Automated tutorials push

Author: pytorchbot

_downloads/3195443a0ced3cabc0ad643537bdb5cd/introyt1_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "03d00eb0",
+   "id": "333110fd",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a2258b92",
+   "id": "bee03c61",
    "metadata": {},
    "source": [
     "\n",

_downloads/4355e2cef7d17548f1e25f97a62828c4/template_tutorial.ipynb

@@ -31,7 +31,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4e1876e7",
+   "id": "6b84cd50",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "57340e2a",
+   "id": "c7942b32",
    "metadata": {},
    "source": [
     "\n",

_downloads/63a0f0fc7b3ffb15d3a5ac8db3d521ee/tensors_deeper_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c82232a1",
+   "id": "9a5e39d6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "aafac980",
+   "id": "bbfa1eb2",
    "metadata": {},
    "source": [
     "\n",

_downloads/770632dd3941d2a51b831c52ded57aa2/trainingyt.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5e949b91",
+   "id": "e7355df9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3593a657",
+   "id": "3a8b0583",
    "metadata": {},
    "source": [
     "\n",

_downloads/c28f42852d456daf9af72da6c6909556/captumyt.ipynb

@@ -37,7 +37,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "241f94be",
+   "id": "c46e89e7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "eb62a5d6",
+   "id": "122eb44e",
    "metadata": {},
    "source": [
     "\n",

_downloads/e2e556f6b4693c2cef716dd7f40caaf6/tensorboardyt_tutorial.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6881b39d",
+   "id": "fb14dc6c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4cb84077",
+   "id": "b2b08c1a",
    "metadata": {},
    "source": [
     "\n",

_downloads/ed9d4f94afb79f7dada6742a06c486a5/autogradyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5a85e8ec",
+   "id": "90f4d3a2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "01153738",
+   "id": "4fa489f6",
    "metadata": {},
    "source": [
     "\n",

_downloads/fe726e041160526cf828806536922cf6/modelsyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a6756670",
+   "id": "539ee7a6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "52962b28",
+   "id": "d1844aa4",
    "metadata": {},
    "source": [
     "\n",

_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<00:06, 1413.52it/s]
-     16%|#6        | 1600/10000 [00:03<00:20, 403.13it/s]
-     24%|##4       | 2400/10000 [00:04<00:12, 586.58it/s]
-     32%|###2      | 3200/10000 [00:04<00:08, 768.34it/s]
-     40%|####      | 4000/10000 [00:05<00:06, 920.14it/s]
-     48%|####8     | 4800/10000 [00:05<00:04, 1040.30it/s]
-     56%|#####6    | 5600/10000 [00:06<00:03, 1121.15it/s]
-    reward: -2.56 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-2.85/6.79, grad norm= 86.98, loss_value= 477.54, loss_actor= 16.11, target value: -17.80:  56%|#####6    | 5600/10000 [00:07<00:03, 1121.15it/s]
-    reward: -2.56 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-2.85/6.79, grad norm= 86.98, loss_value= 477.54, loss_actor= 16.11, target value: -17.80:  64%|######4   | 6400/10000 [00:08<00:04, 796.06it/s] 
-    reward: -0.20 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-3.04/5.86, grad norm= 82.28, loss_value= 291.16, loss_actor= 16.75, target value: -19.42:  64%|######4   | 6400/10000 [00:08<00:04, 796.06it/s]
-    reward: -0.20 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-3.04/5.86, grad norm= 82.28, loss_value= 291.16, loss_actor= 16.75, target value: -19.42:  72%|#######2  | 7200/10000 [00:09<00:04, 670.32it/s]
-    reward: -2.85 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-2.93/6.12, grad norm= 169.17, loss_value= 310.63, loss_actor= 15.04, target value: -18.15:  72%|#######2  | 7200/10000 [00:10<00:04, 670.32it/s]
-    reward: -2.85 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-2.93/6.12, grad norm= 169.17, loss_value= 310.63, loss_actor= 15.04, target value: -18.15:  80%|########  | 8000/10000 [00:11<00:03, 611.26it/s]
-    reward: -4.98 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-2.72/4.96, grad norm= 71.58, loss_value= 203.21, loss_actor= 16.10, target value: -17.88:  80%|########  | 8000/10000 [00:12<00:03, 611.26it/s] 
-    reward: -4.98 (r0 = -3.32), reward eval: reward: -0.01, reward normalized=-2.72/4.96, grad norm= 71.58, loss_value= 203.21, loss_actor= 16.10, target value: -17.88:  88%|########8 | 8800/10000 [00:12<00:02, 579.99it/s]
-    reward: -5.15 (r0 = -3.32), reward eval: reward: -5.77, reward normalized=-2.74/4.88, grad norm= 67.79, loss_value= 177.52, loss_actor= 19.43, target value: -18.64:  88%|########8 | 8800/10000 [00:15<00:02, 579.99it/s]
-    reward: -5.15 (r0 = -3.32), reward eval: reward: -5.77, reward normalized=-2.74/4.88, grad norm= 67.79, loss_value= 177.52, loss_actor= 19.43, target value: -18.64:  96%|#########6| 9600/10000 [00:16<00:01, 368.64it/s]
-    reward: -4.63 (r0 = -3.32), reward eval: reward: -5.77, reward normalized=-2.72/4.96, grad norm= 100.61, loss_value= 233.46, loss_actor= 19.22, target value: -19.81:  96%|#########6| 9600/10000 [00:17<00:01, 368.64it/s]
-    reward: -4.63 (r0 = -3.32), reward eval: reward: -5.77, reward normalized=-2.72/4.96, grad norm= 100.61, loss_value= 233.46, loss_actor= 19.22, target value: -19.81: : 10400it [00:19, 348.57it/s]                        
-    reward: -4.79 (r0 = -3.32), reward eval: reward: -5.77, reward normalized=-4.03/4.05, grad norm= 168.97, loss_value= 157.23, loss_actor= 23.69, target value: -28.33: : 10400it [00:20, 348.57it/s]
+      8%|8         | 800/10000 [00:00<00:06, 1416.92it/s]
+     16%|#6        | 1600/10000 [00:03<00:21, 394.72it/s]
+     24%|##4       | 2400/10000 [00:04<00:13, 572.27it/s]
+     32%|###2      | 3200/10000 [00:04<00:09, 740.78it/s]
+     40%|####      | 4000/10000 [00:05<00:06, 881.14it/s]
+     48%|####8     | 4800/10000 [00:06<00:05, 999.44it/s]
+     56%|#####6    | 5600/10000 [00:06<00:04, 1087.14it/s]
+    reward: -2.21 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-1.95/6.62, grad norm= 55.87, loss_value= 464.75, loss_actor= 13.97, target value: -12.47:  56%|#####6    | 5600/10000 [00:07<00:04, 1087.14it/s]
+    reward: -2.21 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-1.95/6.62, grad norm= 55.87, loss_value= 464.75, loss_actor= 13.97, target value: -12.47:  64%|######4   | 6400/10000 [00:08<00:04, 783.28it/s] 
+    reward: -0.13 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-2.44/5.91, grad norm= 85.41, loss_value= 286.78, loss_actor= 12.42, target value: -15.80:  64%|######4   | 6400/10000 [00:09<00:04, 783.28it/s]
+    reward: -0.13 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-2.44/5.91, grad norm= 85.41, loss_value= 286.78, loss_actor= 12.42, target value: -15.80:  72%|#######2  | 7200/10000 [00:09<00:04, 667.62it/s]
+    reward: -3.46 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-1.97/6.10, grad norm= 156.42, loss_value= 294.56, loss_actor= 12.12, target value: -12.42:  72%|#######2  | 7200/10000 [00:10<00:04, 667.62it/s]
+    reward: -3.46 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-1.97/6.10, grad norm= 156.42, loss_value= 294.56, loss_actor= 12.12, target value: -12.42:  80%|########  | 8000/10000 [00:11<00:03, 606.34it/s]
+    reward: -4.76 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-2.34/5.31, grad norm= 90.94, loss_value= 266.09, loss_actor= 17.22, target value: -15.30:  80%|########  | 8000/10000 [00:12<00:03, 606.34it/s] 
+    reward: -4.76 (r0 = -2.33), reward eval: reward:  0.00, reward normalized=-2.34/5.31, grad norm= 90.94, loss_value= 266.09, loss_actor= 17.22, target value: -15.30:  88%|########8 | 8800/10000 [00:13<00:02, 569.06it/s]
+    reward: -5.06 (r0 = -2.33), reward eval: reward: -4.19, reward normalized=-2.55/5.54, grad norm= 88.47, loss_value= 273.97, loss_actor= 18.95, target value: -18.19:  88%|########8 | 8800/10000 [00:16<00:02, 569.06it/s]
+    reward: -5.06 (r0 = -2.33), reward eval: reward: -4.19, reward normalized=-2.55/5.54, grad norm= 88.47, loss_value= 273.97, loss_actor= 18.95, target value: -18.19:  96%|#########6| 9600/10000 [00:17<00:01, 367.86it/s]
+    reward: -4.87 (r0 = -2.33), reward eval: reward: -4.19, reward normalized=-3.12/4.83, grad norm= 62.93, loss_value= 200.26, loss_actor= 17.99, target value: -21.88:  96%|#########6| 9600/10000 [00:17<00:01, 367.86it/s]
+    reward: -4.87 (r0 = -2.33), reward eval: reward: -4.19, reward normalized=-3.12/4.83, grad norm= 62.93, loss_value= 200.26, loss_actor= 17.99, target value: -21.88: : 10400it [00:19, 342.03it/s]                        
+    reward: -6.21 (r0 = -2.33), reward eval: reward: -4.19, reward normalized=-3.63/4.73, grad norm= 70.11, loss_value= 197.44, loss_actor= 21.66, target value: -25.21: : 10400it [00:20, 342.03it/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  31.669 seconds)
+   **Total running time of the script:** ( 0 minutes  31.944 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): 204.3
+    elapsed time (seconds): 203.4
     loss: 5.168
-    elapsed time (seconds): 115.2
+    elapsed time (seconds): 118.1
 
