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, 1722.07it/s]
-     16%|#6        | 1600/10000 [00:02<00:17, 481.23it/s]
-     24%|##4       | 2400/10000 [00:03<00:10, 692.11it/s]
-     32%|###2      | 3200/10000 [00:04<00:07, 889.74it/s]
-     40%|####      | 4000/10000 [00:04<00:05, 1050.97it/s]
-     48%|####8     | 4800/10000 [00:05<00:04, 1176.81it/s]
-     56%|#####6    | 5600/10000 [00:05<00:03, 1298.20it/s]
-    reward: -2.92 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.66/6.18, grad norm= 64.98, loss_value= 354.58, loss_actor= 15.12, target value: -16.19:  56%|#####6    | 5600/10000 [00:06<00:03, 1298.20it/s]
-    reward: -2.92 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.66/6.18, grad norm= 64.98, loss_value= 354.58, loss_actor= 15.12, target value: -16.19:  64%|######4   | 6400/10000 [00:06<00:03, 906.92it/s] 
-    reward: -0.16 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.09/5.62, grad norm= 124.82, loss_value= 219.50, loss_actor= 14.16, target value: -13.41:  64%|######4   | 6400/10000 [00:07<00:03, 906.92it/s]
-    reward: -0.16 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.09/5.62, grad norm= 124.82, loss_value= 219.50, loss_actor= 14.16, target value: -13.41:  72%|#######2  | 7200/10000 [00:08<00:03, 750.54it/s]
-    reward: -2.73 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.40/5.86, grad norm= 125.51, loss_value= 239.26, loss_actor= 12.55, target value: -15.01:  72%|#######2  | 7200/10000 [00:09<00:03, 750.54it/s]
-    reward: -2.73 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.40/5.86, grad norm= 125.51, loss_value= 239.26, loss_actor= 12.55, target value: -15.01:  80%|########  | 8000/10000 [00:09<00:02, 671.44it/s]
-    reward: -4.45 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.48/5.26, grad norm= 133.72, loss_value= 212.55, loss_actor= 17.56, target value: -16.44:  80%|########  | 8000/10000 [00:10<00:02, 671.44it/s]
-    reward: -4.45 (r0 = -2.79), reward eval: reward:  0.00, reward normalized=-2.48/5.26, grad norm= 133.72, loss_value= 212.55, loss_actor= 17.56, target value: -16.44:  88%|########8 | 8800/10000 [00:11<00:01, 614.51it/s]
-    reward: -5.41 (r0 = -2.79), reward eval: reward: -5.53, reward normalized=-3.08/5.18, grad norm= 130.58, loss_value= 202.59, loss_actor= 19.66, target value: -20.80:  88%|########8 | 8800/10000 [00:14<00:01, 614.51it/s]
-    reward: -5.41 (r0 = -2.79), reward eval: reward: -5.53, reward normalized=-3.08/5.18, grad norm= 130.58, loss_value= 202.59, loss_actor= 19.66, target value: -20.80:  96%|#########6| 9600/10000 [00:14<00:00, 406.37it/s]
-    reward: -5.40 (r0 = -2.79), reward eval: reward: -5.53, reward normalized=-3.54/5.03, grad norm= 329.46, loss_value= 245.21, loss_actor= 19.56, target value: -25.54:  96%|#########6| 9600/10000 [00:15<00:00, 406.37it/s]
-    reward: -5.40 (r0 = -2.79), reward eval: reward: -5.53, reward normalized=-3.54/5.03, grad norm= 329.46, loss_value= 245.21, loss_actor= 19.56, target value: -25.54: : 10400it [00:17, 371.25it/s]                        
-    reward: -5.22 (r0 = -2.79), reward eval: reward: -5.53, reward normalized=-4.00/4.30, grad norm= 107.23, loss_value= 199.22, loss_actor= 24.13, target value: -27.65: : 10400it [00:18, 371.25it/s]
+      8%|8         | 800/10000 [00:00<00:05, 1695.61it/s]
+     16%|#6        | 1600/10000 [00:02<00:17, 482.88it/s]
+     24%|##4       | 2400/10000 [00:03<00:11, 687.66it/s]
+     32%|###2      | 3200/10000 [00:04<00:07, 889.93it/s]
+     40%|####      | 4000/10000 [00:04<00:05, 1057.38it/s]
+     48%|####8     | 4800/10000 [00:05<00:04, 1193.59it/s]
+     56%|#####6    | 5600/10000 [00:05<00:03, 1290.37it/s]
+    reward: -2.84 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-2.43/6.31, grad norm= 71.04, loss_value= 396.71, loss_actor= 14.53, target value: -14.87:  56%|#####6    | 5600/10000 [00:06<00:03, 1290.37it/s]
+    reward: -2.84 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-2.43/6.31, grad norm= 71.04, loss_value= 396.71, loss_actor= 14.53, target value: -14.87:  64%|######4   | 6400/10000 [00:07<00:04, 851.50it/s] 
+    reward: -0.15 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-1.76/5.98, grad norm= 118.29, loss_value= 304.53, loss_actor= 12.29, target value: -10.82:  64%|######4   | 6400/10000 [00:07<00:04, 851.50it/s]
+    reward: -0.15 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-1.76/5.98, grad norm= 118.29, loss_value= 304.53, loss_actor= 12.29, target value: -10.82:  72%|#######2  | 7200/10000 [00:08<00:04, 692.07it/s]
+    reward: -2.41 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-1.76/6.10, grad norm= 100.06, loss_value= 349.30, loss_actor= 11.72, target value: -12.19:  72%|#######2  | 7200/10000 [00:09<00:04, 692.07it/s]
+    reward: -2.41 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-1.76/6.10, grad norm= 100.06, loss_value= 349.30, loss_actor= 11.72, target value: -12.19:  80%|########  | 8000/10000 [00:10<00:03, 623.08it/s]
+    reward: -4.83 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-2.22/4.89, grad norm= 68.99, loss_value= 204.73, loss_actor= 13.44, target value: -14.30:  80%|########  | 8000/10000 [00:11<00:03, 623.08it/s] 
+    reward: -4.83 (r0 = -3.17), reward eval: reward: -0.01, reward normalized=-2.22/4.89, grad norm= 68.99, loss_value= 204.73, loss_actor= 13.44, target value: -14.30:  88%|########8 | 8800/10000 [00:11<00:02, 578.83it/s]
+    reward: -4.41 (r0 = -3.17), reward eval: reward: -5.62, reward normalized=-2.91/4.96, grad norm= 81.74, loss_value= 161.88, loss_actor= 13.33, target value: -19.36:  88%|########8 | 8800/10000 [00:14<00:02, 578.83it/s]
+    reward: -4.41 (r0 = -3.17), reward eval: reward: -5.62, reward normalized=-2.91/4.96, grad norm= 81.74, loss_value= 161.88, loss_actor= 13.33, target value: -19.36:  96%|#########6| 9600/10000 [00:15<00:01, 389.80it/s]
+    reward: -5.39 (r0 = -3.17), reward eval: reward: -5.62, reward normalized=-3.06/5.23, grad norm= 193.62, loss_value= 258.27, loss_actor= 14.26, target value: -22.43:  96%|#########6| 9600/10000 [00:16<00:01, 389.80it/s]
+    reward: -5.39 (r0 = -3.17), reward eval: reward: -5.62, reward normalized=-3.06/5.23, grad norm= 193.62, loss_value= 258.27, loss_actor= 14.26, target value: -22.43: : 10400it [00:18, 357.06it/s]                        
+    reward: -4.73 (r0 = -3.17), reward eval: reward: -5.62, reward normalized=-3.74/4.05, grad norm= 76.70, loss_value= 159.92, loss_actor= 23.20, target value: -26.13: : 10400it [00:19, 357.06it/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  28.302 seconds)
+   **Total running time of the script:** ( 0 minutes  29.164 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): 203.3
+    elapsed time (seconds): 201.1
     loss: 5.168
-    elapsed time (seconds): 115.5
+    elapsed time (seconds): 113.3
 
 
 
@@ -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  29.492 seconds)
+   **Total running time of the script:** ( 5 minutes  25.145 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_coding_ddpg_001.png

@@ -410,32 +410,33 @@ 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         | 20.6M/548M [00:00<00:02, 216MB/s]
-      8%|7         | 41.5M/548M [00:00<00:02, 217MB/s]
-     11%|#1        | 62.5M/548M [00:00<00:02, 219MB/s]
-     15%|#5        | 83.8M/548M [00:00<00:02, 220MB/s]
-     19%|#9        | 105M/548M [00:00<00:02, 221MB/s] 
-     23%|##3       | 126M/548M [00:00<00:01, 221MB/s]
-     27%|##6       | 148M/548M [00:00<00:01, 222MB/s]
-     31%|###       | 169M/548M [00:00<00:01, 222MB/s]
-     35%|###4      | 190M/548M [00:00<00:01, 222MB/s]
-     39%|###8      | 211M/548M [00:01<00:01, 222MB/s]
-     42%|####2     | 233M/548M [00:01<00:01, 222MB/s]
-     46%|####6     | 254M/548M [00:01<00:01, 222MB/s]
-     50%|#####     | 275M/548M [00:01<00:01, 222MB/s]
-     54%|#####4    | 296M/548M [00:01<00:01, 222MB/s]
-     58%|#####7    | 318M/548M [00:01<00:01, 222MB/s]
-     62%|######1   | 339M/548M [00:01<00:00, 222MB/s]
-     66%|######5   | 360M/548M [00:01<00:00, 222MB/s]
-     70%|######9   | 382M/548M [00:01<00:00, 223MB/s]
-     74%|#######3  | 403M/548M [00:01<00:00, 223MB/s]
-     77%|#######7  | 424M/548M [00:02<00:00, 223MB/s]
-     81%|########1 | 446M/548M [00:02<00:00, 223MB/s]
-     85%|########5 | 467M/548M [00:02<00:00, 222MB/s]
-     89%|########9 | 488M/548M [00:02<00:00, 223MB/s]
-     93%|#########2| 509M/548M [00:02<00:00, 222MB/s]
-     97%|#########6| 531M/548M [00:02<00:00, 223MB/s]
-    100%|##########| 548M/548M [00:02<00:00, 222MB/s]
+      4%|3         | 20.1M/548M [00:00<00:02, 211MB/s]
+      7%|7         | 40.8M/548M [00:00<00:02, 213MB/s]
+     11%|#1        | 61.5M/548M [00:00<00:02, 215MB/s]
+     15%|#5        | 82.2M/548M [00:00<00:02, 216MB/s]
+     19%|#8        | 103M/548M [00:00<00:02, 216MB/s] 
+     23%|##2       | 124M/548M [00:00<00:02, 216MB/s]
+     26%|##6       | 144M/548M [00:00<00:01, 217MB/s]
+     30%|###       | 165M/548M [00:00<00:01, 217MB/s]
+     34%|###3      | 186M/548M [00:00<00:01, 217MB/s]
+     38%|###7      | 207M/548M [00:01<00:01, 217MB/s]
+     42%|####1     | 228M/548M [00:01<00:01, 217MB/s]
+     45%|####5     | 248M/548M [00:01<00:01, 217MB/s]
+     49%|####9     | 269M/548M [00:01<00:01, 217MB/s]
+     53%|#####2    | 290M/548M [00:01<00:01, 217MB/s]
+     57%|#####6    | 311M/548M [00:01<00:01, 217MB/s]
+     60%|######    | 332M/548M [00:01<00:01, 217MB/s]
+     64%|######4   | 352M/548M [00:01<00:00, 217MB/s]
+     68%|######8   | 373M/548M [00:01<00:00, 217MB/s]
+     72%|#######1  | 394M/548M [00:01<00:00, 217MB/s]
+     76%|#######5  | 415M/548M [00:02<00:00, 217MB/s]
+     79%|#######9  | 436M/548M [00:02<00:00, 217MB/s]
+     83%|########3 | 456M/548M [00:02<00:00, 217MB/s]
+     87%|########7 | 477M/548M [00:02<00:00, 217MB/s]
+     91%|######### | 498M/548M [00:02<00:00, 217MB/s]
+     95%|#########4| 519M/548M [00:02<00:00, 217MB/s]
+     98%|#########8| 539M/548M [00:02<00:00, 217MB/s]
+    100%|##########| 548M/548M [00:02<00:00, 217MB/s]
 
 
 
@@ -756,22 +757,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 4.065745 Content Loss: 4.157114
+    Style Loss : 4.161686 Content Loss: 4.189911
 
     run [100]:
-    Style Loss : 1.119953 Content Loss: 3.009066
+    Style Loss : 1.140328 Content Loss: 3.020304
 
     run [150]:
-    Style Loss : 0.703355 Content Loss: 2.644294
+    Style Loss : 0.716041 Content Loss: 2.644831
 
     run [200]:
-    Style Loss : 0.471478 Content Loss: 2.488785
+    Style Loss : 0.480255 Content Loss: 2.490241
 
     run [250]:
-    Style Loss : 0.341830 Content Loss: 2.400148
+    Style Loss : 0.348056 Content Loss: 2.404358
 
     run [300]:
-    Style Loss : 0.261067 Content Loss: 2.345300
+    Style Loss : 0.265763 Content Loss: 2.351621
 
 
 
@@ -780,7 +781,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  38.628 seconds)
+   **Total running time of the script:** ( 0 minutes  38.500 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  0.595 seconds)
+   **Total running time of the script:** ( 0 minutes  0.598 seconds)
 
 
 .. _sphx_glr_download_advanced_numpy_extensions_tutorial.py: