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, 1635.05it/s]
-     16%|#6        | 1600/10000 [00:02<00:17, 488.67it/s]
-     24%|##4       | 2400/10000 [00:03<00:10, 693.90it/s]
-     32%|###2      | 3200/10000 [00:03<00:07, 898.92it/s]
-     40%|####      | 4000/10000 [00:04<00:05, 1078.60it/s]
-     48%|####8     | 4800/10000 [00:04<00:04, 1235.64it/s]
-     56%|#####6    | 5600/10000 [00:05<00:03, 1360.94it/s]
-    reward: -2.67 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.24/6.42, grad norm= 121.21, loss_value= 442.12, loss_actor= 15.34, target value: -14.76:  56%|#####6    | 5600/10000 [00:06<00:03, 1360.94it/s]
-    reward: -2.67 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.24/6.42, grad norm= 121.21, loss_value= 442.12, loss_actor= 15.34, target value: -14.76:  64%|######4   | 6400/10000 [00:06<00:03, 932.78it/s] 
-    reward: -0.15 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.68/5.62, grad norm= 95.21, loss_value= 284.37, loss_actor= 15.45, target value: -17.78:  64%|######4   | 6400/10000 [00:07<00:03, 932.78it/s] 
-    reward: -0.15 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.68/5.62, grad norm= 95.21, loss_value= 284.37, loss_actor= 15.45, target value: -17.78:  72%|#######2  | 7200/10000 [00:08<00:03, 747.27it/s]
-    reward: -3.37 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.59/6.10, grad norm= 74.55, loss_value= 307.46, loss_actor= 14.67, target value: -15.21:  72%|#######2  | 7200/10000 [00:09<00:03, 747.27it/s]
-    reward: -3.37 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.59/6.10, grad norm= 74.55, loss_value= 307.46, loss_actor= 14.67, target value: -15.21:  80%|########  | 8000/10000 [00:09<00:03, 657.24it/s]
-    reward: -4.37 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.57/4.64, grad norm= 48.72, loss_value= 192.21, loss_actor= 17.71, target value: -17.12:  80%|########  | 8000/10000 [00:10<00:03, 657.24it/s]
-    reward: -4.37 (r0 = -3.61), reward eval: reward: -0.01, reward normalized=-2.57/4.64, grad norm= 48.72, loss_value= 192.21, loss_actor= 17.71, target value: -17.12:  88%|########8 | 8800/10000 [00:11<00:01, 608.99it/s]
-    reward: -5.41 (r0 = -3.61), reward eval: reward: -5.49, reward normalized=-2.94/5.05, grad norm= 121.34, loss_value= 215.46, loss_actor= 20.00, target value: -19.67:  88%|########8 | 8800/10000 [00:14<00:01, 608.99it/s]
-    reward: -5.41 (r0 = -3.61), reward eval: reward: -5.49, reward normalized=-2.94/5.05, grad norm= 121.34, loss_value= 215.46, loss_actor= 20.00, target value: -19.67:  96%|#########6| 9600/10000 [00:14<00:00, 410.18it/s]
-    reward: -4.46 (r0 = -3.61), reward eval: reward: -5.49, reward normalized=-3.61/5.30, grad norm= 308.88, loss_value= 336.67, loss_actor= 19.23, target value: -26.05:  96%|#########6| 9600/10000 [00:15<00:00, 410.18it/s]
-    reward: -4.46 (r0 = -3.61), reward eval: reward: -5.49, reward normalized=-3.61/5.30, grad norm= 308.88, loss_value= 336.67, loss_actor= 19.23, target value: -26.05: : 10400it [00:17, 363.84it/s]                        
-    reward: -4.49 (r0 = -3.61), reward eval: reward: -5.49, reward normalized=-3.30/3.94, grad norm= 92.94, loss_value= 152.10, loss_actor= 24.58, target value: -23.26: : 10400it [00:18, 363.84it/s] 
+      8%|8         | 800/10000 [00:00<00:05, 1780.84it/s]
+     16%|#6        | 1600/10000 [00:02<00:17, 488.94it/s]
+     24%|##4       | 2400/10000 [00:03<00:10, 705.84it/s]