 
 
@@ -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  27.712 seconds)
+   **Total running time of the script:** ( 5 minutes  29.977 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_coding_ddpg_001.png

@@ -410,20 +410,20 @@ 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]
-      7%|7         | 40.5M/548M [00:00<00:01, 424MB/s]
-     15%|#4        | 81.0M/548M [00:00<00:01, 370MB/s]
-     21%|##1       | 117M/548M [00:00<00:01, 365MB/s] 
-     28%|##8       | 155M/548M [00:00<00:01, 378MB/s]
-     35%|###5      | 193M/548M [00:00<00:00, 386MB/s]
-     43%|####3     | 237M/548M [00:00<00:00, 411MB/s]
-     51%|#####1    | 282M/548M [00:00<00:00, 427MB/s]
-     59%|#####8    | 322M/548M [00:00<00:00, 405MB/s]
-     66%|######5   | 362M/548M [00:00<00:00, 391MB/s]
-     73%|#######3  | 401M/548M [00:01<00:00, 398MB/s]
-     80%|########  | 440M/548M [00:01<00:00, 400MB/s]
-     88%|########7 | 480M/548M [00:01<00:00, 406MB/s]
-     95%|#########4| 520M/548M [00:01<00:00, 408MB/s]
-    100%|##########| 548M/548M [00:01<00:00, 403MB/s]
+      8%|7         | 41.5M/548M [00:00<00:01, 435MB/s]
+     15%|#5        | 83.0M/548M [00:00<00:01, 431MB/s]
+     23%|##2       | 124M/548M [00:00<00:01, 392MB/s] 
+     30%|##9       | 162M/548M [00:00<00:01, 310MB/s]
+     35%|###5      | 193M/548M [00:00<00:01, 294MB/s]
+     41%|####      | 223M/548M [00:00<00:01, 297MB/s]
+     47%|####7     | 260M/548M [00:00<00:00, 323MB/s]
+     55%|#####5    | 304M/548M [00:00<00:00, 363MB/s]
+     62%|######2   | 342M/548M [00:01<00:00, 374MB/s]
+     70%|#######   | 386M/548M [00:01<00:00, 401MB/s]
+     79%|#######8  | 431M/548M [00:01<00:00, 420MB/s]
+     86%|########6 | 471M/548M [00:01<00:00, 392MB/s]
+     93%|#########2| 510M/548M [00:01<00:00, 385MB/s]
+    100%|##########| 548M/548M [00:01<00:00, 370MB/s]
 
 
 
@@ -744,22 +744,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 4.094805 Content Loss: 4.188426
+    Style Loss : 4.119137 Content Loss: 4.126241
 
     run [100]:
-    Style Loss : 1.117979 Content Loss: 3.008747
+    Style Loss : 1.133011 Content Loss: 3.011671
 
     run [150]:
-    Style Loss : 0.712450 Content Loss: 2.650858
+    Style Loss : 0.717595 Content Loss: 2.657820
 
     run [200]:
-    Style Loss : 0.476656 Content Loss: 2.489839
+    Style Loss : 0.481263 Content Loss: 2.491316
 
     run [250]:
-    Style Loss : 0.344013 Content Loss: 2.401936
+    Style Loss : 0.347754 Content Loss: 2.402972
 
     run [300]:
-    Style Loss : 0.264354 Content Loss: 2.349211
+    Style Loss : 0.263970 Content Loss: 2.349388
 
 
 
@@ -768,7 +768,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  11.342 seconds)
+   **Total running time of the script:** ( 0 minutes  11.629 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  0.377 seconds)
+   **Total running time of the script:** ( 0 minutes  0.369 seconds)
 
 
 .. _sphx_glr_download_advanced_numpy_extensions_tutorial.py: