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, 1707.64it/s]
-     16%|#6        | 1600/10000 [00:02<00:17, 488.81it/s]
-     24%|##4       | 2400/10000 [00:03<00:10, 699.38it/s]
-     32%|###2      | 3200/10000 [00:03<00:07, 897.49it/s]
-     40%|####      | 4000/10000 [00:04<00:05, 1060.15it/s]
-     48%|####8     | 4800/10000 [00:05<00:04, 1191.03it/s]
-     56%|#####6    | 5600/10000 [00:05<00:03, 1296.38it/s]
-    reward: -2.14 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.08/6.19, grad norm= 234.64, loss_value= 349.42, loss_actor= 15.13, target value: -12.18:  56%|#####6    | 5600/10000 [00:06<00:03, 1296.38it/s]
-    reward: -2.14 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.08/6.19, grad norm= 234.64, loss_value= 349.42, loss_actor= 15.13, target value: -12.18:  64%|######4   | 6400/10000 [00:07<00:04, 889.15it/s] 
-    reward: -0.19 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.52/5.60, grad norm= 99.21, loss_value= 254.70, loss_actor= 14.22, target value: -16.14:  64%|######4   | 6400/10000 [00:07<00:04, 889.15it/s] 
-    reward: -0.19 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.52/5.60, grad norm= 99.21, loss_value= 254.70, loss_actor= 14.22, target value: -16.14:  72%|#######2  | 7200/10000 [00:08<00:03, 722.82it/s]
-    reward: -1.72 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.27/5.64, grad norm= 60.57, loss_value= 231.16, loss_actor= 11.37, target value: -13.73:  72%|#######2  | 7200/10000 [00:09<00:03, 722.82it/s]
-    reward: -1.72 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.27/5.64, grad norm= 60.57, loss_value= 231.16, loss_actor= 11.37, target value: -13.73:  80%|########  | 8000/10000 [00:10<00:03, 641.42it/s]
-    reward: -3.97 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.10/5.46, grad norm= 76.46, loss_value= 310.34, loss_actor= 16.33, target value: -14.06:  80%|########  | 8000/10000 [00:10<00:03, 641.42it/s]
-    reward: -3.97 (r0 = -2.78), reward eval: reward: -0.01, reward normalized=-2.10/5.46, grad norm= 76.46, loss_value= 310.34, loss_actor= 16.33, target value: -14.06:  88%|########8 | 8800/10000 [00:11<00:02, 598.58it/s]
-    reward: -4.50 (r0 = -2.78), reward eval: reward: -2.28, reward normalized=-2.83/5.53, grad norm= 143.03, loss_value= 314.16, loss_actor= 19.17, target value: -18.72:  88%|########8 | 8800/10000 [00:14<00:02, 598.58it/s]
-    reward: -4.50 (r0 = -2.78), reward eval: reward: -2.28, reward normalized=-2.83/5.53, grad norm= 143.03, loss_value= 314.16, loss_actor= 19.17, target value: -18.72:  96%|#########6| 9600/10000 [00:15<00:00, 404.64it/s]
-    reward: -4.74 (r0 = -2.78), reward eval: reward: -2.28, reward normalized=-3.13/4.99, grad norm= 236.04, loss_value= 236.55, loss_actor= 14.05, target value: -22.38:  96%|#########6| 9600/10000 [00:15<00:00, 404.64it/s]
-    reward: -4.74 (r0 = -2.78), reward eval: reward: -2.28, reward normalized=-3.13/4.99, grad norm= 236.04, loss_value= 236.55, loss_actor= 14.05, target value: -22.38: : 10400it [00:17, 358.82it/s]                        
-    reward: -2.65 (r0 = -2.78), reward eval: reward: -2.28, reward normalized=-2.90/4.16, grad norm= 76.19, loss_value= 143.21, loss_actor= 12.72, target value: -20.87: : 10400it [00:18, 358.82it/s] 
+      8%|8         | 800/10000 [00:00<00:05, 1703.98it/s]
+     16%|#6        | 1600/10000 [00:02<00:17, 484.88it/s]
+     24%|##4       | 2400/10000 [00:03<00:10, 699.40it/s]
+     32%|###2      | 3200/10000 [00:03<00:07, 901.42it/s]
+     40%|####      | 4000/10000 [00:04<00:05, 1070.69it/s]
+     48%|####8     | 4800/10000 [00:04<00:04, 1219.46it/s]
+     56%|#####6    | 5600/10000 [00:05<00:03, 1336.30it/s]
+    reward: -2.08 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-2.60/6.39, grad norm= 100.00, loss_value= 431.35, loss_actor= 16.48, target value: -15.57:  56%|#####6    | 5600/10000 [00:06<00:03, 1336.30it/s]
+    reward: -2.08 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-2.60/6.39, grad norm= 100.00, loss_value= 431.35, loss_actor= 16.48, target value: -15.57:  64%|######4   | 6400/10000 [00:06<00:03, 901.23it/s] 
+    reward: -0.20 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-3.16/6.03, grad norm= 379.46, loss_value= 354.63, loss_actor= 14.92, target value: -19.87:  64%|######4   | 6400/10000 [00:07<00:03, 901.23it/s]
+    reward: -0.20 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-3.16/6.03, grad norm= 379.46, loss_value= 354.63, loss_actor= 14.92, target value: -19.87:  72%|#######2  | 7200/10000 [00:08<00:03, 740.79it/s]
+    reward: -3.19 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-1.95/6.12, grad norm= 78.80, loss_value= 296.14, loss_actor= 11.28, target value: -11.78:  72%|#######2  | 7200/10000 [00:09<00:03, 740.79it/s] 
+    reward: -3.19 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-1.95/6.12, grad norm= 78.80, loss_value= 296.14, loss_actor= 11.28, target value: -11.78:  80%|########  | 8000/10000 [00:10<00:03, 652.77it/s]
+    reward: -4.73 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-2.86/5.35, grad norm= 79.71, loss_value= 225.52, loss_actor= 19.22, target value: -18.85:  80%|########  | 8000/10000 [00:10<00:03, 652.77it/s]
+    reward: -4.73 (r0 = -3.42), reward eval: reward:  0.00, reward normalized=-2.86/5.35, grad norm= 79.71, loss_value= 225.52, loss_actor= 19.22, target value: -18.85:  88%|########8 | 8800/10000 [00:11<00:01, 609.61it/s]
+    reward: -5.48 (r0 = -3.42), reward eval: reward: -5.46, reward normalized=-3.25/5.19, grad norm= 207.90, loss_value= 237.13, loss_actor= 21.20, target value: -22.06:  88%|########8 | 8800/10000 [00:14<00:01, 609.61it/s]
+    reward: -5.48 (r0 = -3.42), reward eval: reward: -5.46, reward normalized=-3.25/5.19, grad norm= 207.90, loss_value= 237.13, loss_actor= 21.20, target value: -22.06:  96%|#########6| 9600/10000 [00:14<00:00, 406.16it/s]
+    reward: -5.29 (r0 = -3.42), reward eval: reward: -5.46, reward normalized=-2.87/4.98, grad norm= 54.30, loss_value= 193.69, loss_actor= 20.55, target value: -20.42:  96%|#########6| 9600/10000 [00:15<00:00, 406.16it/s] 
+    reward: -5.29 (r0 = -3.42), reward eval: reward: -5.46, reward normalized=-2.87/4.98, grad norm= 54.30, loss_value= 193.69, loss_actor= 20.55, target value: -20.42: : 10400it [00:17, 363.51it/s]                        
+    reward: -4.67 (r0 = -3.42), reward eval: reward: -5.46, reward normalized=-3.58/4.46, grad norm= 70.11, loss_value= 183.36, loss_actor= 23.07, target value: -25.11: : 10400it [00:18, 363.51it/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  28.713 seconds)
+   **Total running time of the script:** ( 0 minutes  28.464 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): 208.2
+    elapsed time (seconds): 208.6
     loss: 5.168
-    elapsed time (seconds): 116.5
+    elapsed time (seconds): 115.2
 
 
 
@@ -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  35.389 seconds)
+   **Total running time of the script:** ( 5 minutes  34.642 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_coding_ddpg_001.png

@@ -410,36 +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         | 17.2M/548M [00:00<00:03, 181MB/s]
-      7%|6         | 35.6M/548M [00:00<00:02, 187MB/s]
-     10%|9         | 54.0M/548M [00:00<00:02, 190MB/s]
-     13%|#3        | 72.5M/548M [00:00<00:02, 191MB/s]
-     17%|#6        | 90.9M/548M [00:00<00:02, 191MB/s]
-     20%|#9        | 109M/548M [00:00<00:02, 192MB/s] 
-     23%|##3       | 128M/548M [00:00<00:02, 193MB/s]
-     27%|##6       | 146M/548M [00:00<00:02, 193MB/s]
-     30%|###       | 165M/548M [00:00<00:02, 193MB/s]
-     33%|###3      | 184M/548M [00:01<00:01, 193MB/s]
-     37%|###6      | 202M/548M [00:01<00:01, 193MB/s]
-     40%|####      | 220M/548M [00:01<00:01, 193MB/s]
-     44%|####3     | 239M/548M [00:01<00:01, 193MB/s]
-     47%|####7     | 258M/548M [00:01<00:01, 192MB/s]
-     50%|#####     | 276M/548M [00:01<00:01, 191MB/s]
-     54%|#####3    | 294M/548M [00:01<00:01, 190MB/s]
-     57%|#####7    | 313M/548M [00:01<00:01, 190MB/s]
-     60%|######    | 331M/548M [00:01<00:01, 191MB/s]
-     64%|######3   | 349M/548M [00:01<00:01, 191MB/s]
-     67%|######7   | 368M/548M [00:02<00:00, 191MB/s]
-     70%|#######   | 386M/548M [00:02<00:00, 192MB/s]
-     74%|#######3  | 405M/548M [00:02<00:00, 192MB/s]
-     77%|#######7  | 423M/548M [00:02<00:00, 192MB/s]
-     81%|########  | 442M/548M [00:02<00:00, 191MB/s]
-     84%|########3 | 460M/548M [00:02<00:00, 190MB/s]
-     87%|########7 | 478M/548M [00:02<00:00, 188MB/s]
-     90%|######### | 496M/548M [00:02<00:00, 188MB/s]
-     94%|#########3| 514M/548M [00:02<00:00, 187MB/s]
-     97%|#########7| 532M/548M [00:02<00:00, 187MB/s]
-    100%|##########| 548M/548M [00:03<00:00, 191MB/s]
+      4%|3         | 20.6M/548M [00:00<00:02, 216MB/s]
+      8%|7         | 41.9M/548M [00:00<00:02, 219MB/s]
+     12%|#1        | 63.1M/548M [00:00<00:02, 221MB/s]
+     15%|#5        | 84.6M/548M [00:00<00:02, 222MB/s]
+     19%|#9        | 106M/548M [00:00<00:02, 223MB/s] 
+     23%|##3       | 128M/548M [00:00<00:01, 223MB/s]
+     27%|##7       | 149M/548M [00:00<00:01, 224MB/s]
+     31%|###1      | 170M/548M [00:00<00:01, 224MB/s]
+     35%|###5      | 192M/548M [00:00<00:01, 224MB/s]
+     39%|###8      | 213M/548M [00:01<00:01, 224MB/s]
+     43%|####2     | 235M/548M [00:01<00:01, 225MB/s]
+     47%|####6     | 256M/548M [00:01<00:01, 225MB/s]
+     51%|#####     | 278M/548M [00:01<00:01, 225MB/s]
+     55%|#####4    | 299M/548M [00:01<00:01, 225MB/s]
+     59%|#####8    | 321M/548M [00:01<00:01, 225MB/s]
+     62%|######2   | 342M/548M [00:01<00:00, 225MB/s]
+     66%|######6   | 364M/548M [00:01<00:00, 225MB/s]
+     70%|#######   | 385M/548M [00:01<00:00, 225MB/s]
+     74%|#######4  | 407M/548M [00:01<00:00, 225MB/s]
+     78%|#######8  | 428M/548M [00:02<00:00, 225MB/s]
+     82%|########2 | 450M/548M [00:02<00:00, 224MB/s]
+     86%|########6 | 471M/548M [00:02<00:00, 225MB/s]
+     90%|########9 | 493M/548M [00:02<00:00, 225MB/s]
+     94%|#########3| 514M/548M [00:02<00:00, 225MB/s]
+     98%|#########7| 536M/548M [00:02<00:00, 225MB/s]
+    100%|##########| 548M/548M [00:02<00:00, 224MB/s]
 
 
 
@@ -760,22 +756,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 4.116919 Content Loss: 4.180849
+    Style Loss : 4.103480 Content Loss: 4.095845
 
     run [100]:
-    Style Loss : 1.130904 Content Loss: 3.026069
+    Style Loss : 1.120694 Content Loss: 3.009445
 
     run [150]:
-    Style Loss : 0.709217 Content Loss: 2.653672
+    Style Loss : 0.707350 Content Loss: 2.644475
 
     run [200]:
-    Style Loss : 0.472506 Content Loss: 2.489412
+    Style Loss : 0.476449 Content Loss: 2.486541
 
     run [250]:
-    Style Loss : 0.342615 Content Loss: 2.401286
+    Style Loss : 0.344099 Content Loss: 2.402043
 
     run [300]:
-    Style Loss : 0.263712 Content Loss: 2.348886
+    Style Loss : 0.262806 Content Loss: 2.347914
 
 
 
@@ -784,7 +780,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  38.991 seconds)
+   **Total running time of the script:** ( 0 minutes  38.521 seconds)
 
 
 .. _sphx_glr_download_advanced_neural_style_tutorial.py:

_images/sphx_glr_dqn_with_rnn_tutorial_001.png

@@ -303,7 +303,7 @@ The backward pass computes the gradient ``wrt`` the input and the gradient ``wrt
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.633 seconds)
+   **Total running time of the script:** ( 0 minutes  0.582 seconds)
 
 
 .. _sphx_glr_download_advanced_numpy_extensions_tutorial.py: