Automated tutorials push

Author: pytorchbot

_images/sphx_glr_char_rnn_classification_tutorial_001.png

@@ -1634,26 +1634,26 @@ modules we need.
 
 
       0%|          | 0/10000 [00:00<?, ?it/s]
-      8%|8         | 800/10000 [00:00<00:05, 1680.42it/s]
-     16%|#6        | 1600/10000 [00:03<00:17, 471.71it/s]
-     24%|##4       | 2400/10000 [00:03<00:11, 665.05it/s]
-     32%|###2      | 3200/10000 [00:04<00:07, 856.11it/s]
-     40%|####      | 4000/10000 [00:04<00:05, 1027.08it/s]
-     48%|####8     | 4800/10000 [00:05<00:04, 1166.85it/s]
-     56%|#####6    | 5600/10000 [00:05<00:03, 1277.85it/s]
-    reward: -2.85 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-2.54/6.66, grad norm= 155.46, loss_value= 513.11, loss_actor= 18.16, target value: -14.97:  56%|#####6    | 5600/10000 [00:06<00:03, 1277.85it/s]
-    reward: -2.85 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-2.54/6.66, grad norm= 155.46, loss_value= 513.11, loss_actor= 18.16, target value: -14.97:  64%|######4   | 6400/10000 [00:07<00:04, 849.73it/s] 
-    reward: -0.17 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-2.64/5.64, grad norm= 91.66, loss_value= 263.18, loss_actor= 15.17, target value: -16.35:  64%|######4   | 6400/10000 [00:08<00:04, 849.73it/s] 
-    reward: -0.17 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-2.64/5.64, grad norm= 91.66, loss_value= 263.18, loss_actor= 15.17, target value: -16.35:  72%|#######2  | 7200/10000 [00:08<00:03, 704.46it/s]
-    reward: -2.90 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-3.10/6.28, grad norm= 337.43, loss_value= 382.46, loss_actor= 14.87, target value: -19.26:  72%|#######2  | 7200/10000 [00:09<00:03, 704.46it/s]
-    reward: -2.90 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-3.10/6.28, grad norm= 337.43, loss_value= 382.46, loss_actor= 14.87, target value: -19.26:  80%|########  | 8000/10000 [00:10<00:03, 620.21it/s]
-    reward: -4.48 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-2.83/5.17, grad norm= 155.36, loss_value= 266.41, loss_actor= 16.28, target value: -18.26:  80%|########  | 8000/10000 [00:11<00:03, 620.21it/s]
-    reward: -4.48 (r0 = -3.05), reward eval: reward:  0.00, reward normalized=-2.83/5.17, grad norm= 155.36, loss_value= 266.41, loss_actor= 16.28, target value: -18.26:  88%|########8 | 8800/10000 [00:12<00:02, 582.56it/s]
-    reward: -5.43 (r0 = -3.05), reward eval: reward: -5.34, reward normalized=-2.46/5.01, grad norm= 233.46, loss_value= 207.46, loss_actor= 20.07, target value: -16.09:  88%|########8 | 8800/10000 [00:14<00:02, 582.56it/s]
-    reward: -5.43 (r0 = -3.05), reward eval: reward: -5.34, reward normalized=-2.46/5.01, grad norm= 233.46, loss_value= 207.46, loss_actor= 20.07, target value: -16.09:  96%|#########6| 9600/10000 [00:15<00:01, 392.16it/s]
-    reward: -5.40 (r0 = -3.05), reward eval: reward: -5.34, reward normalized=-3.72/5.35, grad norm= 273.07, loss_value= 350.02, loss_actor= 21.10, target value: -25.81:  96%|#########6| 9600/10000 [00:16<00:01, 392.16it/s]
-    reward: -5.40 (r0 = -3.05), reward eval: reward: -5.34, reward normalized=-3.72/5.35, grad norm= 273.07, loss_value= 350.02, loss_actor= 21.10, target value: -25.81: : 10400it [00:18, 360.77it/s]                        
-    reward: -4.90 (r0 = -3.05), reward eval: reward: -5.34, reward normalized=-4.18/4.47, grad norm= 120.83, loss_value= 254.43, loss_actor= 27.65, target value: -28.47: : 10400it [00:19, 360.77it/s]
+      8%|8         | 800/10000 [00:00<00:05, 1732.40it/s]
+     16%|#6        | 1600/10000 [00:02<00:17, 488.68it/s]
+     24%|##4       | 2400/10000 [00:03<00:10, 693.03it/s]
+     32%|###2      | 3200/10000 [00:04<00:07, 878.39it/s]
+     40%|####      | 4000/10000 [00:04<00:05, 1035.33it/s]
+     48%|####8     | 4800/10000 [00:05<00:04, 1177.04it/s]
+     56%|#####6    | 5600/10000 [00:05<00:03, 1283.39it/s]
+    reward: -2.12 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.19/6.34, grad norm= 169.82, loss_value= 407.42, loss_actor= 15.43, target value: -13.32:  56%|#####6    | 5600/10000 [00:06<00:03, 1283.39it/s]
+    reward: -2.12 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.19/6.34, grad norm= 169.82, loss_value= 407.42, loss_actor= 15.43, target value: -13.32:  64%|######4   | 6400/10000 [00:07<00:04, 877.86it/s] 
+    reward: -0.22 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.38/5.77, grad norm= 73.76, loss_value= 250.94, loss_actor= 14.13, target value: -16.05:  64%|######4   | 6400/10000 [00:07<00:04, 877.86it/s] 
+    reward: -0.22 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.38/5.77, grad norm= 73.76, loss_value= 250.94, loss_actor= 14.13, target value: -16.05:  72%|#######2  | 7200/10000 [00:08<00:03, 723.38it/s]
+    reward: -3.28 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.41/5.98, grad norm= 135.06, loss_value= 295.38, loss_actor= 13.13, target value: -15.44:  72%|#######2  | 7200/10000 [00:09<00:03, 723.38it/s]
+    reward: -3.28 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.41/5.98, grad norm= 135.06, loss_value= 295.38, loss_actor= 13.13, target value: -15.44:  80%|########  | 8000/10000 [00:10<00:03, 642.40it/s]
+    reward: -4.93 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.81/5.28, grad norm= 257.19, loss_value= 257.16, loss_actor= 14.93, target value: -18.10:  80%|########  | 8000/10000 [00:10<00:03, 642.40it/s]
+    reward: -4.93 (r0 = -2.92), reward eval: reward: -0.01, reward normalized=-2.81/5.28, grad norm= 257.19, loss_value= 257.16, loss_actor= 14.93, target value: -18.10:  88%|########8 | 8800/10000 [00:11<00:02, 598.47it/s]
+    reward: -4.99 (r0 = -2.92), reward eval: reward: -5.87, reward normalized=-3.09/5.10, grad norm= 126.61, loss_value= 224.68, loss_actor= 19.46, target value: -20.96:  88%|########8 | 8800/10000 [00:14<00:02, 598.47it/s]
+    reward: -4.99 (r0 = -2.92), reward eval: reward: -5.87, reward normalized=-3.09/5.10, grad norm= 126.61, loss_value= 224.68, loss_actor= 19.46, target value: -20.96:  96%|#########6| 9600/10000 [00:15<00:00, 404.31it/s]
+    reward: -5.12 (r0 = -2.92), reward eval: reward: -5.87, reward normalized=-2.99/5.42, grad norm= 104.60, loss_value= 239.53, loss_actor= 20.24, target value: -21.99:  96%|#########6| 9600/10000 [00:15<00:00, 404.31it/s]
+    reward: -5.12 (r0 = -2.92), reward eval: reward: -5.87, reward normalized=-2.99/5.42, grad norm= 104.60, loss_value= 239.53, loss_actor= 20.24, target value: -21.99: : 10400it [00:18, 356.24it/s]                        
+    reward: -4.86 (r0 = -2.92), reward eval: reward: -5.87, reward normalized=-3.77/4.27, grad norm= 89.54, loss_value= 168.68, loss_actor= 23.35, target value: -25.89: : 10400it [00:18, 356.24it/s] 
 
 
 
@@ -1723,7 +1723,7 @@ To iterate further on this loss module we might consider:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  29.113 seconds)
+   **Total running time of the script:** ( 0 minutes  28.909 seconds)
 
 
 .. _sphx_glr_download_advanced_coding_ddpg.py:

_images/sphx_glr_char_rnn_classification_tutorial_002.png

@@ -517,9 +517,9 @@ models run single threaded.
  .. code-block:: none
 
     loss: 5.167
-    elapsed time (seconds): 204.0
+    elapsed time (seconds): 199.4
     loss: 5.168
-    elapsed time (seconds): 116.6
+    elapsed time (seconds): 114.7
 
 
 
@@ -541,7 +541,7 @@ Thanks for reading! As always, we welcome any feedback, so please create an issu
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  31.500 seconds)
+   **Total running time of the script:** ( 5 minutes  24.982 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_coding_ddpg_001.png

@@ -410,38 +410,32 @@ network to evaluation mode using ``.eval()``.
     Downloading: "https://download.pytorch.org/models/vgg19-dcbb9e9d.pth" to /var/lib/ci-user/.cache/torch/hub/checkpoints/vgg19-dcbb9e9d.pth
 
       0%|          | 0.00/548M [00:00<?, ?B/s]
-      3%|3         | 16.5M/548M [00:00<00:03, 173MB/s]
-      6%|6         | 33.5M/548M [00:00<00:03, 176MB/s]
-      9%|9         | 50.5M/548M [00:00<00:02, 177MB/s]
-     12%|#2        | 67.8M/548M [00:00<00:02, 178MB/s]
-     15%|#5        | 84.9M/548M [00:00<00:02, 178MB/s]
-     19%|#8        | 102M/548M [00:00<00:02, 179MB/s] 
-     22%|##1       | 119M/548M [00:00<00:02, 179MB/s]
-     25%|##4       | 136M/548M [00:00<00:02, 179MB/s]
-     28%|##8       | 154M/548M [00:00<00:02, 179MB/s]
-     31%|###1      | 171M/548M [00:01<00:02, 179MB/s]
-     34%|###4      | 188M/548M [00:01<00:02, 179MB/s]
-     37%|###7      | 205M/548M [00:01<00:02, 179MB/s]
-     41%|####      | 222M/548M [00:01<00:01, 179MB/s]
-     44%|####3     | 239M/548M [00:01<00:01, 179MB/s]
-     47%|####6     | 256M/548M [00:01<00:01, 179MB/s]
-     50%|####9     | 274M/548M [00:01<00:01, 179MB/s]
-     53%|#####3    | 291M/548M [00:01<00:01, 179MB/s]
-     56%|#####6    | 308M/548M [00:01<00:01, 180MB/s]
-     59%|#####9    | 325M/548M [00:01<00:01, 180MB/s]
-     63%|######2   | 343M/548M [00:02<00:01, 180MB/s]
-     66%|######5   | 360M/548M [00:02<00:01, 179MB/s]
-     69%|######8   | 377M/548M [00:02<00:01, 179MB/s]
-     72%|#######1  | 394M/548M [00:02<00:00, 179MB/s]
-     75%|#######5  | 411M/548M [00:02<00:00, 179MB/s]
-     78%|#######8  | 428M/548M [00:02<00:00, 179MB/s]
-     81%|########1 | 446M/548M [00:02<00:00, 179MB/s]
-     84%|########4 | 463M/548M [00:02<00:00, 179MB/s]
-     88%|########7 | 480M/548M [00:02<00:00, 178MB/s]
-     91%|######### | 498M/548M [00:02<00:00, 181MB/s]
-     94%|#########4| 516M/548M [00:03<00:00, 184MB/s]
-     98%|#########7| 534M/548M [00:03<00:00, 186MB/s]
-    100%|##########| 548M/548M [00:03<00:00, 180MB/s]
+      4%|3         | 20.9M/548M [00:00<00:02, 218MB/s]
+      8%|7         | 42.5M/548M [00:00<00:02, 223MB/s]
+     12%|#1        | 64.1M/548M [00:00<00:02, 224MB/s]
+     16%|#5        | 85.8M/548M [00:00<00:02, 225MB/s]
+     20%|#9        | 107M/548M [00:00<00:02, 225MB/s] 
+     24%|##3       | 129M/548M [00:00<00:01, 226MB/s]
+     28%|##7       | 151M/548M [00:00<00:01, 226MB/s]
+     31%|###1      | 172M/548M [00:00<00:01, 226MB/s]
+     35%|###5      | 194M/548M [00:00<00:01, 219MB/s]
+     39%|###9      | 216M/548M [00:01<00:01, 221MB/s]
+     43%|####3     | 237M/548M [00:01<00:01, 223MB/s]
+     47%|####7     | 259M/548M [00:01<00:01, 224MB/s]
+     51%|#####1    | 281M/548M [00:01<00:01, 225MB/s]
+     55%|#####5    | 302M/548M [00:01<00:01, 225MB/s]
+     59%|#####9    | 324M/548M [00:01<00:01, 226MB/s]
+     63%|######3   | 346M/548M [00:01<00:00, 226MB/s]
+     67%|######7   | 367M/548M [00:01<00:00, 226MB/s]
+     71%|#######   | 389M/548M [00:01<00:00, 226MB/s]
+     75%|#######4  | 411M/548M [00:01<00:00, 226MB/s]
+     79%|#######8  | 432M/548M [00:02<00:00, 226MB/s]
+     83%|########2 | 454M/548M [00:02<00:00, 226MB/s]
+     87%|########6 | 476M/548M [00:02<00:00, 226MB/s]
+     91%|######### | 498M/548M [00:02<00:00, 227MB/s]
+     95%|#########4| 519M/548M [00:02<00:00, 227MB/s]
+     99%|#########8| 541M/548M [00:02<00:00, 227MB/s]
+    100%|##########| 548M/548M [00:02<00:00, 225MB/s]
 
 
 
@@ -762,22 +756,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 3.992533 Content Loss: 4.103969
+    Style Loss : 4.038539 Content Loss: 4.104365
 
     run [100]:
-    Style Loss : 1.138738 Content Loss: 3.028159
+    Style Loss : 1.119395 Content Loss: 3.013746
 
     run [150]:
-    Style Loss : 0.703683 Content Loss: 2.647084
+    Style Loss : 0.697405 Content Loss: 2.644443
 
     run [200]:
-    Style Loss : 0.469144 Content Loss: 2.487169
+    Style Loss : 0.471228 Content Loss: 2.485675
 
     run [250]:
-    Style Loss : 0.344788 Content Loss: 2.401090
+    Style Loss : 0.343578 Content Loss: 2.401301
 
     run [300]:
-    Style Loss : 0.262716 Content Loss: 2.349406
+    Style Loss : 0.261325 Content Loss: 2.348558
 
 
 
@@ -786,7 +780,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  39.124 seconds)
+   **Total running time of the script:** ( 0 minutes  38.355 seconds)
 
 
 .. _sphx_glr_download_advanced_neural_style_tutorial.py: