69092	Loss: 94.497
+60800/69092	Loss: 94.849
+64000/69092	Loss: 94.038
+67200/69092	Loss: 94.939
+Training time 0:07:37.721995
+Epoch: 7 Average loss: 94.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 246)
+0/69092	Loss: 89.671
+3200/69092	Loss: 94.643
+6400/69092	Loss: 94.845
+9600/69092	Loss: 95.375
+12800/69092	Loss: 94.272
+16000/69092	Loss: 94.186
+19200/69092	Loss: 92.535
+22400/69092	Loss: 95.824
+25600/69092	Loss: 95.247
+28800/69092	Loss: 94.298
+32000/69092	Loss: 94.496
+35200/69092	Loss: 95.532
+38400/69092	Loss: 94.614
+41600/69092	Loss: 95.700
+44800/69092	Loss: 95.332
+48000/69092	Loss: 94.459
+51200/69092	Loss: 94.370
+54400/69092	Loss: 94.947
+57600/69092	Loss: 92.311
+60800/69092	Loss: 95.635
+64000/69092	Loss: 95.287
+67200/69092	Loss: 96.058
+Training time 0:07:35.909222
+Epoch: 8 Average loss: 94.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 247)
+0/69092	Loss: 100.903
+3200/69092	Loss: 94.753
+6400/69092	Loss: 95.036
+9600/69092	Loss: 93.688
+12800/69092	Loss: 94.177
+16000/69092	Loss: 94.756
+19200/69092	Loss: 94.085
+22400/69092	Loss: 94.164
+25600/69092	Loss: 94.147
+28800/69092	Loss: 94.651
+32000/69092	Loss: 95.327
+35200/69092	Loss: 95.869
+38400/69092	Loss: 95.395
+41600/69092	Loss: 94.101
+44800/69092	Loss: 93.981
+48000/69092	Loss: 94.858
+51200/69092	Loss: 94.705
+54400/69092	Loss: 95.636
+57600/69092	Loss: 95.710
+60800/69092	Loss: 93.323
+64000/69092	Loss: 96.510
+67200/69092	Loss: 93.088
+Training time 0:07:37.958332
+Epoch: 9 Average loss: 94.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 248)
+0/69092	Loss: 98.991
+3200/69092	Loss: 93.498
+6400/69092	Loss: 95.857
+9600/69092	Loss: 93.504
+12800/69092	Loss: 93.981
+16000/69092	Loss: 93.482
+19200/69092	Loss: 95.759
+22400/69092	Loss: 95.438
+25600/69092	Loss: 94.804
+28800/69092	Loss: 94.057
+32000/69092	Loss: 95.488
+35200/69092	Loss: 94.579
+38400/69092	Loss: 93.834
+41600/69092	Loss: 93.938
+44800/69092	Loss: 96.286
+48000/69092	Loss: 95.217
+51200/69092	Loss: 93.604
+54400/69092	Loss: 94.940
+57600/69092	Loss: 95.563
+60800/69092	Loss: 94.343
+64000/69092	Loss: 95.703
+67200/69092	Loss: 93.698
+Training time 0:07:34.264781
+Epoch: 10 Average loss: 94.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 249)
+0/69092	Loss: 96.338
+3200/69092	Loss: 94.590
+6400/69092	Loss: 94.183
+9600/69092	Loss: 94.754
+12800/69092	Loss: 94.780
+16000/69092	Loss: 95.641
+19200/69092	Loss: 93.974
+22400/69092	Loss: 95.738
+25600/69092	Loss: 94.854
+28800/69092	Loss: 94.071
+32000/69092	Loss: 95.264
+35200/69092	Loss: 94.423
+38400/69092	Loss: 94.114
+41600/69092	Loss: 95.172
+44800/69092	Loss: 94.337
+48000/69092	Loss: 95.276
+51200/69092	Loss: 94.170
+54400/69092	Loss: 93.907
+57600/69092	Loss: 95.703
+60800/69092	Loss: 93.719
+64000/69092	Loss: 93.856
+67200/69092	Loss: 95.361
+Training time 0:07:33.702575
+Epoch: 11 Average loss: 94.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 250)
+0/69092	Loss: 100.942
+3200/69092	Loss: 93.738
+6400/69092	Loss: 94.480
+9600/69092	Loss: 94.316
+12800/69092	Loss: 94.968
+16000/69092	Loss: 94.243
+19200/69092	Loss: 95.541
+22400/69092	Loss: 95.174
+25600/69092	Loss: 94.635
+28800/69092	Loss: 95.222
+32000/69092	Loss: 95.156
+35200/69092	Loss: 94.535
+38400/69092	Loss: 94.693
+41600/69092	Loss: 93.758
+44800/69092	Loss: 95.036
+48000/69092	Loss: 94.345
+51200/69092	Loss: 93.736
+54400/69092	Loss: 95.426
+57600/69092	Loss: 94.698
+60800/69092	Loss: 95.613
+64000/69092	Loss: 94.012
+67200/69092	Loss: 94.687
+Training time 0:07:45.223018
+Epoch: 12 Average loss: 94.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 251)
+0/69092	Loss: 90.434
+3200/69092	Loss: 94.635
+6400/69092	Loss: 94.848
+9600/69092	Loss: 96.252
+12800/69092	Loss: 93.579
+16000/69092	Loss: 93.772
+19200/69092	Loss: 94.314
+22400/69092	Loss: 95.190
+25600/69092	Loss: 94.962
+28800/69092	Loss: 95.252
+32000/69092	Loss: 95.202
+35200/69092	Loss: 94.123
+38400/69092	Loss: 95.166
+41600/69092	Loss: 95.511
+44800/69092	Loss: 93.693
+48000/69092	Loss: 94.801
+51200/69092	Loss: 94.598
+54400/69092	Loss: 95.383
+57600/69092	Loss: 94.257
+60800/69092	Loss: 94.973
+64000/69092	Loss: 93.321
+67200/69092	Loss: 93.447
+Training time 0:07:52.187914
+Epoch: 13 Average loss: 94.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 252)
+0/69092	Loss: 85.430
+3200/69092	Loss: 94.940
+6400/69092	Loss: 95.067
+9600/69092	Loss: 94.559
+12800/69092	Loss: 94.629
+16000/69092	Loss: 95.475
+19200/69092	Loss: 93.454
+22400/69092	Loss: 94.783
+25600/69092	Loss: 94.548
+28800/69092	Loss: 94.813
+32000/69092	Loss: 95.987
+35200/69092	Loss: 95.610
+38400/69092	Loss: 93.338
+41600/69092	Loss: 95.800
+44800/69092	Loss: 95.104
+48000/69092	Loss: 95.476
+51200/69092	Loss: 93.797
+54400/69092	Loss: 93.919
+57600/69092	Loss: 94.411
+60800/69092	Loss: 94.585
+64000/69092	Loss: 94.856
+67200/69092	Loss: 94.021
+Training time 0:07:49.779707
+Epoch: 14 Average loss: 94.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 253)
+0/69092	Loss: 95.120
+3200/69092	Loss: 94.783
+6400/69092	Loss: 93.848
+9600/69092	Loss: 94.201
+12800/69092	Loss: 94.406
+16000/69092	Loss: 95.225
+19200/69092	Loss: 94.874
+22400/69092	Loss: 94.254
+25600/69092	Loss: 94.114
+28800/69092	Loss: 93.878
+32000/69092	Loss: 95.399
+35200/69092	Loss: 94.656
+38400/69092	Loss: 94.471
+41600/69092	Loss: 94.607
+44800/69092	Loss: 93.156
+48000/69092	Loss: 94.416
+51200/69092	Loss: 94.910
+54400/69092	Loss: 93.830
+57600/69092	Loss: 94.580
+60800/69092	Loss: 93.446
+64000/69092	Loss: 95.133
+67200/69092	Loss: 95.964
+Training time 0:07:40.646446
+Epoch: 15 Average loss: 94.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 254)
+0/69092	Loss: 86.913
+3200/69092	Loss: 94.085
+6400/69092	Loss: 94.676
+9600/69092	Loss: 96.533
+12800/69092	Loss: 94.517
+16000/69092	Loss: 94.314
+19200/69092	Loss: 94.220
+22400/69092	Loss: 94.264
+25600/69092	Loss: 92.935
+28800/69092	Loss: 94.763
+32000/69092	Loss: 94.426
+35200/69092	Loss: 94.177
+38400/69092	Loss: 95.931
+41600/69092	Loss: 95.531
+44800/69092	Loss: 93.417
+48000/69092	Loss: 93.912
+51200/69092	Loss: 94.897
+54400/69092	Loss: 94.307
+57600/69092	Loss: 94.409
+60800/69092	Loss: 94.410
+64000/69092	Loss: 94.081
+67200/69092	Loss: 95.346
+Training time 0:07:36.018561
+Epoch: 16 Average loss: 94.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 255)
+0/69092	Loss: 96.777
+3200/69092	Loss: 94.232
+6400/69092	Loss: 94.977
+9600/69092	Loss: 94.023
+12800/69092	Loss: 95.017
+16000/69092	Loss: 93.906
+19200/69092	Loss: 94.546
+22400/69092	Loss: 94.468
+25600/69092	Loss: 95.171
+28800/69092	Loss: 93.640
+32000/69092	Loss: 94.658
+35200/69092	Loss: 95.302
+38400/69092	Loss: 94.736
+41600/69092	Loss: 93.309
+44800/69092	Loss: 95.051
+48000/69092	Loss: 94.710
+51200/69092	Loss: 93.588
+54400/69092	Loss: 95.197
+57600/69092	Loss: 94.820
+60800/69092	Loss: 93.350
+64000/69092	Loss: 94.439
+67200/69092	Loss: 95.510
+Training time 0:07:37.855103
+Epoch: 17 Average loss: 94.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 256)
+0/69092	Loss: 101.684
+3200/69092	Loss: 94.559
+6400/69092	Loss: 94.739
+9600/69092	Loss: 95.764
+12800/69092	Loss: 93.370
+16000/69092	Loss: 94.570
+19200/69092	Loss: 95.003
+22400/69092	Loss: 93.765
+25600/69092	Loss: 94.356
+28800/69092	Loss: 94.998
+32000/69092	Loss: 94.055
+35200/69092	Loss: 93.653
+38400/69092	Loss: 94.553
+41600/69092	Loss: 93.680
+44800/69092	Loss: 95.310
+48000/69092	Loss: 93.775
+51200/69092	Loss: 91.700
+54400/69092	Loss: 95.288
+57600/69092	Loss: 94.939
+60800/69092	Loss: 95.419
+64000/69092	Loss: 95.868
+67200/69092	Loss: 94.779
+Training time 0:07:37.858746
+Epoch: 18 Average loss: 94.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 257)
+0/69092	Loss: 96.910
+3200/69092	Loss: 95.853
+6400/69092	Loss: 94.429
+9600/69092	Loss: 94.754
+12800/69092	Loss: 93.127
+16000/69092	Loss: 93.772
+19200/69092	Loss: 94.906
+22400/69092	Loss: 95.004
+25600/69092	Loss: 94.717
+28800/69092	Loss: 95.597
+32000/69092	Loss: 95.501
+35200/69092	Loss: 94.846
+38400/69092	Loss: 94.447
+41600/69092	Loss: 93.667
+44800/69092	Loss: 93.858
+48000/69092	Loss: 93.926
+51200/69092	Loss: 94.066
+54400/69092	Loss: 94.172
+57600/69092	Loss: 93.810
+60800/69092	Loss: 93.445
+64000/69092	Loss: 94.430
+67200/69092	Loss: 95.836
+Training time 0:07:37.058295
+Epoch: 19 Average loss: 94.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 258)
+0/69092	Loss: 98.137
+3200/69092	Loss: 95.687
+6400/69092	Loss: 93.072
+9600/69092	Loss: 92.561
+12800/69092	Loss: 95.054
+16000/69092	Loss: 95.547
+19200/69092	Loss: 94.516
+22400/69092	Loss: 94.784
+25600/69092	Loss: 94.360
+28800/69092	Loss: 94.958
+32000/69092	Loss: 93.761
+35200/69092	Loss: 95.370
+38400/69092	Loss: 94.824
+41600/69092	Loss: 95.439
+44800/69092	Loss: 94.956
+48000/69092	Loss: 94.107
+51200/69092	Loss: 93.872
+54400/69092	Loss: 94.252
+57600/69092	Loss: 94.347
+60800/69092	Loss: 94.054
+64000/69092	Loss: 94.425
+67200/69092	Loss: 93.218
+Training time 0:07:39.688092
+Epoch: 20 Average loss: 94.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 259)
+0/69092	Loss: 86.177
+3200/69092	Loss: 93.400
+6400/69092	Loss: 94.399
+9600/69092	Loss: 95.195
+12800/69092	Loss: 94.801
+16000/69092	Loss: 94.270
+19200/69092	Loss: 93.821
+22400/69092	Loss: 93.997
+25600/69092	Loss: 94.577
+28800/69092	Loss: 94.196
+32000/69092	Loss: 95.066
+35200/69092	Loss: 94.995
+38400/69092	Loss: 94.059
+41600/69092	Loss: 94.573
+44800/69092	Loss: 93.481
+48000/69092	Loss: 95.030
+51200/69092	Loss: 95.501
+54400/69092	Loss: 94.967
+57600/69092	Loss: 94.556
+60800/69092	Loss: 94.177
+64000/69092	Loss: 95.666
+67200/69092	Loss: 94.133
+Training time 0:07:43.573102
+Epoch: 21 Average loss: 94.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 260)
+0/69092	Loss: 99.793
+3200/69092	Loss: 94.147
+6400/69092	Loss: 95.434
+9600/69092	Loss: 95.217
+12800/69092	Loss: 94.321
+16000/69092	Loss: 95.361
+19200/69092	Loss: 94.131
+22400/69092	Loss: 93.712
+25600/69092	Loss: 94.402
+28800/69092	Loss: 94.374
+32000/69092	Loss: 93.928
+35200/69092	Loss: 93.980
+38400/69092	Loss: 93.457
+41600/69092	Loss: 94.467
+44800/69092	Loss: 94.433
+48000/69092	Loss: 94.036
+51200/69092	Loss: 95.764
+54400/69092	Loss: 95.252
+57600/69092	Loss: 93.298
+60800/69092	Loss: 94.516
+64000/69092	Loss: 94.321
+67200/69092	Loss: 96.485
+Training time 0:07:45.702914
+Epoch: 22 Average loss: 94.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 261)
+0/69092	Loss: 91.129
+3200/69092	Loss: 94.574
+6400/69092	Loss: 94.748
+9600/69092	Loss: 93.301
+12800/69092	Loss: 94.842
+16000/69092	Loss: 93.721
+19200/69092	Loss: 96.039
+22400/69092	Loss: 94.234
+25600/69092	Loss: 94.628
+28800/69092	Loss: 94.492
+32000/69092	Loss: 94.608
+35200/69092	Loss: 94.682
+38400/69092	Loss: 94.898
+41600/69092	Loss: 94.128
+44800/69092	Loss: 93.289
+48000/69092	Loss: 94.227
+51200/69092	Loss: 95.205
+54400/69092	Loss: 95.398
+57600/69092	Loss: 93.717
+60800/69092	Loss: 94.521
+64000/69092	Loss: 94.331
+67200/69092	Loss: 94.194
+Training time 0:07:37.814544
+Epoch: 23 Average loss: 94.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 262)
+0/69092	Loss: 100.275
+3200/69092	Loss: 93.559
+6400/69092	Loss: 93.706
+9600/69092	Loss: 94.569
+12800/69092	Loss: 94.809
+16000/69092	Loss: 93.883
+19200/69092	Loss: 95.446
+22400/69092	Loss: 94.435
+25600/69092	Loss: 93.197
+28800/69092	Loss: 94.484
+32000/69092	Loss: 93.676
+35200/69092	Loss: 95.907
+38400/69092	Loss: 95.711
+41600/69092	Loss: 94.039
+44800/69092	Loss: 95.335
+48000/69092	Loss: 94.150
+51200/69092	Loss: 93.520
+54400/69092	Loss: 94.110
+57600/69092	Loss: 93.849
+60800/69092	Loss: 94.094
+64000/69092	Loss: 94.586
+67200/69092	Loss: 93.006
+Training time 0:07:42.206996
+Epoch: 24 Average loss: 94.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 263)
+0/69092	Loss: 88.416
+3200/69092	Loss: 94.540
+6400/69092	Loss: 94.009
+9600/69092	Loss: 93.845
+12800/69092	Loss: 94.440
+16000/69092	Loss: 95.946
+19200/69092	Loss: 94.573
+22400/69092	Loss: 94.471
+25600/69092	Loss: 94.279
+28800/69092	Loss: 93.898
+32000/69092	Loss: 94.539
+35200/69092	Loss: 94.141
+38400/69092	Loss: 94.315
+41600/69092	Loss: 94.690
+44800/69092	Loss: 95.521
+48000/69092	Loss: 94.180
+51200/69092	Loss: 94.408
+54400/69092	Loss: 94.011
+57600/69092	Loss: 93.877
+60800/69092	Loss: 95.488
+64000/69092	Loss: 94.899
+67200/69092	Loss: 95.261
+Training time 0:07:40.103666
+Epoch: 25 Average loss: 94.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 264)
+0/69092	Loss: 85.111
+3200/69092	Loss: 94.827
+6400/69092	Loss: 94.699
+9600/69092	Loss: 96.204
+12800/69092	Loss: 94.342
+16000/69092	Loss: 93.345
+19200/69092	Loss: 94.901
+22400/69092	Loss: 95.114
+25600/69092	Loss: 94.180
+28800/69092	Loss: 95.085
+32000/69092	Loss: 93.044
+35200/69092	Loss: 92.472
+38400/69092	Loss: 95.928
+41600/69092	Loss: 93.398
+44800/69092	Loss: 93.856
+48000/69092	Loss: 94.865
+51200/69092	Loss: 94.287
+54400/69092	Loss: 94.606
+57600/69092	Loss: 93.693
+60800/69092	Loss: 95.496
+64000/69092	Loss: 94.321
+67200/69092	Loss: 93.808
+Training time 0:07:34.503459
+Epoch: 26 Average loss: 94.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 265)
+0/69092	Loss: 88.303
+3200/69092	Loss: 95.841
+6400/69092	Loss: 93.394
+9600/69092	Loss: 95.016
+12800/69092	Loss: 94.989
+16000/69092	Loss: 94.769
+19200/69092	Loss: 93.279
+22400/69092	Loss: 94.236
+25600/69092	Loss: 95.781
+28800/69092	Loss: 95.774
+32000/69092	Loss: 93.033
+35200/69092	Loss: 92.807
+38400/69092	Loss: 94.712
+41600/69092	Loss: 94.715
+44800/69092	Loss: 95.253
+48000/69092	Loss: 94.960
+51200/69092	Loss: 94.723
+54400/69092	Loss: 93.044
+57600/69092	Loss: 93.961
+60800/69092	Loss: 94.069
+64000/69092	Loss: 94.524
+67200/69092	Loss: 93.462
+Training time 0:07:39.386642
+Epoch: 27 Average loss: 94.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 266)
+0/69092	Loss: 94.946
+3200/69092	Loss: 95.531
+6400/69092	Loss: 93.108
+9600/69092	Loss: 93.064
+12800/69092	Loss: 93.868
+16000/69092	Loss: 94.985
+19200/69092	Loss: 93.235
+22400/69092	Loss: 96.176
+25600/69092	Loss: 93.569
+28800/69092	Loss: 93.586
+32000/69092	Loss: 93.847
+35200/69092	Loss: 95.598
+38400/69092	Loss: 94.281
+41600/69092	Loss: 93.923
+44800/69092	Loss: 92.984
+48000/69092	Loss: 94.620
+51200/69092	Loss: 93.596
+54400/69092	Loss: 94.434
+57600/69092	Loss: 93.549
+60800/69092	Loss: 95.144
+64000/69092	Loss: 94.602
+67200/69092	Loss: 93.778
+Training time 0:07:38.999495
+Epoch: 28 Average loss: 94.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 267)
+0/69092	Loss: 101.820
+3200/69092	Loss: 95.849
+6400/69092	Loss: 94.409
+9600/69092	Loss: 94.295
+12800/69092	Loss: 94.057
+16000/69092	Loss: 93.504
+19200/69092	Loss: 94.535
+22400/69092	Loss: 94.866
+25600/69092	Loss: 94.070
+28800/69092	Loss: 94.800
+32000/69092	Loss: 95.176
+35200/69092	Loss: 93.409
+38400/69092	Loss: 94.730
+41600/69092	Loss: 95.053
+44800/69092	Loss: 94.510
+48000/69092	Loss: 93.804
+51200/69092	Loss: 93.469
+54400/69092	Loss: 94.109
+57600/69092	Loss: 93.638
+60800/69092	Loss: 93.365
+64000/69092	Loss: 93.684
+67200/69092	Loss: 93.409
+Training time 0:07:45.171285
+Epoch: 29 Average loss: 94.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 268)
+0/69092	Loss: 96.377
+3200/69092	Loss: 94.557
+6400/69092	Loss: 94.312
+9600/69092	Loss: 92.308
+12800/69092	Loss: 94.452
+16000/69092	Loss: 93.923
+19200/69092	Loss: 94.038
+22400/69092	Loss: 94.325
+25600/69092	Loss: 94.091
+28800/69092	Loss: 94.862
+32000/69092	Loss: 95.689
+35200/69092	Loss: 95.604
+38400/69092	Loss: 93.382
+41600/69092	Loss: 94.479
+44800/69092	Loss: 93.209
+48000/69092	Loss: 94.666
+51200/69092	Loss: 92.685
+54400/69092	Loss: 95.245
+57600/69092	Loss: 94.772
+60800/69092	Loss: 94.947
+64000/69092	Loss: 93.205
+67200/69092	Loss: 94.040
+Training time 0:07:42.609167
+Epoch: 30 Average loss: 94.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 269)
+0/69092	Loss: 103.367
+3200/69092	Loss: 94.699
+6400/69092	Loss: 95.023
+9600/69092	Loss: 95.379
+12800/69092	Loss: 94.293
+16000/69092	Loss: 94.712
+19200/69092	Loss: 93.848
+22400/69092	Loss: 93.260
+25600/69092	Loss: 93.806
+28800/69092	Loss: 95.096
+32000/69092	Loss: 95.030
+35200/69092	Loss: 93.984
+38400/69092	Loss: 94.321
+41600/69092	Loss: 94.702
+44800/69092	Loss: 95.071
+48000/69092	Loss: 93.694
+51200/69092	Loss: 94.426
+54400/69092	Loss: 92.545
+57600/69092	Loss: 94.269
+60800/69092	Loss: 94.967
+64000/69092	Loss: 93.812
+67200/69092	Loss: 93.935
+Training time 0:07:43.513473
+Epoch: 31 Average loss: 94.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 270)
+0/69092	Loss: 86.774
+3200/69092	Loss: 92.884
+6400/69092	Loss: 94.309
+9600/69092	Loss: 94.701
+12800/69092	Loss: 93.789
+16000/69092	Loss: 94.992
+19200/69092	Loss: 94.160
+22400/69092	Loss: 94.172
+25600/69092	Loss: 94.512
+28800/69092	Loss: 94.316
+32000/69092	Loss: 93.107
+35200/69092	Loss: 93.197
+38400/69092	Loss: 94.714
+41600/69092	Loss: 94.126
+44800/69092	Loss: 93.114
+48000/69092	Loss: 93.985
+51200/69092	Loss: 94.220
+54400/69092	Loss: 95.437
+57600/69092	Loss: 94.879
+60800/69092	Loss: 95.131
+64000/69092	Loss: 93.899
+67200/69092	Loss: 93.811
+Training time 0:07:34.525610
+Epoch: 32 Average loss: 94.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 271)
+0/69092	Loss: 79.082
+3200/69092	Loss: 93.919
+6400/69092	Loss: 92.965
+9600/69092	Loss: 93.827
+12800/69092	Loss: 94.259
+16000/69092	Loss: 93.290
+19200/69092	Loss: 93.047
+22400/69092	Loss: 93.228
+25600/69092	Loss: 94.482
+28800/69092	Loss: 94.434
+32000/69092	Loss: 95.008
+35200/69092	Loss: 94.336
+38400/69092	Loss: 94.221
+41600/69092	Loss: 93.217
+44800/69092	Loss: 94.862
+48000/69092	Loss: 96.200
+51200/69092	Loss: 94.070
+54400/69092	Loss: 95.314
+57600/69092	Loss: 95.655
+60800/69092	Loss: 93.137
+64000/69092	Loss: 94.254
+67200/69092	Loss: 94.553
+Training time 0:07:47.004933
+Epoch: 33 Average loss: 94.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 272)
+0/69092	Loss: 92.115
+3200/69092	Loss: 94.322
+6400/69092	Loss: 94.053
+9600/69092	Loss: 94.973
+12800/69092	Loss: 94.937
+16000/69092	Loss: 93.713
+19200/69092	Loss: 93.324
+22400/69092	Loss: 94.396
+25600/69092	Loss: 93.361
+28800/69092	Loss: 94.258
+32000/69092	Loss: 94.962
+35200/69092	Loss: 93.783
+38400/69092	Loss: 93.671
+41600/69092	Loss: 95.809
+44800/69092	Loss: 94.409
+48000/69092	Loss: 95.979
+51200/69092	Loss: 93.135
+54400/69092	Loss: 94.423
+57600/69092	Loss: 95.068
+60800/69092	Loss: 94.002
+64000/69092	Loss: 93.866
+67200/69092	Loss: 94.337
+Training time 0:07:54.671753
+Epoch: 34 Average loss: 94.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 273)
+0/69092	Loss: 88.563
+3200/69092	Loss: 95.024
+6400/69092	Loss: 93.990
+9600/69092	Loss: 94.811
+12800/69092	Loss: 94.545
+16000/69092	Loss: 94.481
+19200/69092	Loss: 94.026
+22400/69092	Loss: 94.225
+25600/69092	Loss: 93.618
+28800/69092	Loss: 94.643
+32000/69092	Loss: 93.735
+35200/69092	Loss: 94.191
+38400/69092	Loss: 93.790
+41600/69092	Loss: 94.506
+44800/69092	Loss: 94.931
+48000/69092	Loss: 94.278
+51200/69092	Loss: 92.736
+54400/69092	Loss: 92.957
+57600/69092	Loss: 95.095
+60800/69092	Loss: 96.386
+64000/69092	Loss: 93.339
+67200/69092	Loss: 93.537
+Training time 0:07:40.178223
+Epoch: 35 Average loss: 94.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 274)
+0/69092	Loss: 87.948
+3200/69092	Loss: 95.042
+6400/69092	Loss: 94.420
+9600/69092	Loss: 94.592
+12800/69092	Loss: 93.621
+16000/69092	Loss: 94.335
+19200/69092	Loss: 92.897
+22400/69092	Loss: 95.980
+25600/69092	Loss: 94.108
+28800/69092	Loss: 95.702
+32000/69092	Loss: 94.126
+35200/69092	Loss: 94.676
+38400/69092	Loss: 93.227
+41600/69092	Loss: 93.622
+44800/69092	Loss: 93.259
+48000/69092	Loss: 93.458
+51200/69092	Loss: 93.247
+54400/69092	Loss: 94.638
+57600/69092	Loss: 94.964
+60800/69092	Loss: 94.570
+64000/69092	Loss: 93.521
+67200/69092	Loss: 92.679
+Training time 0:07:46.574816
+Epoch: 36 Average loss: 94.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 275)
+0/69092	Loss: 98.575
+3200/69092	Loss: 94.629
+6400/69092	Loss: 94.557
+9600/69092	Loss: 95.206
+12800/69092	Loss: 93.700
+16000/69092	Loss: 92.573
+19200/69092	Loss: 94.727
+22400/69092	Loss: 94.275
+25600/69092	Loss: 93.691
+28800/69092	Loss: 93.505
+32000/69092	Loss: 94.334
+35200/69092	Loss: 95.038
+38400/69092	Loss: 93.536
+41600/69092	Loss: 93.998
+44800/69092	Loss: 95.422
+48000/69092	Loss: 92.996
+51200/69092	Loss: 93.841
+54400/69092	Loss: 94.419
+57600/69092	Loss: 94.256
+60800/69092	Loss: 94.062
+64000/69092	Loss: 94.341
+67200/69092	Loss: 93.731
+Training time 0:07:36.066927
+Epoch: 37 Average loss: 94.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 276)
+0/69092	Loss: 106.238
+3200/69092	Loss: 93.937
+6400/69092	Loss: 92.894
+9600/69092	Loss: 94.920
+12800/69092	Loss: 94.130
+16000/69092	Loss: 93.202
+19200/69092	Loss: 94.408
+22400/69092	Loss: 94.472
+25600/69092	Loss: 94.444
+28800/69092	Loss: 93.888
+32000/69092	Loss: 95.488
+35200/69092	Loss: 95.220
+38400/69092	Loss: 94.451
+41600/69092	Loss: 95.058
+44800/69092	Loss: 93.607
+48000/69092	Loss: 94.011
+51200/69092	Loss: 94.617
+54400/69092	Loss: 94.563
+57600/69092	Loss: 94.011
+60800/69092	Loss: 95.383
+64000/69092	Loss: 95.589
+67200/69092	Loss: 92.824
+Training time 0:07:44.982394
+Epoch: 38 Average loss: 94.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 277)
+0/69092	Loss: 96.650
+3200/69092	Loss: 93.978
+6400/69092	Loss: 94.503
+9600/69092	Loss: 94.344
+12800/69092	Loss: 94.054
+16000/69092	Loss: 93.252
+19200/69092	Loss: 93.878
+22400/69092	Loss: 94.215
+25600/69092	Loss: 92.709
+28800/69092	Loss: 93.490
+32000/69092	Loss: 95.771
+35200/69092	Loss: 96.025
+38400/69092	Loss: 93.638
+41600/69092	Loss: 94.336
+44800/69092	Loss: 93.556
+48000/69092	Loss: 94.772
+51200/69092	Loss: 94.093
+54400/69092	Loss: 94.135
+57600/69092	Loss: 93.590
+60800/69092	Loss: 95.128
+64000/69092	Loss: 93.634
+67200/69092	Loss: 94.064
+Training time 0:07:59.348702
+Epoch: 39 Average loss: 94.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 278)
+0/69092	Loss: 85.455
+3200/69092	Loss: 94.549
+6400/69092	Loss: 93.275
+9600/69092	Loss: 94.619
+12800/69092	Loss: 94.962
+16000/69092	Loss: 95.033
+19200/69092	Loss: 93.486
+22400/69092	Loss: 94.033
+25600/69092	Loss: 93.805
+28800/69092	Loss: 93.607
+32000/69092	Loss: 94.808
+35200/69092	Loss: 94.589
+38400/69092	Loss: 93.609
+41600/69092	Loss: 94.311
+44800/69092	Loss: 96.463
+48000/69092	Loss: 94.146
+51200/69092	Loss: 93.707
+54400/69092	Loss: 94.317
+57600/69092	Loss: 93.891
+60800/69092	Loss: 95.680
+64000/69092	Loss: 94.708
+67200/69092	Loss: 93.152
+Training time 0:07:41.063716
+Epoch: 40 Average loss: 94.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 279)
+0/69092	Loss: 95.901
+3200/69092	Loss: 93.413
+6400/69092	Loss: 94.176
diff --git a/OAR.2071927.stderr b/OAR.2071927.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a9c628a29c58ebc65df754dd5dfbbd99e2282b5f
--- /dev/null
+++ b/OAR.2071927.stderr
@@ -0,0 +1,2 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071927.stdout b/OAR.2071927.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..e01dbf8014c1032b3fb423e87ad6e9e68e8f62e7
--- /dev/null
+++ b/OAR.2071927.stdout
@@ -0,0 +1,1138 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='VAE_bs_64_ls_50', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=50, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K80
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=100, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=50, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 796135
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last (iter 231)'
+0/69092	Loss: 91.954
+3200/69092	Loss: 94.564
+6400/69092	Loss: 93.376
+9600/69092	Loss: 93.990
+12800/69092	Loss: 92.945
+16000/69092	Loss: 95.209
+19200/69092	Loss: 93.579
+22400/69092	Loss: 94.560
+25600/69092	Loss: 94.213
+28800/69092	Loss: 94.965
+32000/69092	Loss: 94.429
+35200/69092	Loss: 93.918
+38400/69092	Loss: 95.537
+41600/69092	Loss: 93.524
+44800/69092	Loss: 96.094
+48000/69092	Loss: 93.614
+51200/69092	Loss: 93.349
+54400/69092	Loss: 94.956
+57600/69092	Loss: 94.136
+60800/69092	Loss: 95.075
+64000/69092	Loss: 95.717
+67200/69092	Loss: 96.182
+Training time 0:06:56.489005
+Epoch: 1 Average loss: 94.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 232)
+0/69092	Loss: 90.646
+3200/69092	Loss: 94.751
+6400/69092	Loss: 94.286
+9600/69092	Loss: 91.797
+12800/69092	Loss: 94.522
+16000/69092	Loss: 95.491
+19200/69092	Loss: 93.723
+22400/69092	Loss: 94.257
+25600/69092	Loss: 94.333
+28800/69092	Loss: 93.729
+32000/69092	Loss: 94.455
+35200/69092	Loss: 94.175
+38400/69092	Loss: 93.918
+41600/69092	Loss: 92.870
+44800/69092	Loss: 93.593
+48000/69092	Loss: 95.452
+51200/69092	Loss: 94.741
+54400/69092	Loss: 94.695
+57600/69092	Loss: 94.203
+60800/69092	Loss: 95.056
+64000/69092	Loss: 93.085
+67200/69092	Loss: 96.027
+Training time 0:06:57.405771
+Epoch: 2 Average loss: 94.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 233)
+0/69092	Loss: 94.921
+3200/69092	Loss: 94.141
+6400/69092	Loss: 94.381
+9600/69092	Loss: 94.649
+12800/69092	Loss: 94.833
+16000/69092	Loss: 93.805
+19200/69092	Loss: 93.936
+22400/69092	Loss: 94.193
+25600/69092	Loss: 92.998
+28800/69092	Loss: 95.128
+32000/69092	Loss: 94.053
+35200/69092	Loss: 94.406
+38400/69092	Loss: 94.352
+41600/69092	Loss: 93.951
+44800/69092	Loss: 94.333
+48000/69092	Loss: 93.812
+51200/69092	Loss: 94.470
+54400/69092	Loss: 93.909
+57600/69092	Loss: 93.817
+60800/69092	Loss: 94.382
+64000/69092	Loss: 95.342
+67200/69092	Loss: 93.656
+Training time 0:07:06.982462
+Epoch: 3 Average loss: 94.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 234)
+0/69092	Loss: 91.938
+3200/69092	Loss: 93.216
+6400/69092	Loss: 92.719
+9600/69092	Loss: 94.298
+12800/69092	Loss: 95.344
+16000/69092	Loss: 94.878
+19200/69092	Loss: 93.279
+22400/69092	Loss: 94.137
+25600/69092	Loss: 95.604
+28800/69092	Loss: 94.071
+32000/69092	Loss: 93.699
+35200/69092	Loss: 92.445
+38400/69092	Loss: 94.563
+41600/69092	Loss: 94.948
+44800/69092	Loss: 95.028
+48000/69092	Loss: 95.213
+51200/69092	Loss: 93.304
+54400/69092	Loss: 93.944
+57600/69092	Loss: 94.320
+60800/69092	Loss: 93.398
+64000/69092	Loss: 95.316
+67200/69092	Loss: 94.405
+Training time 0:07:02.932819
+Epoch: 4 Average loss: 94.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 235)
+0/69092	Loss: 96.773
+3200/69092	Loss: 94.703
+6400/69092	Loss: 94.128
+9600/69092	Loss: 94.920
+12800/69092	Loss: 94.056
+16000/69092	Loss: 94.226
+19200/69092	Loss: 93.954
+22400/69092	Loss: 93.243
+25600/69092	Loss: 93.155
+28800/69092	Loss: 94.354
+32000/69092	Loss: 94.070
+35200/69092	Loss: 94.949
+38400/69092	Loss: 95.588
+41600/69092	Loss: 94.516
+44800/69092	Loss: 95.082
+48000/69092	Loss: 94.117
+51200/69092	Loss: 94.425
+54400/69092	Loss: 94.776
+57600/69092	Loss: 92.593
+60800/69092	Loss: 94.033
+64000/69092	Loss: 95.372
+67200/69092	Loss: 92.841
+Training time 0:07:00.806582
+Epoch: 5 Average loss: 94.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 236)
+0/69092	Loss: 87.616
+3200/69092	Loss: 94.689
+6400/69092	Loss: 94.062
+9600/69092	Loss: 91.786
+12800/69092	Loss: 93.490
+16000/69092	Loss: 94.050
+19200/69092	Loss: 94.785
+22400/69092	Loss: 93.769
+25600/69092	Loss: 93.951
+28800/69092	Loss: 94.472
+32000/69092	Loss: 94.971
+35200/69092	Loss: 94.899
+38400/69092	Loss: 94.376
+41600/69092	Loss: 94.080
+44800/69092	Loss: 95.883
+48000/69092	Loss: 92.942
+51200/69092	Loss: 95.381
+54400/69092	Loss: 93.424
+57600/69092	Loss: 94.124
+60800/69092	Loss: 93.805
+64000/69092	Loss: 93.311
+67200/69092	Loss: 93.765
+Training time 0:06:54.264797
+Epoch: 6 Average loss: 94.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 237)
+0/69092	Loss: 100.211
+3200/69092	Loss: 93.414
+6400/69092	Loss: 92.689
+9600/69092	Loss: 93.568
+12800/69092	Loss: 93.602
+16000/69092	Loss: 93.310
+19200/69092	Loss: 93.892
+22400/69092	Loss: 95.053
+25600/69092	Loss: 95.893
+28800/69092	Loss: 93.569
+32000/69092	Loss: 95.481
+35200/69092	Loss: 94.790
+38400/69092	Loss: 93.807
+41600/69092	Loss: 93.254
+44800/69092	Loss: 92.942
+48000/69092	Loss: 94.108
+51200/69092	Loss: 92.903
+54400/69092	Loss: 95.305
+57600/69092	Loss: 94.821
+60800/69092	Loss: 93.781
+64000/69092	Loss: 94.486
+67200/69092	Loss: 93.924
+Training time 0:06:57.509953
+Epoch: 7 Average loss: 94.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 238)
+0/69092	Loss: 89.657
+3200/69092	Loss: 94.601
+6400/69092	Loss: 94.332
+9600/69092	Loss: 94.131
+12800/69092	Loss: 94.798
+16000/69092	Loss: 94.570
+19200/69092	Loss: 94.333
+22400/69092	Loss: 93.240
+25600/69092	Loss: 94.566
+28800/69092	Loss: 93.813
+32000/69092	Loss: 93.390
+35200/69092	Loss: 94.517
+38400/69092	Loss: 95.254
+41600/69092	Loss: 94.114
+44800/69092	Loss: 92.701
+48000/69092	Loss: 92.974
+51200/69092	Loss: 93.490
+54400/69092	Loss: 93.963
+57600/69092	Loss: 95.039
+60800/69092	Loss: 92.638
+64000/69092	Loss: 92.846
+67200/69092	Loss: 94.671
+Training time 0:07:03.287176
+Epoch: 8 Average loss: 94.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 239)
+0/69092	Loss: 92.391
+3200/69092	Loss: 94.234
+6400/69092	Loss: 92.268
+9600/69092	Loss: 93.573
+12800/69092	Loss: 95.393
+16000/69092	Loss: 93.456
+19200/69092	Loss: 94.691
+22400/69092	Loss: 94.237
+25600/69092	Loss: 92.955
+28800/69092	Loss: 93.153
+32000/69092	Loss: 94.726
+35200/69092	Loss: 93.210
+38400/69092	Loss: 94.574
+41600/69092	Loss: 95.294
+44800/69092	Loss: 93.646
+48000/69092	Loss: 94.459
+51200/69092	Loss: 94.643
+54400/69092	Loss: 94.692
+57600/69092	Loss: 94.198
+60800/69092	Loss: 93.658
+64000/69092	Loss: 96.210
+67200/69092	Loss: 94.079
+Training time 0:07:04.094575
+Epoch: 9 Average loss: 94.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 240)
+0/69092	Loss: 93.099
+3200/69092	Loss: 94.090
+6400/69092	Loss: 94.101
+9600/69092	Loss: 94.080
+12800/69092	Loss: 94.538
+16000/69092	Loss: 93.421
+19200/69092	Loss: 95.078
+22400/69092	Loss: 93.787
+25600/69092	Loss: 94.570
+28800/69092	Loss: 94.530
+32000/69092	Loss: 95.694
+35200/69092	Loss: 93.178
+38400/69092	Loss: 93.827
+41600/69092	Loss: 93.383
+44800/69092	Loss: 94.239
+48000/69092	Loss: 95.279
+51200/69092	Loss: 92.860
+54400/69092	Loss: 93.146
+57600/69092	Loss: 94.589
+60800/69092	Loss: 92.408
+64000/69092	Loss: 93.531
+67200/69092	Loss: 94.841
+Training time 0:07:08.030146
+Epoch: 10 Average loss: 94.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 241)
+0/69092	Loss: 86.579
+3200/69092	Loss: 94.167
+6400/69092	Loss: 95.532
+9600/69092	Loss: 93.748
+12800/69092	Loss: 95.083
+16000/69092	Loss: 92.132
+19200/69092	Loss: 93.660
+22400/69092	Loss: 94.725
+25600/69092	Loss: 94.670
+28800/69092	Loss: 93.832
+32000/69092	Loss: 93.552
+35200/69092	Loss: 93.077
+38400/69092	Loss: 94.118
+41600/69092	Loss: 92.951
+44800/69092	Loss: 94.034
+48000/69092	Loss: 93.996
+51200/69092	Loss: 93.599
+54400/69092	Loss: 94.383
+57600/69092	Loss: 93.775
+60800/69092	Loss: 93.624
+64000/69092	Loss: 94.947
+67200/69092	Loss: 93.503
+Training time 0:06:58.476348
+Epoch: 11 Average loss: 93.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 242)
+0/69092	Loss: 89.013
+3200/69092	Loss: 94.977
+6400/69092	Loss: 94.617
+9600/69092	Loss: 93.343
+12800/69092	Loss: 95.139
+16000/69092	Loss: 94.109
+19200/69092	Loss: 94.013
+22400/69092	Loss: 93.279
+25600/69092	Loss: 93.785
+28800/69092	Loss: 93.132
+32000/69092	Loss: 94.397
+35200/69092	Loss: 93.784
+38400/69092	Loss: 93.331
+41600/69092	Loss: 94.190
+44800/69092	Loss: 92.857
+48000/69092	Loss: 93.608
+51200/69092	Loss: 94.303
+54400/69092	Loss: 95.162
+57600/69092	Loss: 94.672
+60800/69092	Loss: 94.972
+64000/69092	Loss: 94.054
+67200/69092	Loss: 93.682
+Training time 0:07:00.233406
+Epoch: 12 Average loss: 94.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 243)
+0/69092	Loss: 90.844
+3200/69092	Loss: 92.882
+6400/69092	Loss: 92.729
+9600/69092	Loss: 93.199
+12800/69092	Loss: 94.173
+16000/69092	Loss: 93.976
+19200/69092	Loss: 96.533
+22400/69092	Loss: 94.087
+25600/69092	Loss: 93.430
+28800/69092	Loss: 93.224
+32000/69092	Loss: 94.892
+35200/69092	Loss: 94.992
+38400/69092	Loss: 93.290
+41600/69092	Loss: 94.268
+44800/69092	Loss: 92.762
+48000/69092	Loss: 94.361
+51200/69092	Loss: 94.622
+54400/69092	Loss: 94.934
+57600/69092	Loss: 94.316
+60800/69092	Loss: 94.388
+64000/69092	Loss: 93.523
+67200/69092	Loss: 93.511
+Training time 0:06:52.749979
+Epoch: 13 Average loss: 94.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 244)
+0/69092	Loss: 90.390
+3200/69092	Loss: 93.877
+6400/69092	Loss: 94.948
+9600/69092	Loss: 94.875
+12800/69092	Loss: 93.920
+16000/69092	Loss: 93.379
+19200/69092	Loss: 95.375
+22400/69092	Loss: 93.995
+25600/69092	Loss: 93.755
+28800/69092	Loss: 93.181
+32000/69092	Loss: 93.946
+35200/69092	Loss: 93.749
+38400/69092	Loss: 94.093
+41600/69092	Loss: 93.199
+44800/69092	Loss: 94.266
+48000/69092	Loss: 94.846
+51200/69092	Loss: 93.399
+54400/69092	Loss: 93.975
+57600/69092	Loss: 93.662
+60800/69092	Loss: 93.924
+64000/69092	Loss: 94.626
+67200/69092	Loss: 94.234
+Training time 0:06:59.646990
+Epoch: 14 Average loss: 94.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 245)
+0/69092	Loss: 93.325
+3200/69092	Loss: 94.246
+6400/69092	Loss: 94.331
+9600/69092	Loss: 93.115
+12800/69092	Loss: 94.181
+16000/69092	Loss: 94.444
+19200/69092	Loss: 93.339
+22400/69092	Loss: 94.276
+25600/69092	Loss: 93.336
+28800/69092	Loss: 94.324
+32000/69092	Loss: 93.356
+35200/69092	Loss: 94.727
+38400/69092	Loss: 93.308
+41600/69092	Loss: 93.842
+44800/69092	Loss: 94.296
+48000/69092	Loss: 93.447
+51200/69092	Loss: 94.448
+54400/69092	Loss: 92.919
+57600/69092	Loss: 94.079
+60800/69092	Loss: 94.296
+64000/69092	Loss: 94.785
+67200/69092	Loss: 93.389
+Training time 0:07:05.580641
+Epoch: 15 Average loss: 93.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 246)
+0/69092	Loss: 96.399
+3200/69092	Loss: 93.748
+6400/69092	Loss: 92.157
+9600/69092	Loss: 93.750
+12800/69092	Loss: 94.277
+16000/69092	Loss: 93.989
+19200/69092	Loss: 92.692
+22400/69092	Loss: 94.263
+25600/69092	Loss: 94.895
+28800/69092	Loss: 94.126
+32000/69092	Loss: 93.989
+35200/69092	Loss: 92.535
+38400/69092	Loss: 93.822
+41600/69092	Loss: 94.990
+44800/69092	Loss: 94.324
+48000/69092	Loss: 93.366
+51200/69092	Loss: 94.301
+54400/69092	Loss: 94.812
+57600/69092	Loss: 93.258
+60800/69092	Loss: 93.779
+64000/69092	Loss: 95.196
+67200/69092	Loss: 93.353
+Training time 0:07:05.686162
+Epoch: 16 Average loss: 93.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 247)
+0/69092	Loss: 91.840
+3200/69092	Loss: 93.470
+6400/69092	Loss: 93.651
+9600/69092	Loss: 93.924
+12800/69092	Loss: 93.208
+16000/69092	Loss: 92.839
+19200/69092	Loss: 93.419
+22400/69092	Loss: 92.472
+25600/69092	Loss: 95.862
+28800/69092	Loss: 93.224
+32000/69092	Loss: 93.050
+35200/69092	Loss: 95.159
+38400/69092	Loss: 94.040
+41600/69092	Loss: 95.416
+44800/69092	Loss: 94.545
+48000/69092	Loss: 94.206
+51200/69092	Loss: 92.688
+54400/69092	Loss: 93.768
+57600/69092	Loss: 95.083
+60800/69092	Loss: 94.196
+64000/69092	Loss: 93.584
+67200/69092	Loss: 94.232
+Training time 0:07:04.703433
+Epoch: 17 Average loss: 93.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 248)
+0/69092	Loss: 94.937
+3200/69092	Loss: 93.893
+6400/69092	Loss: 93.498
+9600/69092	Loss: 94.041
+12800/69092	Loss: 93.068
+16000/69092	Loss: 93.918
+19200/69092	Loss: 93.568
+22400/69092	Loss: 93.672
+25600/69092	Loss: 93.894
+28800/69092	Loss: 95.021
+32000/69092	Loss: 93.935
+35200/69092	Loss: 95.891
+38400/69092	Loss: 93.123
+41600/69092	Loss: 93.906
+44800/69092	Loss: 93.249
+48000/69092	Loss: 94.828
+51200/69092	Loss: 94.011
+54400/69092	Loss: 94.052
+57600/69092	Loss: 94.746
+60800/69092	Loss: 93.490
+64000/69092	Loss: 93.899
+67200/69092	Loss: 94.776
+Training time 0:07:03.482239
+Epoch: 18 Average loss: 94.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 249)
+0/69092	Loss: 89.131
+3200/69092	Loss: 92.850
+6400/69092	Loss: 92.899
+9600/69092	Loss: 95.201
+12800/69092	Loss: 93.583
+16000/69092	Loss: 95.122
+19200/69092	Loss: 92.846
+22400/69092	Loss: 93.398
+25600/69092	Loss: 94.351
+28800/69092	Loss: 93.776
+32000/69092	Loss: 94.067
+35200/69092	Loss: 94.017
+38400/69092	Loss: 93.039
+41600/69092	Loss: 93.570
+44800/69092	Loss: 94.194
+48000/69092	Loss: 94.586
+51200/69092	Loss: 95.369
+54400/69092	Loss: 93.713
+57600/69092	Loss: 93.555
+60800/69092	Loss: 93.583
+64000/69092	Loss: 94.926
+67200/69092	Loss: 94.087
+Training time 0:07:04.719803
+Epoch: 19 Average loss: 94.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 250)
+0/69092	Loss: 91.810
+3200/69092	Loss: 93.853
+6400/69092	Loss: 93.550
+9600/69092	Loss: 94.183
+12800/69092	Loss: 94.360
+16000/69092	Loss: 95.047
+19200/69092	Loss: 92.740
+22400/69092	Loss: 93.590
+25600/69092	Loss: 93.564
+28800/69092	Loss: 93.260
+32000/69092	Loss: 94.822
+35200/69092	Loss: 93.956
+38400/69092	Loss: 94.448
+41600/69092	Loss: 94.269
+44800/69092	Loss: 92.516
+48000/69092	Loss: 94.475
+51200/69092	Loss: 95.246
+54400/69092	Loss: 93.080
+57600/69092	Loss: 93.654
+60800/69092	Loss: 93.237
+64000/69092	Loss: 91.936
+67200/69092	Loss: 95.163
+Training time 0:06:56.653846
+Epoch: 20 Average loss: 93.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 251)
+0/69092	Loss: 91.851
+3200/69092	Loss: 93.537
+6400/69092	Loss: 94.055
+9600/69092	Loss: 93.282
+12800/69092	Loss: 92.024
+16000/69092	Loss: 93.725
+19200/69092	Loss: 92.303
+22400/69092	Loss: 93.757
+25600/69092	Loss: 94.509
+28800/69092	Loss: 95.277
+32000/69092	Loss: 92.789
+35200/69092	Loss: 93.005
+38400/69092	Loss: 94.144
+41600/69092	Loss: 94.650
+44800/69092	Loss: 93.839
+48000/69092	Loss: 93.994
+51200/69092	Loss: 92.768
+54400/69092	Loss: 95.125
+57600/69092	Loss: 93.862
+60800/69092	Loss: 93.129
+64000/69092	Loss: 93.729
+67200/69092	Loss: 95.086
+Training time 0:06:56.394174
+Epoch: 21 Average loss: 93.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 252)
+0/69092	Loss: 92.413
+3200/69092	Loss: 92.976
+6400/69092	Loss: 93.642
+9600/69092	Loss: 93.068
+12800/69092	Loss: 95.438
+16000/69092	Loss: 93.382
+19200/69092	Loss: 93.966
+22400/69092	Loss: 92.135
+25600/69092	Loss: 94.228
+28800/69092	Loss: 92.834
+32000/69092	Loss: 93.703
+35200/69092	Loss: 95.286
+38400/69092	Loss: 94.118
+41600/69092	Loss: 93.763
+44800/69092	Loss: 94.233
+48000/69092	Loss: 94.543
+51200/69092	Loss: 95.497
+54400/69092	Loss: 92.438
+57600/69092	Loss: 93.232
+60800/69092	Loss: 94.590
+64000/69092	Loss: 93.731
+67200/69092	Loss: 93.416
+Training time 0:07:04.982861
+Epoch: 22 Average loss: 93.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 253)
+0/69092	Loss: 98.044
+3200/69092	Loss: 94.214
+6400/69092	Loss: 94.709
+9600/69092	Loss: 92.819
+12800/69092	Loss: 94.416
+16000/69092	Loss: 92.884
+19200/69092	Loss: 93.711
+22400/69092	Loss: 94.797
+25600/69092	Loss: 93.724
+28800/69092	Loss: 91.769
+32000/69092	Loss: 94.743
+35200/69092	Loss: 93.565
+38400/69092	Loss: 94.076
+41600/69092	Loss: 95.068
+44800/69092	Loss: 93.737
+48000/69092	Loss: 94.523
+51200/69092	Loss: 94.158
+54400/69092	Loss: 93.901
+57600/69092	Loss: 93.605
+60800/69092	Loss: 94.148
+64000/69092	Loss: 94.700
+67200/69092	Loss: 93.275
+Training time 0:07:01.573592
+Epoch: 23 Average loss: 93.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 254)
+0/69092	Loss: 91.237
+3200/69092	Loss: 94.671
+6400/69092	Loss: 93.024
+9600/69092	Loss: 94.478
+12800/69092	Loss: 93.864
+16000/69092	Loss: 93.331
+19200/69092	Loss: 92.649
+22400/69092	Loss: 94.202
+25600/69092	Loss: 95.006
+28800/69092	Loss: 94.293
+32000/69092	Loss: 95.058
+35200/69092	Loss: 94.177
+38400/69092	Loss: 93.300
+41600/69092	Loss: 95.435
+44800/69092	Loss: 94.899
+48000/69092	Loss: 92.462
+51200/69092	Loss: 93.426
+54400/69092	Loss: 92.618
+57600/69092	Loss: 92.562
+60800/69092	Loss: 93.392
+64000/69092	Loss: 93.695
+67200/69092	Loss: 94.188
+Training time 0:07:04.783166
+Epoch: 24 Average loss: 93.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 255)
+0/69092	Loss: 93.984
+3200/69092	Loss: 92.581
+6400/69092	Loss: 94.216
+9600/69092	Loss: 93.562
+12800/69092	Loss: 93.957
+16000/69092	Loss: 95.314
+19200/69092	Loss: 93.697
+22400/69092	Loss: 94.224
+25600/69092	Loss: 93.041
+28800/69092	Loss: 94.212
+32000/69092	Loss: 93.382
+35200/69092	Loss: 94.075
+38400/69092	Loss: 93.619
+41600/69092	Loss: 92.547
+44800/69092	Loss: 95.178
+48000/69092	Loss: 95.023
+51200/69092	Loss: 94.718
+54400/69092	Loss: 93.548
+57600/69092	Loss: 94.401
+60800/69092	Loss: 92.869
+64000/69092	Loss: 94.009
+67200/69092	Loss: 92.415
+Training time 0:07:06.273061
+Epoch: 25 Average loss: 93.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 256)
+0/69092	Loss: 96.946
+3200/69092	Loss: 93.795
+6400/69092	Loss: 94.650
+9600/69092	Loss: 93.176
+12800/69092	Loss: 94.644
+16000/69092	Loss: 94.119
+19200/69092	Loss: 93.164
+22400/69092	Loss: 93.211
+25600/69092	Loss: 95.226
+28800/69092	Loss: 93.395
+32000/69092	Loss: 93.292
+35200/69092	Loss: 95.615
+38400/69092	Loss: 93.261
+41600/69092	Loss: 94.393
+44800/69092	Loss: 92.232
+48000/69092	Loss: 93.041
+51200/69092	Loss: 92.723
+54400/69092	Loss: 95.004
+57600/69092	Loss: 94.116
+60800/69092	Loss: 94.583
+64000/69092	Loss: 92.882
+67200/69092	Loss: 93.180
+Training time 0:07:00.351770
+Epoch: 26 Average loss: 93.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 257)
+0/69092	Loss: 96.043
+3200/69092	Loss: 93.766
+6400/69092	Loss: 94.551
+9600/69092	Loss: 92.584
+12800/69092	Loss: 94.161
+16000/69092	Loss: 93.527
+19200/69092	Loss: 92.728
+22400/69092	Loss: 94.186
+25600/69092	Loss: 93.800
+28800/69092	Loss: 93.250
+32000/69092	Loss: 95.470
+35200/69092	Loss: 92.976
+38400/69092	Loss: 95.473
+41600/69092	Loss: 93.914
+44800/69092	Loss: 94.419
+48000/69092	Loss: 92.285
+51200/69092	Loss: 94.074
+54400/69092	Loss: 93.707
+57600/69092	Loss: 93.070
+60800/69092	Loss: 93.295
+64000/69092	Loss: 94.360
+67200/69092	Loss: 94.939
+Training time 0:06:57.667458
+Epoch: 27 Average loss: 93.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 258)
+0/69092	Loss: 87.967
+3200/69092	Loss: 93.106
+6400/69092	Loss: 94.031
+9600/69092	Loss: 92.841
+12800/69092	Loss: 94.685
+16000/69092	Loss: 93.360
+19200/69092	Loss: 94.858
+22400/69092	Loss: 93.427
+25600/69092	Loss: 93.627
+28800/69092	Loss: 94.235
+32000/69092	Loss: 94.440
+35200/69092	Loss: 94.991
+38400/69092	Loss: 91.689
+41600/69092	Loss: 92.641
+44800/69092	Loss: 93.826
+48000/69092	Loss: 95.376
+51200/69092	Loss: 91.718
+54400/69092	Loss: 94.108
+57600/69092	Loss: 93.994
+60800/69092	Loss: 94.924
+64000/69092	Loss: 94.465
+67200/69092	Loss: 92.952
+Training time 0:07:07.501697
+Epoch: 28 Average loss: 93.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 259)
+0/69092	Loss: 96.866
+3200/69092	Loss: 93.988
+6400/69092	Loss: 93.443
+9600/69092	Loss: 92.457
+12800/69092	Loss: 94.463
+16000/69092	Loss: 93.752
+19200/69092	Loss: 93.315
+22400/69092	Loss: 95.187
+25600/69092	Loss: 92.730
+28800/69092	Loss: 93.596
+32000/69092	Loss: 94.775
+35200/69092	Loss: 93.785
+38400/69092	Loss: 94.027
+41600/69092	Loss: 94.259
+44800/69092	Loss: 93.648
+48000/69092	Loss: 92.778
+51200/69092	Loss: 93.170
+54400/69092	Loss: 92.939
+57600/69092	Loss: 93.916
+60800/69092	Loss: 92.893
+64000/69092	Loss: 94.399
+67200/69092	Loss: 95.745
+Training time 0:07:01.176009
+Epoch: 29 Average loss: 93.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 260)
+0/69092	Loss: 88.893
+3200/69092	Loss: 93.371
+6400/69092	Loss: 93.672
+9600/69092	Loss: 92.901
+12800/69092	Loss: 94.890
+16000/69092	Loss: 93.264
+19200/69092	Loss: 92.714
+22400/69092	Loss: 93.444
+25600/69092	Loss: 94.636
+28800/69092	Loss: 93.342
+32000/69092	Loss: 93.919
+35200/69092	Loss: 93.856
+38400/69092	Loss: 94.341
+41600/69092	Loss: 92.829
+44800/69092	Loss: 94.299
+48000/69092	Loss: 92.778
+51200/69092	Loss: 94.102
+54400/69092	Loss: 93.205
+57600/69092	Loss: 94.638
+60800/69092	Loss: 93.439
+64000/69092	Loss: 94.108
+67200/69092	Loss: 94.949
+Training time 0:07:01.388608
+Epoch: 30 Average loss: 93.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 261)
+0/69092	Loss: 91.465
+3200/69092	Loss: 93.457
+6400/69092	Loss: 93.957
+9600/69092	Loss: 93.198
+12800/69092	Loss: 92.597
+16000/69092	Loss: 94.662
+19200/69092	Loss: 93.855
+22400/69092	Loss: 92.564
+25600/69092	Loss: 93.856
+28800/69092	Loss: 94.671
+32000/69092	Loss: 93.587
+35200/69092	Loss: 93.843
+38400/69092	Loss: 93.311
+41600/69092	Loss: 94.148
+44800/69092	Loss: 94.342
+48000/69092	Loss: 93.594
+51200/69092	Loss: 93.388
+54400/69092	Loss: 94.381
+57600/69092	Loss: 94.078
+60800/69092	Loss: 95.167
+64000/69092	Loss: 93.073
+67200/69092	Loss: 94.303
+Training time 0:06:54.184314
+Epoch: 31 Average loss: 93.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 262)
+0/69092	Loss: 93.965
+3200/69092	Loss: 92.997
+6400/69092	Loss: 94.673
+9600/69092	Loss: 93.646
+12800/69092	Loss: 92.445
+16000/69092	Loss: 93.038
+19200/69092	Loss: 94.505
+22400/69092	Loss: 94.032
+25600/69092	Loss: 92.595
+28800/69092	Loss: 93.496
+32000/69092	Loss: 92.535
+35200/69092	Loss: 93.531
+38400/69092	Loss: 95.391
+41600/69092	Loss: 93.826
+44800/69092	Loss: 94.712
+48000/69092	Loss: 94.795
+51200/69092	Loss: 93.624
+54400/69092	Loss: 94.756
+57600/69092	Loss: 92.694
+60800/69092	Loss: 93.902
+64000/69092	Loss: 93.025
+67200/69092	Loss: 92.939
+Training time 0:07:05.999554
+Epoch: 32 Average loss: 93.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 263)
+0/69092	Loss: 80.107
+3200/69092	Loss: 93.373
+6400/69092	Loss: 93.693
+9600/69092	Loss: 94.507
+12800/69092	Loss: 90.907
+16000/69092	Loss: 94.202
+19200/69092	Loss: 93.587
+22400/69092	Loss: 94.077
+25600/69092	Loss: 94.347
+28800/69092	Loss: 93.079
+32000/69092	Loss: 93.517
+35200/69092	Loss: 93.432
+38400/69092	Loss: 94.089
+41600/69092	Loss: 94.129
+44800/69092	Loss: 93.881
+48000/69092	Loss: 95.019
+51200/69092	Loss: 93.879
+54400/69092	Loss: 92.711
+57600/69092	Loss: 93.385
+60800/69092	Loss: 94.130
+64000/69092	Loss: 93.788
+67200/69092	Loss: 93.357
+Training time 0:06:58.006102
+Epoch: 33 Average loss: 93.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 264)
+0/69092	Loss: 100.435
+3200/69092	Loss: 95.487
+6400/69092	Loss: 95.220
+9600/69092	Loss: 92.782
+12800/69092	Loss: 92.154
+16000/69092	Loss: 93.941
+19200/69092	Loss: 92.487
+22400/69092	Loss: 93.238
+25600/69092	Loss: 93.125
+28800/69092	Loss: 95.396
+32000/69092	Loss: 93.285
+35200/69092	Loss: 93.284
+38400/69092	Loss: 93.904
+41600/69092	Loss: 93.350
+44800/69092	Loss: 94.356
+48000/69092	Loss: 92.680
+51200/69092	Loss: 92.969
+54400/69092	Loss: 93.093
+57600/69092	Loss: 94.034
+60800/69092	Loss: 93.292
+64000/69092	Loss: 92.719
+67200/69092	Loss: 93.829
+Training time 0:07:06.735766
+Epoch: 34 Average loss: 93.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 265)
+0/69092	Loss: 93.811
+3200/69092	Loss: 92.820
+6400/69092	Loss: 94.973
+9600/69092	Loss: 93.743
+12800/69092	Loss: 93.008
+16000/69092	Loss: 93.329
+19200/69092	Loss: 93.017
+22400/69092	Loss: 94.531
+25600/69092	Loss: 94.180
+28800/69092	Loss: 92.846
+32000/69092	Loss: 94.095
+35200/69092	Loss: 93.935
+38400/69092	Loss: 92.765
+41600/69092	Loss: 94.828
+44800/69092	Loss: 92.949
+48000/69092	Loss: 93.175
+51200/69092	Loss: 95.265
+54400/69092	Loss: 93.193
+57600/69092	Loss: 92.640
+60800/69092	Loss: 93.445
+64000/69092	Loss: 92.821
+67200/69092	Loss: 94.815
+Training time 0:07:03.410689
+Epoch: 35 Average loss: 93.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 266)
+0/69092	Loss: 83.360
+3200/69092	Loss: 94.565
+6400/69092	Loss: 95.067
+9600/69092	Loss: 91.926
+12800/69092	Loss: 93.163
+16000/69092	Loss: 93.349
+19200/69092	Loss: 94.452
+22400/69092	Loss: 93.721
+25600/69092	Loss: 93.591
+28800/69092	Loss: 95.295
+32000/69092	Loss: 93.322
+35200/69092	Loss: 93.582
+38400/69092	Loss: 93.383
+41600/69092	Loss: 92.727
+44800/69092	Loss: 92.520
+48000/69092	Loss: 94.412
+51200/69092	Loss: 94.572
+54400/69092	Loss: 92.589
+57600/69092	Loss: 94.587
+60800/69092	Loss: 93.354
+64000/69092	Loss: 93.367
+67200/69092	Loss: 92.784
+Training time 0:07:04.671140
+Epoch: 36 Average loss: 93.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 267)
+0/69092	Loss: 100.371
+3200/69092	Loss: 94.071
+6400/69092	Loss: 93.271
+9600/69092	Loss: 94.163
+12800/69092	Loss: 91.935
+16000/69092	Loss: 93.439
+19200/69092	Loss: 92.337
+22400/69092	Loss: 93.676
+25600/69092	Loss: 94.121
+28800/69092	Loss: 92.181
+32000/69092	Loss: 92.042
+35200/69092	Loss: 93.660
+38400/69092	Loss: 92.445
+41600/69092	Loss: 93.822
+44800/69092	Loss: 93.543
+48000/69092	Loss: 93.959
+51200/69092	Loss: 93.435
+54400/69092	Loss: 95.076
+57600/69092	Loss: 93.718
+60800/69092	Loss: 93.814
+64000/69092	Loss: 92.744
+67200/69092	Loss: 93.017
+Training time 0:06:59.907736
+Epoch: 37 Average loss: 93.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 268)
+0/69092	Loss: 100.740
+3200/69092	Loss: 92.019
+6400/69092	Loss: 94.097
+9600/69092	Loss: 92.550
+12800/69092	Loss: 93.252
+16000/69092	Loss: 94.385
+19200/69092	Loss: 93.504
+22400/69092	Loss: 92.266
+25600/69092	Loss: 93.742
+28800/69092	Loss: 94.089
+32000/69092	Loss: 94.235
+35200/69092	Loss: 93.887
+38400/69092	Loss: 93.994
+41600/69092	Loss: 93.715
+44800/69092	Loss: 93.188
+48000/69092	Loss: 93.574
+51200/69092	Loss: 92.766
+54400/69092	Loss: 93.564
+57600/69092	Loss: 92.800
+60800/69092	Loss: 93.783
+64000/69092	Loss: 94.058
+67200/69092	Loss: 94.499
+Training time 0:07:05.589520
+Epoch: 38 Average loss: 93.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 269)
+0/69092	Loss: 88.844
+3200/69092	Loss: 93.925
+6400/69092	Loss: 90.867
+9600/69092	Loss: 94.601
+12800/69092	Loss: 93.800
+16000/69092	Loss: 93.144
+19200/69092	Loss: 93.385
+22400/69092	Loss: 93.795
+25600/69092	Loss: 93.682
+28800/69092	Loss: 93.326
+32000/69092	Loss: 93.157
+35200/69092	Loss: 93.875
+38400/69092	Loss: 93.727
+41600/69092	Loss: 93.252
+44800/69092	Loss: 94.059
+48000/69092	Loss: 92.622
+51200/69092	Loss: 93.057
+54400/69092	Loss: 93.775
+57600/69092	Loss: 94.975
+60800/69092	Loss: 92.577
+64000/69092	Loss: 93.395
+67200/69092	Loss: 95.323
+Training time 0:07:01.926352
+Epoch: 39 Average loss: 93.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 270)
+0/69092	Loss: 87.129
+3200/69092	Loss: 92.901
+6400/69092	Loss: 93.095
+9600/69092	Loss: 93.067
+12800/69092	Loss: 93.046
+16000/69092	Loss: 93.275
+19200/69092	Loss: 93.726
+22400/69092	Loss: 92.880
+25600/69092	Loss: 94.158
+28800/69092	Loss: 94.366
+32000/69092	Loss: 94.610
+35200/69092	Loss: 92.425
+38400/69092	Loss: 92.927
+41600/69092	Loss: 94.287
+44800/69092	Loss: 94.346
+48000/69092	Loss: 94.566
+51200/69092	Loss: 93.048
+54400/69092	Loss: 94.151
+57600/69092	Loss: 92.607
+60800/69092	Loss: 92.808
+64000/69092	Loss: 92.593
+67200/69092	Loss: 93.874
+Training time 0:06:54.876161
+Epoch: 40 Average loss: 93.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 271)
+0/69092	Loss: 92.415
+3200/69092	Loss: 92.357
+6400/69092	Loss: 93.147
+9600/69092	Loss: 93.883
+12800/69092	Loss: 93.691
+16000/69092	Loss: 92.528
+19200/69092	Loss: 93.745
+22400/69092	Loss: 94.083
+25600/69092	Loss: 94.158
+28800/69092	Loss: 92.199
+32000/69092	Loss: 93.931
+35200/69092	Loss: 91.717
+38400/69092	Loss: 95.522
+41600/69092	Loss: 93.916
+44800/69092	Loss: 92.727
+48000/69092	Loss: 93.924
+51200/69092	Loss: 93.853
+54400/69092	Loss: 93.795
+57600/69092	Loss: 94.596
+60800/69092	Loss: 94.001
+64000/69092	Loss: 93.537
+67200/69092	Loss: 93.377
+Training time 0:07:04.623070
+Epoch: 41 Average loss: 93.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 272)
+0/69092	Loss: 84.335
+3200/69092	Loss: 93.574
+6400/69092	Loss: 93.742
+9600/69092	Loss: 91.718
+12800/69092	Loss: 93.692
+16000/69092	Loss: 93.585
+19200/69092	Loss: 93.553
+22400/69092	Loss: 94.403
+25600/69092	Loss: 92.876
+28800/69092	Loss: 94.815
+32000/69092	Loss: 92.975
+35200/69092	Loss: 93.024
+38400/69092	Loss: 93.580
+41600/69092	Loss: 92.611
+44800/69092	Loss: 92.174
+48000/69092	Loss: 94.334
+51200/69092	Loss: 93.557
+54400/69092	Loss: 93.344
+57600/69092	Loss: 92.551
+60800/69092	Loss: 92.518
+64000/69092	Loss: 95.062
+67200/69092	Loss: 93.588
+Training time 0:06:58.053124
+Epoch: 42 Average loss: 93.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 273)
+0/69092	Loss: 86.378
+3200/69092	Loss: 94.490
+6400/69092	Loss: 93.240
+9600/69092	Loss: 94.708
+12800/69092	Loss: 92.909
+16000/69092	Loss: 92.741
+19200/69092	Loss: 92.189
+22400/69092	Loss: 93.218
+25600/69092	Loss: 94.175
+28800/69092	Loss: 94.273
+32000/69092	Loss: 93.785
+35200/69092	Loss: 93.442
+38400/69092	Loss: 94.381
+41600/69092	Loss: 94.249
+44800/69092	Loss: 93.853
+48000/69092	Loss: 92.900
+51200/69092	Loss: 94.007
+54400/69092	Loss: 92.366
+57600/69092	Loss: 93.261
+60800/69092	Loss: 94.317
+64000/69092	Loss: 93.246
+67200/69092	Loss: 93.206
+Training time 0:07:11.713550
+Epoch: 43 Average loss: 93.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 274)
+0/69092	Loss: 87.270
+3200/69092	Loss: 93.622
+6400/69092	Loss: 93.504
+9600/69092	Loss: 92.500
+12800/69092	Loss: 93.778
+16000/69092	Loss: 93.100
+19200/69092	Loss: 93.562
+22400/69092	Loss: 93.398
+25600/69092	Loss: 94.634
+28800/69092	Loss: 93.390
+32000/69092	Loss: 93.942
+35200/69092	Loss: 93.197
+38400/69092	Loss: 92.071
+41600/69092	Loss: 93.950
+44800/69092	Loss: 92.994
+48000/69092	Loss: 94.056
diff --git a/OAR.2071928.stderr b/OAR.2071928.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..b94539781871578b0885599ebe7813e2c98e69c9
--- /dev/null
+++ b/OAR.2071928.stderr
@@ -0,0 +1,10 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 394, in load_checkpoint
+    self.mean_epoch_loss = checkpoint['loss']
+KeyError: 'loss'
diff --git a/OAR.2071928.stdout b/OAR.2071928.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..1ef17703fa18f384f1248c43bb9c00235d24f317
--- /dev/null
+++ b/OAR.2071928.stdout
@@ -0,0 +1,46 @@
+Namespace(batch_size=256, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='beta_VAE_bs_256', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
diff --git a/OAR.2071929.stderr b/OAR.2071929.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a9c628a29c58ebc65df754dd5dfbbd99e2282b5f
--- /dev/null
+++ b/OAR.2071929.stderr
@@ -0,0 +1,2 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071929.stdout b/OAR.2071929.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..b21b9064a1cdc3ef62c372457a830d7be6f66708
--- /dev/null
+++ b/OAR.2071929.stdout
@@ -0,0 +1,784 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='beta_VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last (iter 768)'
+0/69092	Loss: 151.940
+3200/69092	Loss: 151.123
+6400/69092	Loss: 152.240
+9600/69092	Loss: 154.456
+12800/69092	Loss: 152.151
+16000/69092	Loss: 150.843
+19200/69092	Loss: 151.704
+22400/69092	Loss: 151.679
+25600/69092	Loss: 150.622
+28800/69092	Loss: 153.092
+32000/69092	Loss: 153.267
+35200/69092	Loss: 150.582
+38400/69092	Loss: 153.799
+41600/69092	Loss: 151.305
+44800/69092	Loss: 151.560
+48000/69092	Loss: 150.741
+51200/69092	Loss: 151.885
+54400/69092	Loss: 150.161
+57600/69092	Loss: 152.044
+60800/69092	Loss: 150.668
+64000/69092	Loss: 150.622
+67200/69092	Loss: 150.227
+Training time 0:10:39.669089
+Epoch: 1 Average loss: 151.68
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 769)
+0/69092	Loss: 159.826
+3200/69092	Loss: 155.528
+6400/69092	Loss: 153.084
+9600/69092	Loss: 152.096
+12800/69092	Loss: 152.363
+16000/69092	Loss: 150.556
+19200/69092	Loss: 148.058
+22400/69092	Loss: 152.518
+25600/69092	Loss: 151.159
+28800/69092	Loss: 153.739
+32000/69092	Loss: 149.939
+35200/69092	Loss: 152.543
+38400/69092	Loss: 151.002
+41600/69092	Loss: 151.378
+44800/69092	Loss: 149.524
+48000/69092	Loss: 152.165
+51200/69092	Loss: 151.533
+54400/69092	Loss: 148.544
+57600/69092	Loss: 152.467
+60800/69092	Loss: 153.726
+64000/69092	Loss: 151.344
+67200/69092	Loss: 154.598
+Training time 0:10:34.220042
+Epoch: 2 Average loss: 151.83
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 770)
+0/69092	Loss: 155.574
+3200/69092	Loss: 151.047
+6400/69092	Loss: 149.378
+9600/69092	Loss: 151.613
+12800/69092	Loss: 152.097
+16000/69092	Loss: 152.221
+19200/69092	Loss: 151.504
+22400/69092	Loss: 152.222
+25600/69092	Loss: 152.531
+28800/69092	Loss: 150.282
+32000/69092	Loss: 151.100
+35200/69092	Loss: 153.495
+38400/69092	Loss: 149.776
+41600/69092	Loss: 150.461
+44800/69092	Loss: 152.533
+48000/69092	Loss: 153.336
+51200/69092	Loss: 153.742
+54400/69092	Loss: 152.341
+57600/69092	Loss: 153.011
+60800/69092	Loss: 153.359
+64000/69092	Loss: 151.765
+67200/69092	Loss: 149.833
+Training time 0:10:18.548337
+Epoch: 3 Average loss: 151.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 771)
+0/69092	Loss: 149.541
+3200/69092	Loss: 150.722
+6400/69092	Loss: 152.327
+9600/69092	Loss: 148.762
+12800/69092	Loss: 150.084
+16000/69092	Loss: 151.317
+19200/69092	Loss: 151.855
+22400/69092	Loss: 151.256
+25600/69092	Loss: 153.280
+28800/69092	Loss: 152.067
+32000/69092	Loss: 154.260
+35200/69092	Loss: 147.713
+38400/69092	Loss: 152.622
+41600/69092	Loss: 152.811
+44800/69092	Loss: 151.757
+48000/69092	Loss: 152.970
+51200/69092	Loss: 150.973
+54400/69092	Loss: 150.648
+57600/69092	Loss: 152.005
+60800/69092	Loss: 152.170
+64000/69092	Loss: 152.880
+67200/69092	Loss: 152.945
+Training time 0:10:46.082361
+Epoch: 4 Average loss: 151.68
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 772)
+0/69092	Loss: 128.234
+3200/69092	Loss: 151.711
+6400/69092	Loss: 151.919
+9600/69092	Loss: 150.830
+12800/69092	Loss: 153.890
+16000/69092	Loss: 150.860
+19200/69092	Loss: 153.058
+22400/69092	Loss: 153.962
+25600/69092	Loss: 151.795
+28800/69092	Loss: 150.298
+32000/69092	Loss: 153.955
+35200/69092	Loss: 151.321
+38400/69092	Loss: 150.578
+41600/69092	Loss: 151.991
+44800/69092	Loss: 151.477
+48000/69092	Loss: 150.079
+51200/69092	Loss: 151.311
+54400/69092	Loss: 150.190
+57600/69092	Loss: 153.374
+60800/69092	Loss: 154.199
+64000/69092	Loss: 152.083
+67200/69092	Loss: 152.334
+Training time 0:10:26.629045
+Epoch: 5 Average loss: 151.90
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 773)
+0/69092	Loss: 151.981
+3200/69092	Loss: 152.328
+6400/69092	Loss: 153.386
+9600/69092	Loss: 150.931
+12800/69092	Loss: 152.916
+16000/69092	Loss: 150.853
+19200/69092	Loss: 155.195
+22400/69092	Loss: 150.530
+25600/69092	Loss: 150.215
+28800/69092	Loss: 149.994
+32000/69092	Loss: 151.922
+35200/69092	Loss: 150.617
+38400/69092	Loss: 148.687
+41600/69092	Loss: 149.949
+44800/69092	Loss: 150.374
+48000/69092	Loss: 153.431
+51200/69092	Loss: 152.256
+54400/69092	Loss: 154.912
+57600/69092	Loss: 151.775
+60800/69092	Loss: 148.809
+64000/69092	Loss: 152.993
+67200/69092	Loss: 152.113
+Training time 0:10:55.747236
+Epoch: 6 Average loss: 151.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 774)
+0/69092	Loss: 161.032
+3200/69092	Loss: 150.489
+6400/69092	Loss: 151.788
+9600/69092	Loss: 151.782
+12800/69092	Loss: 150.235
+16000/69092	Loss: 154.594
+19200/69092	Loss: 150.676
+22400/69092	Loss: 150.407
+25600/69092	Loss: 151.105
+28800/69092	Loss: 152.824
+32000/69092	Loss: 152.237
+35200/69092	Loss: 153.190
+38400/69092	Loss: 150.788
+41600/69092	Loss: 149.924
+44800/69092	Loss: 152.878
+48000/69092	Loss: 151.703
+51200/69092	Loss: 150.422
+54400/69092	Loss: 151.719
+57600/69092	Loss: 152.224
+60800/69092	Loss: 153.809
+64000/69092	Loss: 149.802
+67200/69092	Loss: 150.667
+Training time 0:10:53.402046
+Epoch: 7 Average loss: 151.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 775)
+0/69092	Loss: 150.086
+3200/69092	Loss: 153.433
+6400/69092	Loss: 150.415
+9600/69092	Loss: 153.438
+12800/69092	Loss: 149.193
+16000/69092	Loss: 151.045
+19200/69092	Loss: 148.747
+22400/69092	Loss: 151.117
+25600/69092	Loss: 150.434
+28800/69092	Loss: 150.123
+32000/69092	Loss: 152.996
+35200/69092	Loss: 152.099
+38400/69092	Loss: 151.190
+41600/69092	Loss: 152.928
+44800/69092	Loss: 152.553
+48000/69092	Loss: 151.283
+51200/69092	Loss: 152.039
+54400/69092	Loss: 151.448
+57600/69092	Loss: 151.806
+60800/69092	Loss: 150.245
+64000/69092	Loss: 152.300
+67200/69092	Loss: 152.545
+Training time 0:10:16.941117
+Epoch: 8 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 776)
+0/69092	Loss: 142.755
+3200/69092	Loss: 150.657
+6400/69092	Loss: 151.619
+9600/69092	Loss: 152.357
+12800/69092	Loss: 151.392
+16000/69092	Loss: 151.836
+19200/69092	Loss: 152.021
+22400/69092	Loss: 153.780
+25600/69092	Loss: 151.759
+28800/69092	Loss: 151.016
+32000/69092	Loss: 150.397
+35200/69092	Loss: 151.324
+38400/69092	Loss: 152.198
+41600/69092	Loss: 153.828
+44800/69092	Loss: 150.664
+48000/69092	Loss: 150.837
+51200/69092	Loss: 154.898
+54400/69092	Loss: 151.182
+57600/69092	Loss: 148.820
+60800/69092	Loss: 152.543
+64000/69092	Loss: 151.735
+67200/69092	Loss: 148.089
+Training time 0:10:28.361734
+Epoch: 9 Average loss: 151.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 777)
+0/69092	Loss: 142.051
+3200/69092	Loss: 148.852
+6400/69092	Loss: 148.513
+9600/69092	Loss: 152.910
+12800/69092	Loss: 150.108
+16000/69092	Loss: 154.028
+19200/69092	Loss: 150.451
+22400/69092	Loss: 153.521
+25600/69092	Loss: 147.976
+28800/69092	Loss: 148.766
+32000/69092	Loss: 149.970
+35200/69092	Loss: 150.618
+38400/69092	Loss: 150.971
+41600/69092	Loss: 150.817
+44800/69092	Loss: 154.553
+48000/69092	Loss: 155.033
+51200/69092	Loss: 149.239
+54400/69092	Loss: 152.046
+57600/69092	Loss: 153.721
+60800/69092	Loss: 151.871
+64000/69092	Loss: 154.558
+67200/69092	Loss: 150.223
+Training time 0:10:23.290199
+Epoch: 10 Average loss: 151.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 778)
+0/69092	Loss: 149.057
+3200/69092	Loss: 150.138
+6400/69092	Loss: 150.666
+9600/69092	Loss: 151.855
+12800/69092	Loss: 151.778
+16000/69092	Loss: 151.908
+19200/69092	Loss: 151.032
+22400/69092	Loss: 152.961
+25600/69092	Loss: 154.912
+28800/69092	Loss: 151.573
+32000/69092	Loss: 154.543
+35200/69092	Loss: 151.433
+38400/69092	Loss: 149.579
+41600/69092	Loss: 150.587
+44800/69092	Loss: 152.174
+48000/69092	Loss: 149.528
+51200/69092	Loss: 150.743
+54400/69092	Loss: 152.121
+57600/69092	Loss: 151.739
+60800/69092	Loss: 149.955
+64000/69092	Loss: 150.658
+67200/69092	Loss: 155.248
+Training time 0:10:02.301303
+Epoch: 11 Average loss: 151.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 779)
+0/69092	Loss: 152.842
+3200/69092	Loss: 152.468
+6400/69092	Loss: 149.136
+9600/69092	Loss: 152.618
+12800/69092	Loss: 150.399
+16000/69092	Loss: 153.064
+19200/69092	Loss: 151.608
+22400/69092	Loss: 152.280
+25600/69092	Loss: 150.410
+28800/69092	Loss: 152.462
+32000/69092	Loss: 149.632
+35200/69092	Loss: 151.900
+38400/69092	Loss: 148.866
+41600/69092	Loss: 153.946
+44800/69092	Loss: 153.180
+48000/69092	Loss: 152.256
+51200/69092	Loss: 150.869
+54400/69092	Loss: 151.987
+57600/69092	Loss: 151.927
+60800/69092	Loss: 150.315
+64000/69092	Loss: 152.272
+67200/69092	Loss: 150.027
+Training time 0:10:35.921149
+Epoch: 12 Average loss: 151.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 780)
+0/69092	Loss: 155.203
+3200/69092	Loss: 149.290
+6400/69092	Loss: 150.722
+9600/69092	Loss: 150.173
+12800/69092	Loss: 151.060
+16000/69092	Loss: 152.570
+19200/69092	Loss: 156.369
+22400/69092	Loss: 151.513
+25600/69092	Loss: 150.945
+28800/69092	Loss: 150.378
+32000/69092	Loss: 153.038
+35200/69092	Loss: 154.230
+38400/69092	Loss: 153.176
+41600/69092	Loss: 148.850
+44800/69092	Loss: 154.538
+48000/69092	Loss: 151.359
+51200/69092	Loss: 151.464
+54400/69092	Loss: 151.170
+57600/69092	Loss: 149.252
+60800/69092	Loss: 151.042
+64000/69092	Loss: 153.423
+67200/69092	Loss: 149.422
+Training time 0:10:31.361427
+Epoch: 13 Average loss: 151.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 781)
+0/69092	Loss: 146.776
+3200/69092	Loss: 152.727
+6400/69092	Loss: 154.581
+9600/69092	Loss: 151.684
+12800/69092	Loss: 149.094
+16000/69092	Loss: 151.217
+19200/69092	Loss: 150.166
+22400/69092	Loss: 152.380
+25600/69092	Loss: 151.874
+28800/69092	Loss: 153.713
+32000/69092	Loss: 152.922
+35200/69092	Loss: 154.464
+38400/69092	Loss: 150.433
+41600/69092	Loss: 149.945
+44800/69092	Loss: 152.313
+48000/69092	Loss: 152.333
+51200/69092	Loss: 153.386
+54400/69092	Loss: 152.386
+57600/69092	Loss: 150.411
+60800/69092	Loss: 151.260
+64000/69092	Loss: 153.093
+67200/69092	Loss: 147.063
+Training time 0:10:44.034995
+Epoch: 14 Average loss: 151.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 782)
+0/69092	Loss: 133.995
+3200/69092	Loss: 153.631
+6400/69092	Loss: 152.677
+9600/69092	Loss: 148.565
+12800/69092	Loss: 152.216
+16000/69092	Loss: 153.812
+19200/69092	Loss: 153.412
+22400/69092	Loss: 149.740
+25600/69092	Loss: 152.386
+28800/69092	Loss: 152.186
+32000/69092	Loss: 153.078
+35200/69092	Loss: 151.331
+38400/69092	Loss: 151.224
+41600/69092	Loss: 151.745
+44800/69092	Loss: 150.595
+48000/69092	Loss: 149.903
+51200/69092	Loss: 151.151
+54400/69092	Loss: 152.719
+57600/69092	Loss: 147.748
+60800/69092	Loss: 147.822
+64000/69092	Loss: 151.649
+67200/69092	Loss: 152.350
+Training time 0:10:26.490651
+Epoch: 15 Average loss: 151.37
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 783)
+0/69092	Loss: 165.291
+3200/69092	Loss: 149.069
+6400/69092	Loss: 151.144
+9600/69092	Loss: 149.362
+12800/69092	Loss: 152.472
+16000/69092	Loss: 150.844
+19200/69092	Loss: 150.975
+22400/69092	Loss: 150.666
+25600/69092	Loss: 149.360
+28800/69092	Loss: 150.892
+32000/69092	Loss: 151.124
+35200/69092	Loss: 152.196
+38400/69092	Loss: 153.774
+41600/69092	Loss: 152.521
+44800/69092	Loss: 151.684
+48000/69092	Loss: 153.329
+51200/69092	Loss: 150.415
+54400/69092	Loss: 151.445
+57600/69092	Loss: 154.007
+60800/69092	Loss: 150.657
+64000/69092	Loss: 152.308
+67200/69092	Loss: 150.726
+Training time 0:11:06.137906
+Epoch: 16 Average loss: 151.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 784)
+0/69092	Loss: 144.484
+3200/69092	Loss: 151.458
+6400/69092	Loss: 152.609
+9600/69092	Loss: 152.940
+12800/69092	Loss: 153.378
+16000/69092	Loss: 152.672
+19200/69092	Loss: 152.431
+22400/69092	Loss: 151.115
+25600/69092	Loss: 151.894
+28800/69092	Loss: 150.751
+32000/69092	Loss: 152.050
+35200/69092	Loss: 150.673
+38400/69092	Loss: 151.820
+41600/69092	Loss: 152.699
+44800/69092	Loss: 150.842
+48000/69092	Loss: 152.601
+51200/69092	Loss: 148.367
+54400/69092	Loss: 151.450
+57600/69092	Loss: 151.025
+60800/69092	Loss: 150.256
+64000/69092	Loss: 153.945
+67200/69092	Loss: 150.735
+Training time 0:10:30.921815
+Epoch: 17 Average loss: 151.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 785)
+0/69092	Loss: 149.105
+3200/69092	Loss: 154.167
+6400/69092	Loss: 150.111
+9600/69092	Loss: 150.985
+12800/69092	Loss: 151.978
+16000/69092	Loss: 151.739
+19200/69092	Loss: 153.227
+22400/69092	Loss: 150.762
+25600/69092	Loss: 153.572
+28800/69092	Loss: 151.868
+32000/69092	Loss: 152.932
+35200/69092	Loss: 150.313
+38400/69092	Loss: 149.599
+41600/69092	Loss: 151.857
+44800/69092	Loss: 152.196
+48000/69092	Loss: 151.910
+51200/69092	Loss: 149.218
+54400/69092	Loss: 151.897
+57600/69092	Loss: 152.954
+60800/69092	Loss: 149.504
+64000/69092	Loss: 152.771
+67200/69092	Loss: 151.289
+Training time 0:10:48.111194
+Epoch: 18 Average loss: 151.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 786)
+0/69092	Loss: 156.353
+3200/69092	Loss: 151.484
+6400/69092	Loss: 152.173
+9600/69092	Loss: 150.284
+12800/69092	Loss: 152.109
+16000/69092	Loss: 153.112
+19200/69092	Loss: 155.199
+22400/69092	Loss: 150.800
+25600/69092	Loss: 149.949
+28800/69092	Loss: 151.230
+32000/69092	Loss: 149.613
+35200/69092	Loss: 152.457
+38400/69092	Loss: 152.412
+41600/69092	Loss: 151.116
+44800/69092	Loss: 153.088
+48000/69092	Loss: 151.320
+51200/69092	Loss: 149.919
+54400/69092	Loss: 150.432
+57600/69092	Loss: 153.685
+60800/69092	Loss: 151.287
+64000/69092	Loss: 150.028
+67200/69092	Loss: 150.473
+Training time 0:10:12.069793
+Epoch: 19 Average loss: 151.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 787)
+0/69092	Loss: 139.116
+3200/69092	Loss: 152.967
+6400/69092	Loss: 148.803
+9600/69092	Loss: 151.478
+12800/69092	Loss: 151.373
+16000/69092	Loss: 150.007
+19200/69092	Loss: 153.504
+22400/69092	Loss: 151.458
+25600/69092	Loss: 149.068
+28800/69092	Loss: 153.966
+32000/69092	Loss: 153.562
+35200/69092	Loss: 148.962
+38400/69092	Loss: 153.138
+41600/69092	Loss: 154.136
+44800/69092	Loss: 149.912
+48000/69092	Loss: 151.040
+51200/69092	Loss: 150.974
+54400/69092	Loss: 152.708
+57600/69092	Loss: 150.486
+60800/69092	Loss: 153.213
+64000/69092	Loss: 151.913
+67200/69092	Loss: 152.005
+Training time 0:10:20.811275
+Epoch: 20 Average loss: 151.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 788)
+0/69092	Loss: 147.916
+3200/69092	Loss: 149.391
+6400/69092	Loss: 150.723
+9600/69092	Loss: 152.174
+12800/69092	Loss: 151.629
+16000/69092	Loss: 153.353
+19200/69092	Loss: 151.887
+22400/69092	Loss: 150.459
+25600/69092	Loss: 152.292
+28800/69092	Loss: 151.080
+32000/69092	Loss: 154.926
+35200/69092	Loss: 150.486
+38400/69092	Loss: 151.631
+41600/69092	Loss: 150.604
+44800/69092	Loss: 151.841
+48000/69092	Loss: 151.894
+51200/69092	Loss: 149.205
+54400/69092	Loss: 151.854
+57600/69092	Loss: 150.251
+60800/69092	Loss: 149.714
+64000/69092	Loss: 152.077
+67200/69092	Loss: 152.032
+Training time 0:10:11.770670
+Epoch: 21 Average loss: 151.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 789)
+0/69092	Loss: 164.078
+3200/69092	Loss: 151.525
+6400/69092	Loss: 153.988
+9600/69092	Loss: 149.142
+12800/69092	Loss: 151.592
+16000/69092	Loss: 151.993
+19200/69092	Loss: 150.118
+22400/69092	Loss: 150.498
+25600/69092	Loss: 151.343
+28800/69092	Loss: 153.764
+32000/69092	Loss: 150.852
+35200/69092	Loss: 152.486
+38400/69092	Loss: 152.394
+41600/69092	Loss: 150.734
+44800/69092	Loss: 151.284
+48000/69092	Loss: 152.597
+51200/69092	Loss: 150.589
+54400/69092	Loss: 150.206
+57600/69092	Loss: 151.417
+60800/69092	Loss: 151.005
+64000/69092	Loss: 153.224
+67200/69092	Loss: 153.169
+Training time 0:10:33.472371
+Epoch: 22 Average loss: 151.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 790)
+0/69092	Loss: 145.559
+3200/69092	Loss: 150.164
+6400/69092	Loss: 151.514
+9600/69092	Loss: 151.173
+12800/69092	Loss: 152.271
+16000/69092	Loss: 153.139
+19200/69092	Loss: 150.887
+22400/69092	Loss: 150.752
+25600/69092	Loss: 152.485
+28800/69092	Loss: 151.779
+32000/69092	Loss: 151.846
+35200/69092	Loss: 152.138
+38400/69092	Loss: 154.723
+41600/69092	Loss: 152.015
+44800/69092	Loss: 152.515
+48000/69092	Loss: 151.063
+51200/69092	Loss: 154.114
+54400/69092	Loss: 151.833
+57600/69092	Loss: 148.895
+60800/69092	Loss: 149.349
+64000/69092	Loss: 151.584
+67200/69092	Loss: 148.678
+Training time 0:09:53.632891
+Epoch: 23 Average loss: 151.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 791)
+0/69092	Loss: 135.151
+3200/69092	Loss: 150.026
+6400/69092	Loss: 149.487
+9600/69092	Loss: 152.590
+12800/69092	Loss: 150.973
+16000/69092	Loss: 150.229
+19200/69092	Loss: 148.999
+22400/69092	Loss: 147.100
+25600/69092	Loss: 153.667
+28800/69092	Loss: 152.520
+32000/69092	Loss: 152.234
+35200/69092	Loss: 153.836
+38400/69092	Loss: 150.599
+41600/69092	Loss: 153.598
+44800/69092	Loss: 153.442
+48000/69092	Loss: 151.034
+51200/69092	Loss: 151.636
+54400/69092	Loss: 150.366
+57600/69092	Loss: 152.079
+60800/69092	Loss: 155.366
+64000/69092	Loss: 152.208
+67200/69092	Loss: 154.034
+Training time 0:11:00.856151
+Epoch: 24 Average loss: 151.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 792)
+0/69092	Loss: 148.839
+3200/69092	Loss: 150.547
+6400/69092	Loss: 152.331
+9600/69092	Loss: 150.041
+12800/69092	Loss: 149.418
+16000/69092	Loss: 148.857
+19200/69092	Loss: 151.414
+22400/69092	Loss: 152.656
+25600/69092	Loss: 150.780
+28800/69092	Loss: 151.046
+32000/69092	Loss: 152.391
+35200/69092	Loss: 152.347
+38400/69092	Loss: 151.635
+41600/69092	Loss: 151.890
+44800/69092	Loss: 154.596
+48000/69092	Loss: 149.873
+51200/69092	Loss: 150.918
+54400/69092	Loss: 151.772
+57600/69092	Loss: 152.508
+60800/69092	Loss: 151.179
+64000/69092	Loss: 152.463
+67200/69092	Loss: 152.157
+Training time 0:11:03.146948
+Epoch: 25 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 793)
+0/69092	Loss: 161.401
+3200/69092	Loss: 149.583
+6400/69092	Loss: 153.927
+9600/69092	Loss: 151.978
+12800/69092	Loss: 148.130
+16000/69092	Loss: 150.961
+19200/69092	Loss: 152.851
+22400/69092	Loss: 152.051
+25600/69092	Loss: 151.571
+28800/69092	Loss: 154.100
+32000/69092	Loss: 151.094
+35200/69092	Loss: 155.622
+38400/69092	Loss: 149.063
+41600/69092	Loss: 149.194
+44800/69092	Loss: 152.503
+48000/69092	Loss: 151.265
+51200/69092	Loss: 150.613
+54400/69092	Loss: 150.716
+57600/69092	Loss: 151.582
+60800/69092	Loss: 152.828
+64000/69092	Loss: 152.323
+67200/69092	Loss: 151.812
+Training time 0:10:32.774337
+Epoch: 26 Average loss: 151.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 794)
+0/69092	Loss: 161.924
+3200/69092	Loss: 150.709
+6400/69092	Loss: 148.974
+9600/69092	Loss: 150.561
+12800/69092	Loss: 151.155
+16000/69092	Loss: 153.755
+19200/69092	Loss: 153.586
+22400/69092	Loss: 152.655
+25600/69092	Loss: 152.570
+28800/69092	Loss: 153.050
+32000/69092	Loss: 152.711
+35200/69092	Loss: 151.796
+38400/69092	Loss: 151.566
+41600/69092	Loss: 151.215
+44800/69092	Loss: 151.070
+48000/69092	Loss: 152.138
+51200/69092	Loss: 151.314
+54400/69092	Loss: 151.994
+57600/69092	Loss: 149.981
+60800/69092	Loss: 149.437
+64000/69092	Loss: 149.455
+67200/69092	Loss: 154.203
+Training time 0:10:02.543376
+Epoch: 27 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 795)
+0/69092	Loss: 144.700
+3200/69092	Loss: 150.546
+6400/69092	Loss: 151.705
+9600/69092	Loss: 151.077
+12800/69092	Loss: 151.864
+16000/69092	Loss: 151.946
+19200/69092	Loss: 150.677
+22400/69092	Loss: 150.169
+25600/69092	Loss: 148.889
+28800/69092	Loss: 154.708
+32000/69092	Loss: 151.943
+35200/69092	Loss: 152.121
+38400/69092	Loss: 152.201
+41600/69092	Loss: 152.669
+44800/69092	Loss: 152.839
+48000/69092	Loss: 154.190
+51200/69092	Loss: 150.046
+54400/69092	Loss: 150.808
+57600/69092	Loss: 153.924
+60800/69092	Loss: 149.571
+64000/69092	Loss: 151.539
+67200/69092	Loss: 149.816
+Training time 0:10:12.554327
+Epoch: 28 Average loss: 151.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 796)
+0/69092	Loss: 159.629
+3200/69092	Loss: 151.190
+6400/69092	Loss: 152.045
+9600/69092	Loss: 151.655
+12800/69092	Loss: 149.766
+16000/69092	Loss: 150.414
+19200/69092	Loss: 151.565
+22400/69092	Loss: 149.433
+25600/69092	Loss: 154.225
+28800/69092	Loss: 153.969
+32000/69092	Loss: 148.928
+35200/69092	Loss: 150.995
+38400/69092	Loss: 150.903
+41600/69092	Loss: 149.831
+44800/69092	Loss: 152.827
+48000/69092	Loss: 150.649
+51200/69092	Loss: 152.855
+54400/69092	Loss: 152.803
+57600/69092	Loss: 151.228
+60800/69092	Loss: 151.632
+64000/69092	Loss: 151.694
+67200/69092	Loss: 151.580
+Training time 0:10:29.073350
+Epoch: 29 Average loss: 151.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 797)
+0/69092	Loss: 153.443
+3200/69092	Loss: 152.324
+6400/69092	Loss: 150.465
+9600/69092	Loss: 149.903
+12800/69092	Loss: 152.710
+16000/69092	Loss: 149.294
+19200/69092	Loss: 150.507
+22400/69092	Loss: 150.007
+25600/69092	Loss: 151.076
+28800/69092	Loss: 150.543
+32000/69092	Loss: 152.231
+35200/69092	Loss: 151.692
diff --git a/OAR.2071930.stderr b/OAR.2071930.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a9c628a29c58ebc65df754dd5dfbbd99e2282b5f
--- /dev/null
+++ b/OAR.2071930.stderr
@@ -0,0 +1,2 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071930.stdout b/OAR.2071930.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..46e50419e9ff8f4dd8a795e2e0621850c0216a68
--- /dev/null
+++ b/OAR.2071930.stdout
@@ -0,0 +1,319 @@
+Namespace(batch_size=256, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='VAE_bs_256', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last (iter 698)'
+0/69092	Loss: 108.257
+12800/69092	Loss: 111.037
+25600/69092	Loss: 111.303
+38400/69092	Loss: 111.113
+51200/69092	Loss: 110.736
+64000/69092	Loss: 111.199
+Training time 0:10:21.698606
+Epoch: 1 Average loss: 111.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 699)
+0/69092	Loss: 104.603
+12800/69092	Loss: 111.150
+25600/69092	Loss: 110.834
+38400/69092	Loss: 111.260
+51200/69092	Loss: 111.194
+64000/69092	Loss: 111.373
+Training time 0:10:20.675258
+Epoch: 2 Average loss: 111.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 700)
+0/69092	Loss: 111.066
+12800/69092	Loss: 111.171
+25600/69092	Loss: 111.355
+38400/69092	Loss: 111.289
+51200/69092	Loss: 110.907
+64000/69092	Loss: 111.152
+Training time 0:09:57.137305
+Epoch: 3 Average loss: 111.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 701)
+0/69092	Loss: 112.474
+12800/69092	Loss: 110.678
+25600/69092	Loss: 111.427
+38400/69092	Loss: 111.644
+51200/69092	Loss: 111.016
+64000/69092	Loss: 111.316
+Training time 0:10:35.748850
+Epoch: 4 Average loss: 111.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 702)
+0/69092	Loss: 109.716
+12800/69092	Loss: 111.310
+25600/69092	Loss: 111.895
+38400/69092	Loss: 110.686
+51200/69092	Loss: 111.364
+64000/69092	Loss: 111.271
+Training time 0:10:36.029432
+Epoch: 5 Average loss: 111.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 703)
+0/69092	Loss: 112.889
+12800/69092	Loss: 111.197
+25600/69092	Loss: 110.554
+38400/69092	Loss: 111.645
+51200/69092	Loss: 110.559
+64000/69092	Loss: 111.748
+Training time 0:10:28.903556
+Epoch: 6 Average loss: 111.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 704)
+0/69092	Loss: 109.053
+12800/69092	Loss: 111.012
+25600/69092	Loss: 110.963
+38400/69092	Loss: 111.352
+51200/69092	Loss: 112.067
+64000/69092	Loss: 110.935
+Training time 0:10:12.876278
+Epoch: 7 Average loss: 111.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 705)
+0/69092	Loss: 105.232
+12800/69092	Loss: 110.625
+25600/69092	Loss: 111.185
+38400/69092	Loss: 111.544
+51200/69092	Loss: 110.688
+64000/69092	Loss: 111.145
+Training time 0:10:17.070023
+Epoch: 8 Average loss: 111.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 706)
+0/69092	Loss: 110.348
+12800/69092	Loss: 110.485
+25600/69092	Loss: 111.852
+38400/69092	Loss: 111.109
+51200/69092	Loss: 111.071
+64000/69092	Loss: 111.193
+Training time 0:10:13.666167
+Epoch: 9 Average loss: 111.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 707)
+0/69092	Loss: 111.819
+12800/69092	Loss: 110.953
+25600/69092	Loss: 111.249
+38400/69092	Loss: 111.333
+51200/69092	Loss: 110.671
+64000/69092	Loss: 111.599
+Training time 0:10:25.411552
+Epoch: 10 Average loss: 111.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 708)
+0/69092	Loss: 109.143
+12800/69092	Loss: 111.175
+25600/69092	Loss: 111.717
+38400/69092	Loss: 110.971
+51200/69092	Loss: 111.052
+64000/69092	Loss: 111.495
+Training time 0:09:47.203189
+Epoch: 11 Average loss: 111.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 709)
+0/69092	Loss: 109.594
+12800/69092	Loss: 111.242
+25600/69092	Loss: 111.338
+38400/69092	Loss: 111.486
+51200/69092	Loss: 111.300
+64000/69092	Loss: 110.529
+Training time 0:10:34.029615
+Epoch: 12 Average loss: 111.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 710)
+0/69092	Loss: 112.388
+12800/69092	Loss: 111.593
+25600/69092	Loss: 111.454
+38400/69092	Loss: 110.729
+51200/69092	Loss: 111.548
+64000/69092	Loss: 110.343
+Training time 0:09:57.117715
+Epoch: 13 Average loss: 111.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 711)
+0/69092	Loss: 108.358
+12800/69092	Loss: 110.723
+25600/69092	Loss: 110.354
+38400/69092	Loss: 111.101
+51200/69092	Loss: 111.659
+64000/69092	Loss: 112.200
+Training time 0:10:32.154893
+Epoch: 14 Average loss: 111.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 712)
+0/69092	Loss: 115.446
+12800/69092	Loss: 110.808
+25600/69092	Loss: 111.401
+38400/69092	Loss: 111.777
+51200/69092	Loss: 111.487
+64000/69092	Loss: 110.340
+Training time 0:10:10.584737
+Epoch: 15 Average loss: 111.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 713)
+0/69092	Loss: 108.508
+12800/69092	Loss: 111.041
+25600/69092	Loss: 111.330
+38400/69092	Loss: 111.807
+51200/69092	Loss: 110.823
+64000/69092	Loss: 111.151
+Training time 0:10:14.803333
+Epoch: 16 Average loss: 111.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 714)
+0/69092	Loss: 112.184
+12800/69092	Loss: 109.998
+25600/69092	Loss: 110.801
+38400/69092	Loss: 111.722
+51200/69092	Loss: 111.301
+64000/69092	Loss: 111.610
+Training time 0:10:35.918923
+Epoch: 17 Average loss: 111.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 715)
+0/69092	Loss: 111.794
+12800/69092	Loss: 111.958
+25600/69092	Loss: 110.631
+38400/69092	Loss: 110.767
+51200/69092	Loss: 110.908
+64000/69092	Loss: 111.484
+Training time 0:10:23.342858
+Epoch: 18 Average loss: 111.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 716)
+0/69092	Loss: 111.656
+12800/69092	Loss: 110.986
+25600/69092	Loss: 111.361
+38400/69092	Loss: 110.774
+51200/69092	Loss: 111.714
+64000/69092	Loss: 110.844
+Training time 0:10:23.680008
+Epoch: 19 Average loss: 111.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 717)
+0/69092	Loss: 111.053
+12800/69092	Loss: 110.972
+25600/69092	Loss: 110.889
+38400/69092	Loss: 110.627
+51200/69092	Loss: 110.883
+64000/69092	Loss: 111.855
+Training time 0:10:05.521272
+Epoch: 20 Average loss: 111.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 718)
+0/69092	Loss: 114.731
+12800/69092	Loss: 110.582
+25600/69092	Loss: 110.897
+38400/69092	Loss: 111.680
+51200/69092	Loss: 111.049
+64000/69092	Loss: 110.636
+Training time 0:09:57.470885
+Epoch: 21 Average loss: 110.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 719)
+0/69092	Loss: 107.406
+12800/69092	Loss: 111.142
+25600/69092	Loss: 110.856
+38400/69092	Loss: 110.898
+51200/69092	Loss: 111.567
+64000/69092	Loss: 110.952
+Training time 0:10:21.494861
+Epoch: 22 Average loss: 111.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 720)
+0/69092	Loss: 110.198
+12800/69092	Loss: 111.221
+25600/69092	Loss: 110.645
+38400/69092	Loss: 111.540
+51200/69092	Loss: 110.118
+64000/69092	Loss: 111.931
+Training time 0:10:36.660048
+Epoch: 23 Average loss: 111.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 721)
+0/69092	Loss: 111.275
+12800/69092	Loss: 111.169
+25600/69092	Loss: 110.754
+38400/69092	Loss: 110.518
+51200/69092	Loss: 110.996
+64000/69092	Loss: 110.942
+Training time 0:10:24.377103
+Epoch: 24 Average loss: 111.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 722)
+0/69092	Loss: 109.891
+12800/69092	Loss: 111.340
+25600/69092	Loss: 110.879
+38400/69092	Loss: 110.899
+51200/69092	Loss: 111.343
+64000/69092	Loss: 110.808
+Training time 0:10:52.849173
+Epoch: 25 Average loss: 111.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 723)
+0/69092	Loss: 114.979
+12800/69092	Loss: 110.284
+25600/69092	Loss: 111.689
+38400/69092	Loss: 110.894
+51200/69092	Loss: 110.399
+64000/69092	Loss: 111.512
+Training time 0:10:33.774797
+Epoch: 26 Average loss: 111.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 724)
+0/69092	Loss: 109.348
+12800/69092	Loss: 111.616
+25600/69092	Loss: 111.608
+38400/69092	Loss: 110.426
+51200/69092	Loss: 111.261
+64000/69092	Loss: 110.918
+Training time 0:10:14.889610
+Epoch: 27 Average loss: 111.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 725)
+0/69092	Loss: 102.225
+12800/69092	Loss: 111.153
+25600/69092	Loss: 110.742
+38400/69092	Loss: 111.073
+51200/69092	Loss: 111.250
+64000/69092	Loss: 111.164
+Training time 0:10:20.088056
+Epoch: 28 Average loss: 111.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 726)
+0/69092	Loss: 109.719
+12800/69092	Loss: 110.633
+25600/69092	Loss: 111.668
+38400/69092	Loss: 110.447
+51200/69092	Loss: 110.795
+64000/69092	Loss: 110.865
+Training time 0:10:19.927331
+Epoch: 29 Average loss: 110.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 727)
+0/69092	Loss: 106.510
+12800/69092	Loss: 110.479
+25600/69092	Loss: 111.096
+38400/69092	Loss: 111.419
+51200/69092	Loss: 111.554
+64000/69092	Loss: 110.890
+Training time 0:10:14.306920
+Epoch: 30 Average loss: 111.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 728)
+0/69092	Loss: 109.131
+12800/69092	Loss: 111.285
diff --git a/OAR.2071931.stderr b/OAR.2071931.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a9c628a29c58ebc65df754dd5dfbbd99e2282b5f
--- /dev/null
+++ b/OAR.2071931.stderr
@@ -0,0 +1,2 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071931.stdout b/OAR.2071931.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..a18f71b5dc40dd79af6548131a4043a3fc664f68
--- /dev/null
+++ b/OAR.2071931.stdout
@@ -0,0 +1,965 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last (iter 893)'
+0/69092	Loss: 96.506
+3200/69092	Loss: 107.976
+6400/69092	Loss: 111.118
+9600/69092	Loss: 109.679
+12800/69092	Loss: 111.490
+16000/69092	Loss: 110.653
+19200/69092	Loss: 110.753
+22400/69092	Loss: 110.464
+25600/69092	Loss: 108.793
+28800/69092	Loss: 111.036
+32000/69092	Loss: 109.287
+35200/69092	Loss: 111.332
+38400/69092	Loss: 110.710
+41600/69092	Loss: 110.470
+44800/69092	Loss: 108.910
+48000/69092	Loss: 109.653
+51200/69092	Loss: 110.298
+54400/69092	Loss: 111.237
+57600/69092	Loss: 108.088
+60800/69092	Loss: 108.456
+64000/69092	Loss: 108.938
+67200/69092	Loss: 110.837
+Training time 0:08:08.135205
+Epoch: 1 Average loss: 110.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 894)
+0/69092	Loss: 102.102
+3200/69092	Loss: 109.706
+6400/69092	Loss: 112.744
+9600/69092	Loss: 110.252
+12800/69092	Loss: 109.895
+16000/69092	Loss: 109.431
+19200/69092	Loss: 109.181
+22400/69092	Loss: 109.455
+25600/69092	Loss: 109.177
+28800/69092	Loss: 109.263
+32000/69092	Loss: 110.940
+35200/69092	Loss: 111.500
+38400/69092	Loss: 110.274
+41600/69092	Loss: 109.270
+44800/69092	Loss: 109.507
+48000/69092	Loss: 109.601
+51200/69092	Loss: 108.849
+54400/69092	Loss: 110.087
+57600/69092	Loss: 110.105
+60800/69092	Loss: 109.624
+64000/69092	Loss: 109.683
+67200/69092	Loss: 108.176
+Training time 0:08:38.014367
+Epoch: 2 Average loss: 109.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 895)
+0/69092	Loss: 110.342
+3200/69092	Loss: 110.021
+6400/69092	Loss: 109.821
+9600/69092	Loss: 110.290
+12800/69092	Loss: 109.858
+16000/69092	Loss: 109.090
+19200/69092	Loss: 111.522
+22400/69092	Loss: 108.451
+25600/69092	Loss: 109.246
+28800/69092	Loss: 111.043
+32000/69092	Loss: 112.258
+35200/69092	Loss: 109.115
+38400/69092	Loss: 110.949
+41600/69092	Loss: 109.815
+44800/69092	Loss: 108.342
+48000/69092	Loss: 110.874
+51200/69092	Loss: 110.267
+54400/69092	Loss: 110.616
+57600/69092	Loss: 109.410
+60800/69092	Loss: 109.178
+64000/69092	Loss: 108.993
+67200/69092	Loss: 108.393
+Training time 0:08:26.658550
+Epoch: 3 Average loss: 109.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 896)
+0/69092	Loss: 106.450
+3200/69092	Loss: 108.478
+6400/69092	Loss: 109.268
+9600/69092	Loss: 107.994
+12800/69092	Loss: 109.262
+16000/69092	Loss: 110.297
+19200/69092	Loss: 109.548
+22400/69092	Loss: 110.925
+25600/69092	Loss: 110.579
+28800/69092	Loss: 109.089
+32000/69092	Loss: 111.086
+35200/69092	Loss: 110.345
+38400/69092	Loss: 108.975
+41600/69092	Loss: 108.031
+44800/69092	Loss: 110.949
+48000/69092	Loss: 108.343
+51200/69092	Loss: 110.290
+54400/69092	Loss: 112.152
+57600/69092	Loss: 111.389
+60800/69092	Loss: 108.413
+64000/69092	Loss: 109.156
+67200/69092	Loss: 110.323
+Training time 0:08:14.276140
+Epoch: 4 Average loss: 109.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 897)
+0/69092	Loss: 111.066
+3200/69092	Loss: 108.904
+6400/69092	Loss: 111.266
+9600/69092	Loss: 110.323
+12800/69092	Loss: 109.788
+16000/69092	Loss: 110.000
+19200/69092	Loss: 109.390
+22400/69092	Loss: 111.585
+25600/69092	Loss: 107.813
+28800/69092	Loss: 109.511
+32000/69092	Loss: 109.187
+35200/69092	Loss: 108.621
+38400/69092	Loss: 108.665
+41600/69092	Loss: 110.370
+44800/69092	Loss: 109.704
+48000/69092	Loss: 109.402
+51200/69092	Loss: 108.475
+54400/69092	Loss: 111.507
+57600/69092	Loss: 109.633
+60800/69092	Loss: 111.263
+64000/69092	Loss: 110.222
+67200/69092	Loss: 109.318
+Training time 0:08:35.101683
+Epoch: 5 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 898)
+0/69092	Loss: 102.434
+3200/69092	Loss: 108.549
+6400/69092	Loss: 110.515
+9600/69092	Loss: 109.571
+12800/69092	Loss: 108.974
+16000/69092	Loss: 108.870
+19200/69092	Loss: 110.333
+22400/69092	Loss: 108.688
+25600/69092	Loss: 109.629
+28800/69092	Loss: 109.930
+32000/69092	Loss: 109.784
+35200/69092	Loss: 110.607
+38400/69092	Loss: 109.851
+41600/69092	Loss: 110.287
+44800/69092	Loss: 109.118
+48000/69092	Loss: 111.187
+51200/69092	Loss: 110.033
+54400/69092	Loss: 109.707
+57600/69092	Loss: 111.196
+60800/69092	Loss: 112.121
+64000/69092	Loss: 111.448
+67200/69092	Loss: 110.298
+Training time 0:08:24.229024
+Epoch: 6 Average loss: 110.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 899)
+0/69092	Loss: 106.925
+3200/69092	Loss: 110.441
+6400/69092	Loss: 110.143
+9600/69092	Loss: 108.793
+12800/69092	Loss: 110.355
+16000/69092	Loss: 110.902
+19200/69092	Loss: 111.763
+22400/69092	Loss: 110.550
+25600/69092	Loss: 110.683
+28800/69092	Loss: 110.057
+32000/69092	Loss: 110.056
+35200/69092	Loss: 109.016
+38400/69092	Loss: 108.872
+41600/69092	Loss: 111.028
+44800/69092	Loss: 108.918
+48000/69092	Loss: 109.556
+51200/69092	Loss: 110.492
+54400/69092	Loss: 109.169
+57600/69092	Loss: 109.681
+60800/69092	Loss: 110.108
+64000/69092	Loss: 106.451
+67200/69092	Loss: 111.016
+Training time 0:08:12.867429
+Epoch: 7 Average loss: 109.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 900)
+0/69092	Loss: 104.499
+3200/69092	Loss: 110.522
+6400/69092	Loss: 109.600
+9600/69092	Loss: 109.528
+12800/69092	Loss: 109.834
+16000/69092	Loss: 110.322
+19200/69092	Loss: 110.263
+22400/69092	Loss: 110.173
+25600/69092	Loss: 111.851
+28800/69092	Loss: 108.172
+32000/69092	Loss: 108.699
+35200/69092	Loss: 108.834
+38400/69092	Loss: 109.039
+41600/69092	Loss: 110.192
+44800/69092	Loss: 110.667
+48000/69092	Loss: 109.423
+51200/69092	Loss: 109.373
+54400/69092	Loss: 109.808
+57600/69092	Loss: 109.878
+60800/69092	Loss: 109.106
+64000/69092	Loss: 109.970
+67200/69092	Loss: 111.754
+Training time 0:08:15.733421
+Epoch: 8 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 901)
+0/69092	Loss: 109.801
+3200/69092	Loss: 107.471
+6400/69092	Loss: 110.665
+9600/69092	Loss: 109.222
+12800/69092	Loss: 109.381
+16000/69092	Loss: 109.497
+19200/69092	Loss: 109.513
+22400/69092	Loss: 110.913
+25600/69092	Loss: 110.735
+28800/69092	Loss: 108.249
+32000/69092	Loss: 109.736
+35200/69092	Loss: 108.231
+38400/69092	Loss: 110.026
+41600/69092	Loss: 108.559
+44800/69092	Loss: 109.407
+48000/69092	Loss: 109.920
+51200/69092	Loss: 111.791
+54400/69092	Loss: 109.308
+57600/69092	Loss: 111.891
+60800/69092	Loss: 109.453
+64000/69092	Loss: 110.515
+67200/69092	Loss: 109.339
+Training time 0:08:38.954356
+Epoch: 9 Average loss: 109.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 902)
+0/69092	Loss: 96.886
+3200/69092	Loss: 108.678
+6400/69092	Loss: 109.940
+9600/69092	Loss: 109.740
+12800/69092	Loss: 109.167
+16000/69092	Loss: 109.458
+19200/69092	Loss: 111.670
+22400/69092	Loss: 110.005
+25600/69092	Loss: 108.490
+28800/69092	Loss: 110.023
+32000/69092	Loss: 111.877
+35200/69092	Loss: 110.076
+38400/69092	Loss: 108.383
+41600/69092	Loss: 110.857
+44800/69092	Loss: 108.288
+48000/69092	Loss: 111.406
+51200/69092	Loss: 112.466
+54400/69092	Loss: 109.424
+57600/69092	Loss: 108.588
+60800/69092	Loss: 110.404
+64000/69092	Loss: 111.132
+67200/69092	Loss: 110.336
+Training time 0:08:27.222467
+Epoch: 10 Average loss: 109.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 903)
+0/69092	Loss: 117.604
+3200/69092	Loss: 109.267
+6400/69092	Loss: 109.354
+9600/69092	Loss: 108.803
+12800/69092	Loss: 110.667
+16000/69092	Loss: 109.150
+19200/69092	Loss: 109.900
+22400/69092	Loss: 110.840
+25600/69092	Loss: 108.930
+28800/69092	Loss: 109.228
+32000/69092	Loss: 109.978
+35200/69092	Loss: 108.748
+38400/69092	Loss: 108.769
+41600/69092	Loss: 111.524
+44800/69092	Loss: 110.138
+48000/69092	Loss: 111.239
+51200/69092	Loss: 108.361
+54400/69092	Loss: 110.076
+57600/69092	Loss: 112.542
+60800/69092	Loss: 109.636
+64000/69092	Loss: 108.758
+67200/69092	Loss: 108.637
+Training time 0:08:13.154020
+Epoch: 11 Average loss: 109.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 904)
+0/69092	Loss: 108.394
+3200/69092	Loss: 109.591
+6400/69092	Loss: 109.260
+9600/69092	Loss: 109.824
+12800/69092	Loss: 108.291
+16000/69092	Loss: 109.754
+19200/69092	Loss: 109.808
+22400/69092	Loss: 110.037
+25600/69092	Loss: 110.108
+28800/69092	Loss: 109.019
+32000/69092	Loss: 109.431
+35200/69092	Loss: 110.360
+38400/69092	Loss: 109.336
+41600/69092	Loss: 108.839
+44800/69092	Loss: 111.310
+48000/69092	Loss: 110.200
+51200/69092	Loss: 109.521
+54400/69092	Loss: 111.582
+57600/69092	Loss: 110.712
+60800/69092	Loss: 109.611
+64000/69092	Loss: 109.852
+67200/69092	Loss: 107.889
+Training time 0:08:30.258220
+Epoch: 12 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 905)
+0/69092	Loss: 108.899
+3200/69092	Loss: 110.286
+6400/69092	Loss: 110.807
+9600/69092	Loss: 109.053
+12800/69092	Loss: 110.819
+16000/69092	Loss: 109.535
+19200/69092	Loss: 109.243
+22400/69092	Loss: 111.400
+25600/69092	Loss: 109.584
+28800/69092	Loss: 109.922
+32000/69092	Loss: 109.843
+35200/69092	Loss: 110.877
+38400/69092	Loss: 109.381
+41600/69092	Loss: 108.467
+44800/69092	Loss: 110.268
+48000/69092	Loss: 108.943
+51200/69092	Loss: 107.386
+54400/69092	Loss: 110.501
+57600/69092	Loss: 110.936
+60800/69092	Loss: 107.051
+64000/69092	Loss: 109.743
+67200/69092	Loss: 110.801
+Training time 0:08:34.919019
+Epoch: 13 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 906)
+0/69092	Loss: 106.480
+3200/69092	Loss: 108.637
+6400/69092	Loss: 111.363
+9600/69092	Loss: 108.151
+12800/69092	Loss: 111.287
+16000/69092	Loss: 109.215
+19200/69092	Loss: 110.570
+22400/69092	Loss: 109.414
+25600/69092	Loss: 110.231
+28800/69092	Loss: 108.371
+32000/69092	Loss: 110.356
+35200/69092	Loss: 108.899
+38400/69092	Loss: 111.158
+41600/69092	Loss: 109.454
+44800/69092	Loss: 109.332
+48000/69092	Loss: 110.420
+51200/69092	Loss: 109.121
+54400/69092	Loss: 110.583
+57600/69092	Loss: 111.224
+60800/69092	Loss: 111.062
+64000/69092	Loss: 107.604
+67200/69092	Loss: 109.295
+Training time 0:08:12.988694
+Epoch: 14 Average loss: 109.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 907)
+0/69092	Loss: 113.552
+3200/69092	Loss: 109.272
+6400/69092	Loss: 109.035
+9600/69092	Loss: 110.843
+12800/69092	Loss: 108.581
+16000/69092	Loss: 110.015
+19200/69092	Loss: 109.440
+22400/69092	Loss: 108.619
+25600/69092	Loss: 108.504
+28800/69092	Loss: 110.964
+32000/69092	Loss: 110.685
+35200/69092	Loss: 110.124
+38400/69092	Loss: 109.331
+41600/69092	Loss: 109.444
+44800/69092	Loss: 110.493
+48000/69092	Loss: 109.717
+51200/69092	Loss: 110.052
+54400/69092	Loss: 109.734
+57600/69092	Loss: 110.113
+60800/69092	Loss: 110.238
+64000/69092	Loss: 110.355
+67200/69092	Loss: 110.088
+Training time 0:08:17.855916
+Epoch: 15 Average loss: 109.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 908)
+0/69092	Loss: 115.582
+3200/69092	Loss: 111.049
+6400/69092	Loss: 108.889
+9600/69092	Loss: 110.467
+12800/69092	Loss: 109.753
+16000/69092	Loss: 109.980
+19200/69092	Loss: 110.101
+22400/69092	Loss: 108.659
+25600/69092	Loss: 109.954
+28800/69092	Loss: 110.273
+32000/69092	Loss: 111.276
+35200/69092	Loss: 110.227
+38400/69092	Loss: 109.020
+41600/69092	Loss: 109.429
+44800/69092	Loss: 109.395
+48000/69092	Loss: 108.223
+51200/69092	Loss: 111.319
+54400/69092	Loss: 109.162
+57600/69092	Loss: 107.795
+60800/69092	Loss: 109.384
+64000/69092	Loss: 109.929
+67200/69092	Loss: 110.769
+Training time 0:08:22.153288
+Epoch: 16 Average loss: 109.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 909)
+0/69092	Loss: 110.604
+3200/69092	Loss: 109.816
+6400/69092	Loss: 110.551
+9600/69092	Loss: 108.674
+12800/69092	Loss: 109.234
+16000/69092	Loss: 110.181
+19200/69092	Loss: 109.667
+22400/69092	Loss: 110.132
+25600/69092	Loss: 109.124
+28800/69092	Loss: 109.338
+32000/69092	Loss: 110.111
+35200/69092	Loss: 110.614
+38400/69092	Loss: 110.279
+41600/69092	Loss: 108.266
+44800/69092	Loss: 109.889
+48000/69092	Loss: 111.837
+51200/69092	Loss: 110.700
+54400/69092	Loss: 109.877
+57600/69092	Loss: 110.370
+60800/69092	Loss: 109.595
+64000/69092	Loss: 107.575
+67200/69092	Loss: 107.701
+Training time 0:08:12.541597
+Epoch: 17 Average loss: 109.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 910)
+0/69092	Loss: 113.704
+3200/69092	Loss: 108.796
+6400/69092	Loss: 110.130
+9600/69092	Loss: 109.383
+12800/69092	Loss: 109.466
+16000/69092	Loss: 110.090
+19200/69092	Loss: 109.447
+22400/69092	Loss: 110.780
+25600/69092	Loss: 109.133
+28800/69092	Loss: 109.416
+32000/69092	Loss: 108.995
+35200/69092	Loss: 109.165
+38400/69092	Loss: 110.280
+41600/69092	Loss: 110.049
+44800/69092	Loss: 111.023
+48000/69092	Loss: 110.316
+51200/69092	Loss: 109.759
+54400/69092	Loss: 110.034
+57600/69092	Loss: 109.265
+60800/69092	Loss: 109.184
+64000/69092	Loss: 109.522
+67200/69092	Loss: 110.263
+Training time 0:08:14.583313
+Epoch: 18 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 911)
+0/69092	Loss: 108.895
+3200/69092	Loss: 109.986
+6400/69092	Loss: 109.630
+9600/69092	Loss: 111.963
+12800/69092	Loss: 111.758
+16000/69092	Loss: 108.648
+19200/69092	Loss: 109.151
+22400/69092	Loss: 109.271
+25600/69092	Loss: 109.333
+28800/69092	Loss: 110.728
+32000/69092	Loss: 110.444
+35200/69092	Loss: 109.595
+38400/69092	Loss: 109.363
+41600/69092	Loss: 110.533
+44800/69092	Loss: 108.189
+48000/69092	Loss: 108.910
+51200/69092	Loss: 110.093
+54400/69092	Loss: 108.096
+57600/69092	Loss: 109.775
+60800/69092	Loss: 109.771
+64000/69092	Loss: 111.250
+67200/69092	Loss: 109.601
+Training time 0:08:31.719230
+Epoch: 19 Average loss: 109.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 912)
+0/69092	Loss: 120.258
+3200/69092	Loss: 109.774
+6400/69092	Loss: 109.994
+9600/69092	Loss: 109.507
+12800/69092	Loss: 109.003
+16000/69092	Loss: 108.244
+19200/69092	Loss: 108.104
+22400/69092	Loss: 108.867
+25600/69092	Loss: 110.178
+28800/69092	Loss: 110.568
+32000/69092	Loss: 110.986
+35200/69092	Loss: 109.078
+38400/69092	Loss: 110.728
+41600/69092	Loss: 109.283
+44800/69092	Loss: 108.889
+48000/69092	Loss: 110.796
+51200/69092	Loss: 109.935
+54400/69092	Loss: 111.437
+57600/69092	Loss: 108.444
+60800/69092	Loss: 111.464
+64000/69092	Loss: 110.165
+67200/69092	Loss: 111.627
+Training time 0:08:23.221328
+Epoch: 20 Average loss: 109.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 913)
+0/69092	Loss: 108.357
+3200/69092	Loss: 111.646
+6400/69092	Loss: 108.523
+9600/69092	Loss: 110.985
+12800/69092	Loss: 110.621
+16000/69092	Loss: 109.441
+19200/69092	Loss: 110.316
+22400/69092	Loss: 109.373
+25600/69092	Loss: 108.827
+28800/69092	Loss: 109.140
+32000/69092	Loss: 107.578
+35200/69092	Loss: 111.282
+38400/69092	Loss: 109.706
+41600/69092	Loss: 108.787
+44800/69092	Loss: 110.955
+48000/69092	Loss: 110.700
+51200/69092	Loss: 109.682
+54400/69092	Loss: 110.392
+57600/69092	Loss: 109.227
+60800/69092	Loss: 109.500
+64000/69092	Loss: 108.587
+67200/69092	Loss: 108.766
+Training time 0:08:15.513935
+Epoch: 21 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 914)
+0/69092	Loss: 108.012
+3200/69092	Loss: 109.785
+6400/69092	Loss: 108.768
+9600/69092	Loss: 107.534
+12800/69092	Loss: 108.122
+16000/69092	Loss: 108.332
+19200/69092	Loss: 110.009
+22400/69092	Loss: 109.827
+25600/69092	Loss: 109.433
+28800/69092	Loss: 110.671
+32000/69092	Loss: 108.734
+35200/69092	Loss: 108.370
+38400/69092	Loss: 110.615
+41600/69092	Loss: 111.236
+44800/69092	Loss: 110.378
+48000/69092	Loss: 110.068
+51200/69092	Loss: 110.537
+54400/69092	Loss: 109.612
+57600/69092	Loss: 108.842
+60800/69092	Loss: 109.957
+64000/69092	Loss: 110.722
+67200/69092	Loss: 109.085
+Training time 0:08:29.323857
+Epoch: 22 Average loss: 109.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 915)
+0/69092	Loss: 98.606
+3200/69092	Loss: 111.806
+6400/69092	Loss: 108.681
+9600/69092	Loss: 110.218
+12800/69092	Loss: 111.459
+16000/69092	Loss: 110.256
+19200/69092	Loss: 109.856
+22400/69092	Loss: 108.792
+25600/69092	Loss: 109.350
+28800/69092	Loss: 109.909
+32000/69092	Loss: 109.159
+35200/69092	Loss: 110.690
+38400/69092	Loss: 108.486
+41600/69092	Loss: 109.467
+44800/69092	Loss: 108.747
+48000/69092	Loss: 111.261
+51200/69092	Loss: 109.100
+54400/69092	Loss: 109.166
+57600/69092	Loss: 110.897
+60800/69092	Loss: 109.595
+64000/69092	Loss: 110.913
+67200/69092	Loss: 110.218
+Training time 0:08:43.886611
+Epoch: 23 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 916)
+0/69092	Loss: 102.628
+3200/69092	Loss: 109.790
+6400/69092	Loss: 110.513
+9600/69092	Loss: 109.577
+12800/69092	Loss: 110.755
+16000/69092	Loss: 109.130
+19200/69092	Loss: 109.957
+22400/69092	Loss: 108.203
+25600/69092	Loss: 111.515
+28800/69092	Loss: 108.747
+32000/69092	Loss: 109.503
+35200/69092	Loss: 110.292
+38400/69092	Loss: 111.143
+41600/69092	Loss: 108.800
+44800/69092	Loss: 111.631
+48000/69092	Loss: 109.205
+51200/69092	Loss: 109.387
+54400/69092	Loss: 109.282
+57600/69092	Loss: 111.000
+60800/69092	Loss: 109.470
+64000/69092	Loss: 108.622
+67200/69092	Loss: 108.642
+Training time 0:08:17.169422
+Epoch: 24 Average loss: 109.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 917)
+0/69092	Loss: 112.609
+3200/69092	Loss: 109.214
+6400/69092	Loss: 110.045
+9600/69092	Loss: 110.177
+12800/69092	Loss: 110.006
+16000/69092	Loss: 110.071
+19200/69092	Loss: 110.067
+22400/69092	Loss: 111.286
+25600/69092	Loss: 109.371
+28800/69092	Loss: 108.579
+32000/69092	Loss: 109.009
+35200/69092	Loss: 109.586
+38400/69092	Loss: 111.596
+41600/69092	Loss: 109.845
+44800/69092	Loss: 108.395
+48000/69092	Loss: 109.349
+51200/69092	Loss: 110.376
+54400/69092	Loss: 110.299
+57600/69092	Loss: 108.934
+60800/69092	Loss: 109.750
+64000/69092	Loss: 109.232
+67200/69092	Loss: 109.902
+Training time 0:08:24.376567
+Epoch: 25 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 918)
+0/69092	Loss: 101.586
+3200/69092	Loss: 109.017
+6400/69092	Loss: 110.772
+9600/69092	Loss: 110.224
+12800/69092	Loss: 108.636
+16000/69092	Loss: 109.983
+19200/69092	Loss: 110.476
+22400/69092	Loss: 110.637
+25600/69092	Loss: 109.178
+28800/69092	Loss: 110.094
+32000/69092	Loss: 109.600
+35200/69092	Loss: 108.152
+38400/69092	Loss: 109.064
+41600/69092	Loss: 110.805
+44800/69092	Loss: 109.737
+48000/69092	Loss: 109.623
+51200/69092	Loss: 108.737
+54400/69092	Loss: 110.510
+57600/69092	Loss: 108.234
+60800/69092	Loss: 109.183
+64000/69092	Loss: 111.722
+67200/69092	Loss: 108.152
+Training time 0:08:37.100633
+Epoch: 26 Average loss: 109.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 919)
+0/69092	Loss: 106.414
+3200/69092	Loss: 109.265
+6400/69092	Loss: 109.205
+9600/69092	Loss: 109.474
+12800/69092	Loss: 109.728
+16000/69092	Loss: 108.176
+19200/69092	Loss: 110.381
+22400/69092	Loss: 110.187
+25600/69092	Loss: 110.399
+28800/69092	Loss: 110.505
+32000/69092	Loss: 107.933
+35200/69092	Loss: 109.721
+38400/69092	Loss: 109.225
+41600/69092	Loss: 112.266
+44800/69092	Loss: 108.616
+48000/69092	Loss: 110.297
+51200/69092	Loss: 110.420
+54400/69092	Loss: 111.526
+57600/69092	Loss: 108.996
+60800/69092	Loss: 109.643
+64000/69092	Loss: 109.631
+67200/69092	Loss: 109.490
+Training time 0:08:26.801735
+Epoch: 27 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 920)
+0/69092	Loss: 115.588
+3200/69092	Loss: 108.981
+6400/69092	Loss: 111.154
+9600/69092	Loss: 110.157
+12800/69092	Loss: 109.135
+16000/69092	Loss: 110.038
+19200/69092	Loss: 109.615
+22400/69092	Loss: 109.590
+25600/69092	Loss: 110.713
+28800/69092	Loss: 107.865
+32000/69092	Loss: 109.370
+35200/69092	Loss: 108.198
+38400/69092	Loss: 108.758
+41600/69092	Loss: 111.193
+44800/69092	Loss: 108.665
+48000/69092	Loss: 108.259
+51200/69092	Loss: 110.544
+54400/69092	Loss: 110.299
+57600/69092	Loss: 110.564
+60800/69092	Loss: 108.609
+64000/69092	Loss: 108.380
+67200/69092	Loss: 111.460
+Training time 0:08:10.084292
+Epoch: 28 Average loss: 109.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 921)
+0/69092	Loss: 115.302
+3200/69092	Loss: 108.736
+6400/69092	Loss: 109.284
+9600/69092	Loss: 109.514
+12800/69092	Loss: 110.094
+16000/69092	Loss: 108.533
+19200/69092	Loss: 109.507
+22400/69092	Loss: 109.770
+25600/69092	Loss: 110.592
+28800/69092	Loss: 110.646
+32000/69092	Loss: 109.315
+35200/69092	Loss: 109.352
+38400/69092	Loss: 108.755
+41600/69092	Loss: 111.472
+44800/69092	Loss: 110.371
+48000/69092	Loss: 109.554
+51200/69092	Loss: 108.482
+54400/69092	Loss: 108.490
+57600/69092	Loss: 110.220
+60800/69092	Loss: 109.001
+64000/69092	Loss: 110.251
+67200/69092	Loss: 110.991
+Training time 0:08:33.553547
+Epoch: 29 Average loss: 109.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 922)
+0/69092	Loss: 109.241
+3200/69092	Loss: 108.647
+6400/69092	Loss: 108.049
+9600/69092	Loss: 109.502
+12800/69092	Loss: 109.735
+16000/69092	Loss: 111.508
+19200/69092	Loss: 110.922
+22400/69092	Loss: 109.205
+25600/69092	Loss: 109.838
+28800/69092	Loss: 110.626
+32000/69092	Loss: 109.786
+35200/69092	Loss: 110.763
+38400/69092	Loss: 109.427
+41600/69092	Loss: 108.606
+44800/69092	Loss: 109.792
+48000/69092	Loss: 109.158
+51200/69092	Loss: 110.283
+54400/69092	Loss: 109.445
+57600/69092	Loss: 110.223
+60800/69092	Loss: 108.971
+64000/69092	Loss: 111.724
+67200/69092	Loss: 109.088
+Training time 0:08:27.126029
+Epoch: 30 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 923)
+0/69092	Loss: 116.686
+3200/69092	Loss: 110.322
+6400/69092	Loss: 109.907
+9600/69092	Loss: 109.940
+12800/69092	Loss: 111.581
+16000/69092	Loss: 109.236
+19200/69092	Loss: 108.935
+22400/69092	Loss: 108.903
+25600/69092	Loss: 110.447
+28800/69092	Loss: 108.463
+32000/69092	Loss: 110.719
+35200/69092	Loss: 108.835
+38400/69092	Loss: 110.248
+41600/69092	Loss: 110.756
+44800/69092	Loss: 108.916
+48000/69092	Loss: 109.694
+51200/69092	Loss: 109.632
+54400/69092	Loss: 109.935
+57600/69092	Loss: 110.132
+60800/69092	Loss: 110.983
+64000/69092	Loss: 109.134
+67200/69092	Loss: 109.580
+Training time 0:08:20.480800
+Epoch: 31 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 924)
+0/69092	Loss: 110.905
+3200/69092	Loss: 109.653
+6400/69092	Loss: 109.556
+9600/69092	Loss: 110.120
+12800/69092	Loss: 109.615
+16000/69092	Loss: 111.569
+19200/69092	Loss: 110.255
+22400/69092	Loss: 107.942
+25600/69092	Loss: 110.008
+28800/69092	Loss: 108.796
+32000/69092	Loss: 110.053
+35200/69092	Loss: 109.828
+38400/69092	Loss: 109.237
+41600/69092	Loss: 109.805
+44800/69092	Loss: 108.382
+48000/69092	Loss: 109.038
+51200/69092	Loss: 110.557
+54400/69092	Loss: 110.062
+57600/69092	Loss: 108.280
+60800/69092	Loss: 110.407
+64000/69092	Loss: 109.928
+67200/69092	Loss: 108.921
+Training time 0:08:20.143426
+Epoch: 32 Average loss: 109.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 925)
+0/69092	Loss: 114.821
+3200/69092	Loss: 108.729
+6400/69092	Loss: 110.943
+9600/69092	Loss: 108.081
+12800/69092	Loss: 108.091
+16000/69092	Loss: 109.974
+19200/69092	Loss: 110.299
+22400/69092	Loss: 110.198
+25600/69092	Loss: 109.387
+28800/69092	Loss: 109.245
+32000/69092	Loss: 110.016
+35200/69092	Loss: 109.274
+38400/69092	Loss: 109.848
+41600/69092	Loss: 109.667
+44800/69092	Loss: 109.867
+48000/69092	Loss: 108.490
+51200/69092	Loss: 110.273
+54400/69092	Loss: 110.828
+57600/69092	Loss: 110.311
+60800/69092	Loss: 109.978
+64000/69092	Loss: 110.202
+67200/69092	Loss: 109.773
+Training time 0:08:29.862622
+Epoch: 33 Average loss: 109.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 926)
+0/69092	Loss: 106.247
+3200/69092	Loss: 109.189
+6400/69092	Loss: 110.799
+9600/69092	Loss: 111.419
+12800/69092	Loss: 108.602
+16000/69092	Loss: 110.871
+19200/69092	Loss: 108.889
+22400/69092	Loss: 106.634
+25600/69092	Loss: 109.990
+28800/69092	Loss: 111.041
+32000/69092	Loss: 110.678
+35200/69092	Loss: 108.914
+38400/69092	Loss: 111.101
+41600/69092	Loss: 108.035
+44800/69092	Loss: 110.859
+48000/69092	Loss: 109.421
+51200/69092	Loss: 109.238
+54400/69092	Loss: 109.267
+57600/69092	Loss: 109.837
+60800/69092	Loss: 108.726
+64000/69092	Loss: 110.032
+67200/69092	Loss: 109.824
+Training time 0:08:21.746606
+Epoch: 34 Average loss: 109.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 927)
+0/69092	Loss: 113.420
+3200/69092	Loss: 108.717
+6400/69092	Loss: 109.250
+9600/69092	Loss: 108.531
+12800/69092	Loss: 111.823
+16000/69092	Loss: 108.119
+19200/69092	Loss: 110.376
+22400/69092	Loss: 108.626
+25600/69092	Loss: 110.165
+28800/69092	Loss: 109.598
+32000/69092	Loss: 109.473
+35200/69092	Loss: 109.605
+38400/69092	Loss: 108.955
+41600/69092	Loss: 108.566
+44800/69092	Loss: 108.869
+48000/69092	Loss: 109.015
+51200/69092	Loss: 109.486
+54400/69092	Loss: 108.909
+57600/69092	Loss: 109.819
+60800/69092	Loss: 112.781
+64000/69092	Loss: 110.751
+67200/69092	Loss: 110.591
+Training time 0:08:09.939992
+Epoch: 35 Average loss: 109.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 928)
+0/69092	Loss: 112.473
+3200/69092	Loss: 108.880
+6400/69092	Loss: 110.422
+9600/69092	Loss: 108.548
+12800/69092	Loss: 108.895
+16000/69092	Loss: 108.475
+19200/69092	Loss: 109.079
+22400/69092	Loss: 109.963
+25600/69092	Loss: 110.722
+28800/69092	Loss: 109.424
+32000/69092	Loss: 110.036
+35200/69092	Loss: 109.287
+38400/69092	Loss: 110.355
+41600/69092	Loss: 109.804
+44800/69092	Loss: 110.613
+48000/69092	Loss: 108.773
+51200/69092	Loss: 108.909
+54400/69092	Loss: 108.376
+57600/69092	Loss: 109.938
+60800/69092	Loss: 111.428
+64000/69092	Loss: 111.244
+67200/69092	Loss: 109.535
+Training time 0:08:34.925414
+Epoch: 36 Average loss: 109.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 929)
+0/69092	Loss: 104.706
+3200/69092	Loss: 108.327
+6400/69092	Loss: 108.243
+9600/69092	Loss: 109.821
+12800/69092	Loss: 111.070
+16000/69092	Loss: 108.779
+19200/69092	Loss: 109.712
+22400/69092	Loss: 109.174
+25600/69092	Loss: 111.046
+28800/69092	Loss: 109.639
+32000/69092	Loss: 109.781
+35200/69092	Loss: 108.534
+38400/69092	Loss: 110.820
+41600/69092	Loss: 111.755
+44800/69092	Loss: 107.944
+48000/69092	Loss: 112.064
+51200/69092	Loss: 110.967
+54400/69092	Loss: 109.786
diff --git a/OAR.2071932.stderr b/OAR.2071932.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a9c628a29c58ebc65df754dd5dfbbd99e2282b5f
--- /dev/null
+++ b/OAR.2071932.stderr
@@ -0,0 +1,2 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
diff --git a/OAR.2071932.stdout b/OAR.2071932.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..a8cc4bdf572decb852ca3060e55f111071b181f7
--- /dev/null
+++ b/OAR.2071932.stdout
@@ -0,0 +1,909 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=400, experiment_name='beta_VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 769185
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last (iter 384)'
+0/69092	Loss: 152.361
+3200/69092	Loss: 148.499
+6400/69092	Loss: 149.480
+9600/69092	Loss: 147.846
+12800/69092	Loss: 151.184
+16000/69092	Loss: 149.320
+19200/69092	Loss: 147.923
+22400/69092	Loss: 147.379
+25600/69092	Loss: 148.429
+28800/69092	Loss: 147.844
+32000/69092	Loss: 148.419
+35200/69092	Loss: 145.906
+38400/69092	Loss: 147.226
+41600/69092	Loss: 149.770
+44800/69092	Loss: 147.473
+48000/69092	Loss: 147.804
+51200/69092	Loss: 148.531
+54400/69092	Loss: 146.512
+57600/69092	Loss: 147.608
+60800/69092	Loss: 148.155
+64000/69092	Loss: 150.530
+67200/69092	Loss: 150.236
+Training time 0:08:48.207744
+Epoch: 1 Average loss: 148.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 385)
+0/69092	Loss: 150.210
+3200/69092	Loss: 148.198
+6400/69092	Loss: 147.188
+9600/69092	Loss: 147.347
+12800/69092	Loss: 148.467
+16000/69092	Loss: 150.042
+19200/69092	Loss: 148.443
+22400/69092	Loss: 147.597
+25600/69092	Loss: 148.485
+28800/69092	Loss: 146.093
+32000/69092	Loss: 148.259
+35200/69092	Loss: 148.657
+38400/69092	Loss: 148.375
+41600/69092	Loss: 147.089
+44800/69092	Loss: 150.649
+48000/69092	Loss: 149.635
+51200/69092	Loss: 150.797
+54400/69092	Loss: 147.939
+57600/69092	Loss: 151.415
+60800/69092	Loss: 147.258
+64000/69092	Loss: 150.691
+67200/69092	Loss: 151.794
+Training time 0:08:57.550437
+Epoch: 2 Average loss: 148.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 386)
+0/69092	Loss: 152.646
+3200/69092	Loss: 148.428
+6400/69092	Loss: 146.480
+9600/69092	Loss: 147.692
+12800/69092	Loss: 144.389
+16000/69092	Loss: 148.671
+19200/69092	Loss: 149.079
+22400/69092	Loss: 151.463
+25600/69092	Loss: 148.722
+28800/69092	Loss: 148.784
+32000/69092	Loss: 148.804
+35200/69092	Loss: 148.886
+38400/69092	Loss: 149.955
+41600/69092	Loss: 149.098
+44800/69092	Loss: 148.989
+48000/69092	Loss: 147.723
+51200/69092	Loss: 149.765
+54400/69092	Loss: 151.254
+57600/69092	Loss: 151.866
+60800/69092	Loss: 147.102
+64000/69092	Loss: 146.083
+67200/69092	Loss: 147.822
+Training time 0:08:51.299947
+Epoch: 3 Average loss: 148.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 387)
+0/69092	Loss: 142.594
+3200/69092	Loss: 148.032
+6400/69092	Loss: 149.080
+9600/69092	Loss: 147.561
+12800/69092	Loss: 149.002
+16000/69092	Loss: 147.063
+19200/69092	Loss: 150.164
+22400/69092	Loss: 150.987
+25600/69092	Loss: 147.199
+28800/69092	Loss: 150.476
+32000/69092	Loss: 147.531
+35200/69092	Loss: 146.436
+38400/69092	Loss: 147.448
+41600/69092	Loss: 150.520
+44800/69092	Loss: 151.851
+48000/69092	Loss: 148.633
+51200/69092	Loss: 147.498
+54400/69092	Loss: 148.287
+57600/69092	Loss: 150.259
+60800/69092	Loss: 147.854
+64000/69092	Loss: 148.655
+67200/69092	Loss: 148.532
+Training time 0:09:12.031770
+Epoch: 4 Average loss: 148.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 388)
+0/69092	Loss: 146.292
+3200/69092	Loss: 146.458
+6400/69092	Loss: 148.207
+9600/69092	Loss: 149.125
+12800/69092	Loss: 148.913
+16000/69092	Loss: 151.184
+19200/69092	Loss: 148.501
+22400/69092	Loss: 148.748
+25600/69092	Loss: 149.945
+28800/69092	Loss: 148.486
+32000/69092	Loss: 149.766
+35200/69092	Loss: 144.062
+38400/69092	Loss: 146.422
+41600/69092	Loss: 147.301
+44800/69092	Loss: 148.002
+48000/69092	Loss: 149.905
+51200/69092	Loss: 148.207
+54400/69092	Loss: 149.714
+57600/69092	Loss: 148.578
+60800/69092	Loss: 149.743
+64000/69092	Loss: 149.386
+67200/69092	Loss: 148.032
+Training time 0:09:00.591673
+Epoch: 5 Average loss: 148.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 389)
+0/69092	Loss: 146.621
+3200/69092	Loss: 150.144
+6400/69092	Loss: 150.271
+9600/69092	Loss: 148.271
+12800/69092	Loss: 149.640
+16000/69092	Loss: 148.857
+19200/69092	Loss: 147.642
+22400/69092	Loss: 149.931
+25600/69092	Loss: 148.541
+28800/69092	Loss: 148.161
+32000/69092	Loss: 149.247
+35200/69092	Loss: 148.439
+38400/69092	Loss: 148.187
+41600/69092	Loss: 147.979
+44800/69092	Loss: 146.100
+48000/69092	Loss: 148.955
+51200/69092	Loss: 146.269
+54400/69092	Loss: 150.135
+57600/69092	Loss: 148.776
+60800/69092	Loss: 145.928
+64000/69092	Loss: 148.470
+67200/69092	Loss: 148.817
+Training time 0:08:44.529777
+Epoch: 6 Average loss: 148.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 390)
+0/69092	Loss: 141.314
+3200/69092	Loss: 150.979
+6400/69092	Loss: 147.888
+9600/69092	Loss: 149.883
+12800/69092	Loss: 146.250
+16000/69092	Loss: 149.826
+19200/69092	Loss: 147.241
+22400/69092	Loss: 149.990
+25600/69092	Loss: 149.990
+28800/69092	Loss: 148.794
+32000/69092	Loss: 145.935
+35200/69092	Loss: 149.564
+38400/69092	Loss: 150.240
+41600/69092	Loss: 148.454
+44800/69092	Loss: 150.215
+48000/69092	Loss: 148.807
+51200/69092	Loss: 148.885
+54400/69092	Loss: 147.434
+57600/69092	Loss: 148.269
+60800/69092	Loss: 146.226
+64000/69092	Loss: 148.154
+67200/69092	Loss: 147.661
+Training time 0:08:52.399564
+Epoch: 7 Average loss: 148.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 391)
+0/69092	Loss: 154.954
+3200/69092	Loss: 146.626
+6400/69092	Loss: 146.706
+9600/69092	Loss: 147.856
+12800/69092	Loss: 147.818
+16000/69092	Loss: 147.751
+19200/69092	Loss: 147.856
+22400/69092	Loss: 150.530
+25600/69092	Loss: 148.228
+28800/69092	Loss: 150.639
+32000/69092	Loss: 147.815
+35200/69092	Loss: 148.694
+38400/69092	Loss: 147.708
+41600/69092	Loss: 148.732
+44800/69092	Loss: 149.883
+48000/69092	Loss: 147.828
+51200/69092	Loss: 149.429
+54400/69092	Loss: 148.536
+57600/69092	Loss: 149.280
+60800/69092	Loss: 149.577
+64000/69092	Loss: 147.691
+67200/69092	Loss: 148.652
+Training time 0:09:05.264120
+Epoch: 8 Average loss: 148.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 392)
+0/69092	Loss: 141.132
+3200/69092	Loss: 146.203
+6400/69092	Loss: 151.039
+9600/69092	Loss: 147.543
+12800/69092	Loss: 146.663
+16000/69092	Loss: 147.522
+19200/69092	Loss: 147.544
+22400/69092	Loss: 146.566
+25600/69092	Loss: 150.070
+28800/69092	Loss: 151.101
+32000/69092	Loss: 148.373
+35200/69092	Loss: 149.597
+38400/69092	Loss: 146.910
+41600/69092	Loss: 148.381
+44800/69092	Loss: 150.115
+48000/69092	Loss: 145.903
+51200/69092	Loss: 147.350
+54400/69092	Loss: 148.460
+57600/69092	Loss: 147.940
+60800/69092	Loss: 150.142
+64000/69092	Loss: 148.387
+67200/69092	Loss: 147.158
+Training time 0:09:03.795954
+Epoch: 9 Average loss: 148.23
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 393)
+0/69092	Loss: 150.138
+3200/69092	Loss: 149.238
+6400/69092	Loss: 149.604
+9600/69092	Loss: 146.707
+12800/69092	Loss: 149.958
+16000/69092	Loss: 148.945
+19200/69092	Loss: 148.408
+22400/69092	Loss: 149.698
+25600/69092	Loss: 150.222
+28800/69092	Loss: 149.839
+32000/69092	Loss: 148.148
+35200/69092	Loss: 147.426
+38400/69092	Loss: 147.905
+41600/69092	Loss: 150.213
+44800/69092	Loss: 149.591
+48000/69092	Loss: 148.548
+51200/69092	Loss: 147.646
+54400/69092	Loss: 147.575
+57600/69092	Loss: 150.757
+60800/69092	Loss: 145.836
+64000/69092	Loss: 148.908
+67200/69092	Loss: 148.884
+Training time 0:09:06.431221
+Epoch: 10 Average loss: 148.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 394)
+0/69092	Loss: 132.612
+3200/69092	Loss: 148.859
+6400/69092	Loss: 148.332
+9600/69092	Loss: 147.848
+12800/69092	Loss: 147.987
+16000/69092	Loss: 146.405
+19200/69092	Loss: 149.743
+22400/69092	Loss: 148.967
+25600/69092	Loss: 150.643
+28800/69092	Loss: 147.096
+32000/69092	Loss: 150.261
+35200/69092	Loss: 148.284
+38400/69092	Loss: 150.075
+41600/69092	Loss: 149.636
+44800/69092	Loss: 145.665
+48000/69092	Loss: 148.471
+51200/69092	Loss: 151.987
+54400/69092	Loss: 149.194
+57600/69092	Loss: 145.463
+60800/69092	Loss: 147.419
+64000/69092	Loss: 148.302
+67200/69092	Loss: 147.979
+Training time 0:08:55.323519
+Epoch: 11 Average loss: 148.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 395)
+0/69092	Loss: 145.348
+3200/69092	Loss: 148.658
+6400/69092	Loss: 148.206
+9600/69092	Loss: 148.802
+12800/69092	Loss: 147.112
+16000/69092	Loss: 147.435
+19200/69092	Loss: 149.155
+22400/69092	Loss: 148.159
+25600/69092	Loss: 151.041
+28800/69092	Loss: 150.103
+32000/69092	Loss: 147.212
+35200/69092	Loss: 148.987
+38400/69092	Loss: 146.847
+41600/69092	Loss: 147.224
+44800/69092	Loss: 147.831
+48000/69092	Loss: 149.702
+51200/69092	Loss: 148.154
+54400/69092	Loss: 148.037
+57600/69092	Loss: 148.568
+60800/69092	Loss: 147.742
+64000/69092	Loss: 149.219
+67200/69092	Loss: 148.690
+Training time 0:09:02.812885
+Epoch: 12 Average loss: 148.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 396)
+0/69092	Loss: 142.583
+3200/69092	Loss: 148.079
+6400/69092	Loss: 148.763
+9600/69092	Loss: 149.152
+12800/69092	Loss: 148.507
+16000/69092	Loss: 149.841
+19200/69092	Loss: 148.869
+22400/69092	Loss: 149.488
+25600/69092	Loss: 148.301
+28800/69092	Loss: 149.035
+32000/69092	Loss: 148.148
+35200/69092	Loss: 146.048
+38400/69092	Loss: 149.526
+41600/69092	Loss: 145.658
+44800/69092	Loss: 148.386
+48000/69092	Loss: 150.427
+51200/69092	Loss: 150.326
+54400/69092	Loss: 145.604
+57600/69092	Loss: 148.702
+60800/69092	Loss: 151.526
+64000/69092	Loss: 147.669
+67200/69092	Loss: 148.106
+Training time 0:09:00.687459
+Epoch: 13 Average loss: 148.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 397)
+0/69092	Loss: 153.672
+3200/69092	Loss: 150.343
+6400/69092	Loss: 148.938
+9600/69092	Loss: 145.993
+12800/69092	Loss: 147.901
+16000/69092	Loss: 147.641
+19200/69092	Loss: 150.301
+22400/69092	Loss: 147.967
+25600/69092	Loss: 149.461
+28800/69092	Loss: 147.351
+32000/69092	Loss: 147.978
+35200/69092	Loss: 147.770
+38400/69092	Loss: 148.081
+41600/69092	Loss: 152.066
+44800/69092	Loss: 149.364
+48000/69092	Loss: 149.303
+51200/69092	Loss: 147.742
+54400/69092	Loss: 147.767
+57600/69092	Loss: 149.432
+60800/69092	Loss: 148.578
+64000/69092	Loss: 148.193
+67200/69092	Loss: 146.824
+Training time 0:09:07.147777
+Epoch: 14 Average loss: 148.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 398)
+0/69092	Loss: 154.706
+3200/69092	Loss: 149.984
+6400/69092	Loss: 147.826
+9600/69092	Loss: 149.050
+12800/69092	Loss: 148.082
+16000/69092	Loss: 147.026
+19200/69092	Loss: 147.830
+22400/69092	Loss: 147.191
+25600/69092	Loss: 150.028
+28800/69092	Loss: 147.502
+32000/69092	Loss: 148.913
+35200/69092	Loss: 147.774
+38400/69092	Loss: 146.584
+41600/69092	Loss: 147.086
+44800/69092	Loss: 151.431
+48000/69092	Loss: 148.993
+51200/69092	Loss: 147.126
+54400/69092	Loss: 149.061
+57600/69092	Loss: 149.496
+60800/69092	Loss: 150.705
+64000/69092	Loss: 149.200
+67200/69092	Loss: 147.942
+Training time 0:08:47.208411
+Epoch: 15 Average loss: 148.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 399)
+0/69092	Loss: 162.081
+3200/69092	Loss: 146.958
+6400/69092	Loss: 147.251
+9600/69092	Loss: 147.883
+12800/69092	Loss: 145.721
+16000/69092	Loss: 145.575
+19200/69092	Loss: 151.240
+22400/69092	Loss: 147.378
+25600/69092	Loss: 149.983
+28800/69092	Loss: 148.666
+32000/69092	Loss: 148.957
+35200/69092	Loss: 147.893
+38400/69092	Loss: 150.558
+41600/69092	Loss: 148.435
+44800/69092	Loss: 149.339
+48000/69092	Loss: 148.824
+51200/69092	Loss: 146.886
+54400/69092	Loss: 147.452
+57600/69092	Loss: 147.164
+60800/69092	Loss: 148.653
+64000/69092	Loss: 147.348
+67200/69092	Loss: 150.272
+Training time 0:08:54.783178
+Epoch: 16 Average loss: 148.19
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 400)
+0/69092	Loss: 148.374
+3200/69092	Loss: 148.049
+6400/69092	Loss: 150.116
+9600/69092	Loss: 143.784
+12800/69092	Loss: 146.203
+16000/69092	Loss: 148.805
+19200/69092	Loss: 149.583
+22400/69092	Loss: 147.258
+25600/69092	Loss: 147.839
+28800/69092	Loss: 149.711
+32000/69092	Loss: 147.253
+35200/69092	Loss: 149.489
+38400/69092	Loss: 147.980
+41600/69092	Loss: 149.826
+44800/69092	Loss: 149.049
+48000/69092	Loss: 148.529
+51200/69092	Loss: 148.352
+54400/69092	Loss: 149.552
+57600/69092	Loss: 148.745
+60800/69092	Loss: 147.908
+64000/69092	Loss: 150.221
+67200/69092	Loss: 148.150
+Training time 0:08:46.326460
+Epoch: 17 Average loss: 148.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 401)
+0/69092	Loss: 148.667
+3200/69092	Loss: 148.798
+6400/69092	Loss: 147.345
+9600/69092	Loss: 151.147
+12800/69092	Loss: 147.851
+16000/69092	Loss: 148.137
+19200/69092	Loss: 147.272
+22400/69092	Loss: 151.296
+25600/69092	Loss: 148.091
+28800/69092	Loss: 146.713
+32000/69092	Loss: 148.339
+35200/69092	Loss: 149.853
+38400/69092	Loss: 148.396
+41600/69092	Loss: 148.286
+44800/69092	Loss: 149.332
+48000/69092	Loss: 147.071
+51200/69092	Loss: 146.582
+54400/69092	Loss: 148.309
+57600/69092	Loss: 147.126
+60800/69092	Loss: 148.934
+64000/69092	Loss: 150.969
+67200/69092	Loss: 149.921
+Training time 0:08:52.783104
+Epoch: 18 Average loss: 148.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 402)
+0/69092	Loss: 160.845
+3200/69092	Loss: 147.069
+6400/69092	Loss: 145.704
+9600/69092	Loss: 148.991
+12800/69092	Loss: 149.128
+16000/69092	Loss: 148.295
+19200/69092	Loss: 146.797
+22400/69092	Loss: 148.149
+25600/69092	Loss: 149.634
+28800/69092	Loss: 146.860
+32000/69092	Loss: 146.170
+35200/69092	Loss: 148.381
+38400/69092	Loss: 146.985
+41600/69092	Loss: 146.265
+44800/69092	Loss: 150.647
+48000/69092	Loss: 149.986
+51200/69092	Loss: 149.418
+54400/69092	Loss: 150.401
+57600/69092	Loss: 148.946
+60800/69092	Loss: 148.241
+64000/69092	Loss: 148.328
+67200/69092	Loss: 149.539
+Training time 0:08:58.246864
+Epoch: 19 Average loss: 148.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 403)
+0/69092	Loss: 148.493
+3200/69092	Loss: 150.437
+6400/69092	Loss: 147.256
+9600/69092	Loss: 150.340
+12800/69092	Loss: 145.597
+16000/69092	Loss: 143.907
+19200/69092	Loss: 147.719
+22400/69092	Loss: 149.212
+25600/69092	Loss: 147.621
+28800/69092	Loss: 149.197
+32000/69092	Loss: 148.108
+35200/69092	Loss: 148.515
+38400/69092	Loss: 147.109
+41600/69092	Loss: 150.834
+44800/69092	Loss: 146.322
+48000/69092	Loss: 147.154
+51200/69092	Loss: 150.583
+54400/69092	Loss: 150.381
+57600/69092	Loss: 147.629
+60800/69092	Loss: 148.895
+64000/69092	Loss: 149.012
+67200/69092	Loss: 150.196
+Training time 0:09:09.768489
+Epoch: 20 Average loss: 148.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 404)
+0/69092	Loss: 155.011
+3200/69092	Loss: 150.039
+6400/69092	Loss: 147.834
+9600/69092	Loss: 151.055
+12800/69092	Loss: 147.030
+16000/69092	Loss: 149.360
+19200/69092	Loss: 147.986
+22400/69092	Loss: 149.366
+25600/69092	Loss: 148.121
+28800/69092	Loss: 148.877
+32000/69092	Loss: 149.134
+35200/69092	Loss: 149.375
+38400/69092	Loss: 147.610
+41600/69092	Loss: 147.797
+44800/69092	Loss: 150.285
+48000/69092	Loss: 146.658
+51200/69092	Loss: 145.238
+54400/69092	Loss: 146.441
+57600/69092	Loss: 149.190
+60800/69092	Loss: 148.107
+64000/69092	Loss: 150.174
+67200/69092	Loss: 147.560
+Training time 0:09:02.290506
+Epoch: 21 Average loss: 148.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 405)
+0/69092	Loss: 136.954
+3200/69092	Loss: 148.606
+6400/69092	Loss: 147.706
+9600/69092	Loss: 146.021
+12800/69092	Loss: 147.506
+16000/69092	Loss: 148.935
+19200/69092	Loss: 148.701
+22400/69092	Loss: 149.310
+25600/69092	Loss: 147.547
+28800/69092	Loss: 148.972
+32000/69092	Loss: 148.618
+35200/69092	Loss: 147.854
+38400/69092	Loss: 147.932
+41600/69092	Loss: 146.946
+44800/69092	Loss: 149.427
+48000/69092	Loss: 148.953
+51200/69092	Loss: 149.170
+54400/69092	Loss: 147.848
+57600/69092	Loss: 147.531
+60800/69092	Loss: 145.401
+64000/69092	Loss: 149.425
+67200/69092	Loss: 149.049
+Training time 0:09:02.930326
+Epoch: 22 Average loss: 148.21
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 406)
+0/69092	Loss: 132.888
+3200/69092	Loss: 146.944
+6400/69092	Loss: 147.659
+9600/69092	Loss: 148.153
+12800/69092	Loss: 146.067
+16000/69092	Loss: 146.874
+19200/69092	Loss: 146.669
+22400/69092	Loss: 149.614
+25600/69092	Loss: 146.883
+28800/69092	Loss: 149.405
+32000/69092	Loss: 146.970
+35200/69092	Loss: 146.448
+38400/69092	Loss: 151.269
+41600/69092	Loss: 149.954
+44800/69092	Loss: 149.437
+48000/69092	Loss: 149.159
+51200/69092	Loss: 146.190
+54400/69092	Loss: 145.881
+57600/69092	Loss: 147.482
+60800/69092	Loss: 151.322
+64000/69092	Loss: 149.133
+67200/69092	Loss: 147.746
+Training time 0:08:47.872983
+Epoch: 23 Average loss: 148.16
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 407)
+0/69092	Loss: 134.402
+3200/69092	Loss: 149.188
+6400/69092	Loss: 148.388
+9600/69092	Loss: 148.458
+12800/69092	Loss: 145.928
+16000/69092	Loss: 147.602
+19200/69092	Loss: 146.478
+22400/69092	Loss: 148.272
+25600/69092	Loss: 148.289
+28800/69092	Loss: 148.099
+32000/69092	Loss: 148.887
+35200/69092	Loss: 150.344
+38400/69092	Loss: 148.626
+41600/69092	Loss: 148.378
+44800/69092	Loss: 149.421
+48000/69092	Loss: 148.677
+51200/69092	Loss: 148.167
+54400/69092	Loss: 148.458
+57600/69092	Loss: 149.659
+60800/69092	Loss: 149.415
+64000/69092	Loss: 147.444
+67200/69092	Loss: 146.036
+Training time 0:08:50.696391
+Epoch: 24 Average loss: 148.35
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 408)
+0/69092	Loss: 157.593
+3200/69092	Loss: 150.009
+6400/69092	Loss: 149.978
+9600/69092	Loss: 148.384
+12800/69092	Loss: 148.417
+16000/69092	Loss: 147.030
+19200/69092	Loss: 148.650
+22400/69092	Loss: 145.753
+25600/69092	Loss: 150.395
+28800/69092	Loss: 147.850
+32000/69092	Loss: 148.134
+35200/69092	Loss: 148.396
+38400/69092	Loss: 147.508
+41600/69092	Loss: 145.220
+44800/69092	Loss: 150.131
+48000/69092	Loss: 149.278
+51200/69092	Loss: 146.565
+54400/69092	Loss: 148.079
+57600/69092	Loss: 151.236
+60800/69092	Loss: 149.145
+64000/69092	Loss: 147.249
+67200/69092	Loss: 148.559
+Training time 0:09:07.761578
+Epoch: 25 Average loss: 148.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 409)
+0/69092	Loss: 157.040
+3200/69092	Loss: 149.437
+6400/69092	Loss: 148.512
+9600/69092	Loss: 147.398
+12800/69092	Loss: 149.228
+16000/69092	Loss: 148.261
+19200/69092	Loss: 151.086
+22400/69092	Loss: 149.001
+25600/69092	Loss: 150.663
+28800/69092	Loss: 148.152
+32000/69092	Loss: 146.417
+35200/69092	Loss: 148.666
+38400/69092	Loss: 148.263
+41600/69092	Loss: 149.578
+44800/69092	Loss: 146.636
+48000/69092	Loss: 147.623
+51200/69092	Loss: 146.347
+54400/69092	Loss: 147.707
+57600/69092	Loss: 148.565
+60800/69092	Loss: 148.173
+64000/69092	Loss: 148.738
+67200/69092	Loss: 148.175
+Training time 0:09:09.511901
+Epoch: 26 Average loss: 148.35
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 410)
+0/69092	Loss: 150.704
+3200/69092	Loss: 147.565
+6400/69092	Loss: 147.792
+9600/69092	Loss: 146.466
+12800/69092	Loss: 147.434
+16000/69092	Loss: 150.431
+19200/69092	Loss: 149.472
+22400/69092	Loss: 147.425
+25600/69092	Loss: 147.409
+28800/69092	Loss: 149.671
+32000/69092	Loss: 147.043
+35200/69092	Loss: 148.956
+38400/69092	Loss: 148.086
+41600/69092	Loss: 149.742
+44800/69092	Loss: 147.087
+48000/69092	Loss: 146.434
+51200/69092	Loss: 147.783
+54400/69092	Loss: 148.881
+57600/69092	Loss: 148.384
+60800/69092	Loss: 150.013
+64000/69092	Loss: 151.416
+67200/69092	Loss: 148.161
+Training time 0:09:05.992895
+Epoch: 27 Average loss: 148.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 411)
+0/69092	Loss: 145.985
+3200/69092	Loss: 148.648
+6400/69092	Loss: 147.020
+9600/69092	Loss: 146.654
+12800/69092	Loss: 146.435
+16000/69092	Loss: 146.639
+19200/69092	Loss: 149.927
+22400/69092	Loss: 148.067
+25600/69092	Loss: 148.626
+28800/69092	Loss: 148.934
+32000/69092	Loss: 149.611
+35200/69092	Loss: 147.454
+38400/69092	Loss: 146.692
+41600/69092	Loss: 147.571
+44800/69092	Loss: 148.395
+48000/69092	Loss: 149.005
+51200/69092	Loss: 149.284
+54400/69092	Loss: 150.009
+57600/69092	Loss: 148.238
+60800/69092	Loss: 148.752
+64000/69092	Loss: 152.488
+67200/69092	Loss: 148.458
+Training time 0:08:53.110724
+Epoch: 28 Average loss: 148.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 412)
+0/69092	Loss: 140.530
+3200/69092	Loss: 149.617
+6400/69092	Loss: 148.875
+9600/69092	Loss: 148.385
+12800/69092	Loss: 145.872
+16000/69092	Loss: 147.475
+19200/69092	Loss: 148.305
+22400/69092	Loss: 150.160
+25600/69092	Loss: 147.275
+28800/69092	Loss: 149.528
+32000/69092	Loss: 147.095
+35200/69092	Loss: 145.753
+38400/69092	Loss: 151.182
+41600/69092	Loss: 148.270
+44800/69092	Loss: 149.513
+48000/69092	Loss: 147.346
+51200/69092	Loss: 147.973
+54400/69092	Loss: 148.995
+57600/69092	Loss: 149.471
+60800/69092	Loss: 146.983
+64000/69092	Loss: 147.300
+67200/69092	Loss: 150.169
+Training time 0:08:59.751902
+Epoch: 29 Average loss: 148.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 413)
+0/69092	Loss: 154.834
+3200/69092	Loss: 148.602
+6400/69092	Loss: 147.281
+9600/69092	Loss: 148.257
+12800/69092	Loss: 148.066
+16000/69092	Loss: 149.303
+19200/69092	Loss: 147.593
+22400/69092	Loss: 150.067
+25600/69092	Loss: 148.943
+28800/69092	Loss: 149.007
+32000/69092	Loss: 149.917
+35200/69092	Loss: 148.033
+38400/69092	Loss: 147.071
+41600/69092	Loss: 145.994
+44800/69092	Loss: 149.236
+48000/69092	Loss: 150.653
+51200/69092	Loss: 147.954
+54400/69092	Loss: 148.355
+57600/69092	Loss: 148.669
+60800/69092	Loss: 148.295
+64000/69092	Loss: 145.584
+67200/69092	Loss: 148.381
+Training time 0:08:53.192705
+Epoch: 30 Average loss: 148.28
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 414)
+0/69092	Loss: 147.329
+3200/69092	Loss: 150.836
+6400/69092	Loss: 148.322
+9600/69092	Loss: 147.041
+12800/69092	Loss: 150.053
+16000/69092	Loss: 148.353
+19200/69092	Loss: 149.621
+22400/69092	Loss: 149.111
+25600/69092	Loss: 146.548
+28800/69092	Loss: 148.025
+32000/69092	Loss: 146.271
+35200/69092	Loss: 146.669
+38400/69092	Loss: 148.178
+41600/69092	Loss: 147.295
+44800/69092	Loss: 150.026
+48000/69092	Loss: 147.352
+51200/69092	Loss: 148.345
+54400/69092	Loss: 149.542
+57600/69092	Loss: 149.092
+60800/69092	Loss: 145.997
+64000/69092	Loss: 149.676
+67200/69092	Loss: 148.665
+Training time 0:09:05.739956
+Epoch: 31 Average loss: 148.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 415)
+0/69092	Loss: 151.837
+3200/69092	Loss: 147.201
+6400/69092	Loss: 149.816
+9600/69092	Loss: 149.556
+12800/69092	Loss: 148.716
+16000/69092	Loss: 147.223
+19200/69092	Loss: 146.076
+22400/69092	Loss: 148.112
+25600/69092	Loss: 148.333
+28800/69092	Loss: 149.023
+32000/69092	Loss: 148.763
+35200/69092	Loss: 148.995
+38400/69092	Loss: 145.106
+41600/69092	Loss: 148.213
+44800/69092	Loss: 149.859
+48000/69092	Loss: 147.339
+51200/69092	Loss: 146.453
+54400/69092	Loss: 150.950
+57600/69092	Loss: 147.687
+60800/69092	Loss: 147.135
+64000/69092	Loss: 151.026
+67200/69092	Loss: 149.801
+Training time 0:08:51.114166
+Epoch: 32 Average loss: 148.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 416)
+0/69092	Loss: 156.896
+3200/69092	Loss: 148.975
+6400/69092	Loss: 147.950
+9600/69092	Loss: 149.030
+12800/69092	Loss: 145.228
+16000/69092	Loss: 147.176
+19200/69092	Loss: 148.334
+22400/69092	Loss: 149.624
+25600/69092	Loss: 152.305
+28800/69092	Loss: 147.235
+32000/69092	Loss: 146.033
+35200/69092	Loss: 147.091
+38400/69092	Loss: 148.412
+41600/69092	Loss: 148.229
+44800/69092	Loss: 148.240
+48000/69092	Loss: 147.240
+51200/69092	Loss: 148.851
+54400/69092	Loss: 147.703
+57600/69092	Loss: 148.065
+60800/69092	Loss: 148.718
+64000/69092	Loss: 148.478
+67200/69092	Loss: 148.794
+Training time 0:09:00.180181
+Epoch: 33 Average loss: 148.26
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 417)
+0/69092	Loss: 148.454
+3200/69092	Loss: 148.839
+6400/69092	Loss: 149.033
+9600/69092	Loss: 148.163
+12800/69092	Loss: 149.427
+16000/69092	Loss: 149.431
+19200/69092	Loss: 151.534
+22400/69092	Loss: 149.696
+25600/69092	Loss: 149.770
+28800/69092	Loss: 147.351
+32000/69092	Loss: 148.725
+35200/69092	Loss: 146.890
+38400/69092	Loss: 147.490
+41600/69092	Loss: 147.314
+44800/69092	Loss: 146.463
+48000/69092	Loss: 146.713
+51200/69092	Loss: 147.816
+54400/69092	Loss: 147.123
+57600/69092	Loss: 148.996
+60800/69092	Loss: 148.508
+64000/69092	Loss: 147.167
+67200/69092	Loss: 146.828
+Training time 0:08:44.694787
+Epoch: 34 Average loss: 148.25
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 418)
+0/69092	Loss: 154.200
+3200/69092	Loss: 146.082
+6400/69092	Loss: 147.593
+9600/69092	Loss: 147.783
+12800/69092	Loss: 146.372
+16000/69092	Loss: 149.915
+19200/69092	Loss: 147.554
+22400/69092	Loss: 149.566
+25600/69092	Loss: 150.731
+28800/69092	Loss: 147.846
+32000/69092	Loss: 148.889
+35200/69092	Loss: 148.217
diff --git a/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last
index d1a87d6f3c35884bfe06323480b84a9506780b70..cb177b2a09cbbb5ec3855f67263df44ec114a168 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last
index e8fc305ece11b771a8d803775d22e57629e170e3..4f2642ad341e29f5407b4424c4b4e2123c640da4 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last
index 9b35309aa4578f2de59bce458f3fdc47ab49254a..72b2573a48d08d3e56c5496b1c132eabd5434fd4 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last
index 466b0762595ac5ab58c360abf843691dd1c4e6ed..ec60f6afe1e8e7f9ad62860e82424b6b1328e366 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last
index 4c186ac9f144c21e647e14546867ddb581b2e061..2b42d43dc2fecf682658e2bb42014de3bb47d9a5 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last b/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last
index bc31e8decd836bb7a49e930b3a502eb5219e0368..bd97a1596ce25bc80b9d7219543de89c95eb8da9 100644
Binary files a/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last and b/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last
index ca6484f67e2c8ffeb890aaa408b77ffb742e3a09..754683cd89ef435818991bf29b93f403a60bbb1c 100644
Binary files a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last and b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last differ