+     32%|###2      | 3200/10000 [00:03<00:07, 907.78it/s]
+     40%|####      | 4000/10000 [00:04<00:05, 1075.55it/s]
+     48%|####8     | 4800/10000 [00:04<00:04, 1222.64it/s]
+     56%|#####6    | 5600/10000 [00:05<00:03, 1338.15it/s]
+    reward: -2.77 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.40/6.62, grad norm= 164.27, loss_value= 396.87, loss_actor= 12.97, target value: -15.44:  56%|#####6    | 5600/10000 [00:06<00:03, 1338.15it/s]
+    reward: -2.77 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.40/6.62, grad norm= 164.27, loss_value= 396.87, loss_actor= 12.97, target value: -15.44:  64%|######4   | 6400/10000 [00:06<00:04, 897.53it/s] 
+    reward: -0.15 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.46/5.64, grad norm= 165.72, loss_value= 260.42, loss_actor= 13.35, target value: -15.62:  64%|######4   | 6400/10000 [00:07<00:04, 897.53it/s]
+    reward: -0.15 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.46/5.64, grad norm= 165.72, loss_value= 260.42, loss_actor= 13.35, target value: -15.62:  72%|#######2  | 7200/10000 [00:08<00:03, 718.68it/s]
+    reward: -2.73 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.34/6.00, grad norm= 116.30, loss_value= 268.66, loss_actor= 13.29, target value: -15.24:  72%|#######2  | 7200/10000 [00:09<00:03, 718.68it/s]
+    reward: -2.73 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.34/6.00, grad norm= 116.30, loss_value= 268.66, loss_actor= 13.29, target value: -15.24:  80%|########  | 8000/10000 [00:10<00:03, 631.02it/s]
+    reward: -4.72 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.68/5.33, grad norm= 98.38, loss_value= 215.18, loss_actor= 17.06, target value: -17.23:  80%|########  | 8000/10000 [00:10<00:03, 631.02it/s] 
+    reward: -4.72 (r0 = -2.01), reward eval: reward: -0.00, reward normalized=-2.68/5.33, grad norm= 98.38, loss_value= 215.18, loss_actor= 17.06, target value: -17.23:  88%|########8 | 8800/10000 [00:11<00:02, 590.95it/s]
+    reward: -5.42 (r0 = -2.01), reward eval: reward: -5.04, reward normalized=-2.73/5.36, grad norm= 65.22, loss_value= 257.60, loss_actor= 20.45, target value: -18.03:  88%|########8 | 8800/10000 [00:14<00:02, 590.95it/s]
+    reward: -5.42 (r0 = -2.01), reward eval: reward: -5.04, reward normalized=-2.73/5.36, grad norm= 65.22, loss_value= 257.60, loss_actor= 20.45, target value: -18.03:  96%|#########6| 9600/10000 [00:15<00:01, 399.48it/s]
+    reward: -5.40 (r0 = -2.01), reward eval: reward: -5.04, reward normalized=-3.53/5.24, grad norm= 410.03, loss_value= 340.43, loss_actor= 19.12, target value: -24.79:  96%|#########6| 9600/10000 [00:15<00:01, 399.48it/s]
+    reward: -5.40 (r0 = -2.01), reward eval: reward: -5.04, reward normalized=-3.53/5.24, grad norm= 410.03, loss_value= 340.43, loss_actor= 19.12, target value: -24.79: : 10400it [00:17, 365.12it/s]                        
+    reward: -4.35 (r0 = -2.01), reward eval: reward: -5.04, reward normalized=-3.57/4.59, grad norm= 83.81, loss_value= 232.02, loss_actor= 22.47, target value: -25.23: : 10400it [00:18, 365.12it/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  28.313 seconds)
+   **Total running time of the script:** ( 0 minutes  28.522 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): 199.8
+    elapsed time (seconds): 210.1
     loss: 5.168
-    elapsed time (seconds): 115.5
+    elapsed time (seconds): 115.7
 
 
 
@@ -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  26.263 seconds)
+   **Total running time of the script:** ( 5 minutes  36.854 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_coding_ddpg_001.png

@@ -410,33 +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]
-      4%|3         | 20.4M/548M [00:00<00:02, 214MB/s]
-      8%|7         | 41.4M/548M [00:00<00:02, 217MB/s]
-     11%|#1        | 62.4M/548M [00:00<00:02, 218MB/s]
-     15%|#5        | 83.4M/548M [00:00<00:02, 219MB/s]
-     19%|#9        | 104M/548M [00:00<00:02, 219MB/s] 
-     23%|##2       | 125M/548M [00:00<00:02, 219MB/s]
-     27%|##6       | 146M/548M [00:00<00:01, 219MB/s]
-     31%|###       | 167M/548M [00:00<00:01, 220MB/s]
-     34%|###4      | 188M/548M [00:00<00:01, 220MB/s]
-     38%|###8      | 210M/548M [00:01<00:01, 220MB/s]
-     42%|####2     | 230M/548M [00:01<00:01, 220MB/s]
-     46%|####5     | 252M/548M [00:01<00:01, 220MB/s]
-     50%|####9     | 272M/548M [00:01<00:01, 220MB/s]
-     54%|#####3    | 294M/548M [00:01<00:01, 220MB/s]
-     57%|#####7    | 314M/548M [00:01<00:01, 220MB/s]
-     61%|######1   | 336M/548M [00:01<00:01, 220MB/s]
-     65%|######5   | 357M/548M [00:01<00:00, 220MB/s]
-     69%|######8   | 378M/548M [00:01<00:00, 220MB/s]
-     73%|#######2  | 399M/548M [00:01<00:00, 220MB/s]
-     77%|#######6  | 420M/548M [00:02<00:00, 220MB/s]
-     80%|########  | 441M/548M [00:02<00:00, 220MB/s]
-     84%|########4 | 462M/548M [00:02<00:00, 220MB/s]
-     88%|########8 | 483M/548M [00:02<00:00, 220MB/s]
-     92%|#########2| 504M/548M [00:02<00:00, 220MB/s]
-     96%|#########5| 526M/548M [00:02<00:00, 221MB/s]
-    100%|#########9| 547M/548M [00:02<00:00, 221MB/s]
-    100%|##########| 548M/548M [00:02<00:00, 220MB/s]
+      4%|3         | 20.6M/548M [00:00<00:02, 216MB/s]
+      8%|7         | 41.8M/548M [00:00<00:02, 219MB/s]
+     11%|#1        | 62.9M/548M [00:00<00:02, 220MB/s]
+     15%|#5        | 84.0M/548M [00:00<00:02, 220MB/s]
+     19%|#9        | 105M/548M [00:00<00:02, 221MB/s] 
+     23%|##3       | 126M/548M [00:00<00:02, 221MB/s]
+     27%|##6       | 147M/548M [00:00<00:01, 221MB/s]
+     31%|###       | 168M/548M [00:00<00:01, 221MB/s]
+     35%|###4      | 190M/548M [00:00<00:01, 221MB/s]
+     38%|###8      | 211M/548M [00:01<00:01, 221MB/s]
+     42%|####2     | 232M/548M [00:01<00:01, 221MB/s]
+     46%|####6     | 253M/548M [00:01<00:01, 221MB/s]
+     50%|#####     | 274M/548M [00:01<00:01, 221MB/s]
+     54%|#####3    | 295M/548M [00:01<00:01, 221MB/s]
+     58%|#####7    | 316M/548M [00:01<00:01, 220MB/s]
+     62%|######1   | 338M/548M [00:01<00:01, 220MB/s]
+     65%|######5   | 359M/548M [00:01<00:00, 220MB/s]
+     69%|######9   | 380M/548M [00:01<00:00, 220MB/s]
+     73%|#######3  | 401M/548M [00:01<00:00, 220MB/s]
+     77%|#######6  | 422M/548M [00:02<00:00, 220MB/s]
+     81%|########  | 443M/548M [00:02<00:00, 220MB/s]
+     85%|########4 | 464M/548M [00:02<00:00, 220MB/s]
+     89%|########8 | 485M/548M [00:02<00:00, 220MB/s]
+     92%|#########2| 506M/548M [00:02<00:00, 221MB/s]
+     96%|#########6| 527M/548M [00:02<00:00, 221MB/s]
+    100%|##########| 548M/548M [00:02<00:00, 221MB/s]
 
 
 
@@ -757,22 +756,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 4.036047 Content Loss: 4.145061
+    Style Loss : 4.118675 Content Loss: 4.164120
 
     run [100]:
-    Style Loss : 1.121276 Content Loss: 3.036377
+    Style Loss : 1.165700 Content Loss: 3.054597
 
     run [150]:
-    Style Loss : 0.717448 Content Loss: 2.649953
+    Style Loss : 0.726226 Content Loss: 2.663800
 
     run [200]:
-    Style Loss : 0.482685 Content Loss: 2.490292
+    Style Loss : 0.479455 Content Loss: 2.492070
 
     run [250]:
-    Style Loss : 0.349416 Content Loss: 2.405339
+    Style Loss : 0.348070 Content Loss: 2.404342
 
     run [300]:
-    Style Loss : 0.269185 Content Loss: 2.352262
+    Style Loss : 0.266881 Content Loss: 2.352220
 
 
 
@@ -781,7 +780,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  38.651 seconds)
+   **Total running time of the script:** ( 0 minutes  38.475 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  0.624 seconds)
+   **Total running time of the script:** ( 0 minutes  0.580 seconds)
 
 
 .. _sphx_glr_download_advanced_numpy_extensions_tutorial.py: