Automated tutorials push

Author: pytorchbot

_downloads/3195443a0ced3cabc0ad643537bdb5cd/introyt1_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ca34c572",
+   "id": "08a56b87",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "69d44866",
+   "id": "6a1a1ff1",
    "metadata": {},
    "source": [
     "\n",

_downloads/4355e2cef7d17548f1e25f97a62828c4/template_tutorial.ipynb

@@ -31,7 +31,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "72b68b4e",
+   "id": "fa407add",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6a298cb8",
+   "id": "798a5677",
    "metadata": {},
    "source": [
     "\n",

_downloads/63a0f0fc7b3ffb15d3a5ac8db3d521ee/tensors_deeper_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c728d905",
+   "id": "70184db4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "609046b9",
+   "id": "fccaaa0c",
    "metadata": {},
    "source": [
     "\n",

_downloads/770632dd3941d2a51b831c52ded57aa2/trainingyt.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "516094be",
+   "id": "87401fce",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "21e35ae9",
+   "id": "30621f77",
    "metadata": {},
    "source": [
     "\n",

_downloads/c28f42852d456daf9af72da6c6909556/captumyt.ipynb

@@ -37,7 +37,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ba753744",
+   "id": "f2168b84",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "acd40f7e",
+   "id": "31b0ca73",
    "metadata": {},
    "source": [
     "\n",

_downloads/e2e556f6b4693c2cef716dd7f40caaf6/tensorboardyt_tutorial.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f65f4e76",
+   "id": "7e4da9f6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "85bef7b2",
+   "id": "bbf7b3e9",
    "metadata": {},
    "source": [
     "\n",

_downloads/ed9d4f94afb79f7dada6742a06c486a5/autogradyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b3844a72",
+   "id": "6bc61fe1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7fd4a9c1",
+   "id": "5a8aecd1",
    "metadata": {},
    "source": [
     "\n",

_downloads/fe726e041160526cf828806536922cf6/modelsyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8b76a6a2",
+   "id": "81372e17",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "da09ceed",
+   "id": "65055fea",
    "metadata": {},
    "source": [
     "\n",

_images/sphx_glr_coding_ddpg_001.png

@@ -1632,26 +1632,26 @@ modules we need.
 
 
       0%|          | 0/10000 [00:00<?, ?it/s]
-      8%|8         | 800/10000 [00:00<00:03, 2882.70it/s]
-     16%|#6        | 1600/10000 [00:01<00:10, 773.39it/s]
-     24%|##4       | 2400/10000 [00:02<00:06, 1161.45it/s]
-     32%|###2      | 3200/10000 [00:02<00:04, 1519.32it/s]
-     40%|####      | 4000/10000 [00:02<00:03, 1827.70it/s]
-     48%|####8     | 4800/10000 [00:02<00:02, 2093.27it/s]
-     56%|#####6    | 5600/10000 [00:03<00:01, 2295.95it/s]
-    reward: -2.27 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-1.58/6.07, grad norm= 183.37, loss_value= 309.57, loss_actor= 12.89, target value: -9.74:  56%|#####6    | 5600/10000 [00:05<00:01, 2295.95it/s]
-    reward: -2.27 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-1.58/6.07, grad norm= 183.37, loss_value= 309.57, loss_actor= 12.89, target value: -9.74:  64%|######4   | 6400/10000 [00:05<00:04, 762.49it/s] 
-    reward: -2.12 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-2.37/5.51, grad norm= 124.05, loss_value= 228.19, loss_actor= 11.76, target value: -15.22:  64%|######4   | 6400/10000 [00:07<00:04, 762.49it/s]
-    reward: -2.12 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-2.37/5.51, grad norm= 124.05, loss_value= 228.19, loss_actor= 11.76, target value: -15.22:  72%|#######2  | 7200/10000 [00:08<00:05, 498.70it/s]
-    reward: -4.36 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-2.31/4.99, grad norm= 47.98, loss_value= 193.70, loss_actor= 15.70, target value: -14.80:  72%|#######2  | 7200/10000 [00:10<00:05, 498.70it/s] 
-    reward: -4.36 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-2.31/4.99, grad norm= 47.98, loss_value= 193.70, loss_actor= 15.70, target value: -14.80:  80%|########  | 8000/10000 [00:11<00:04, 404.95it/s]
-    reward: -5.11 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-2.52/4.88, grad norm= 49.44, loss_value= 141.67, loss_actor= 16.39, target value: -16.19:  80%|########  | 8000/10000 [00:13<00:04, 404.95it/s]
-    reward: -5.11 (r0 = -1.76), reward eval: reward: -0.00, reward normalized=-2.52/4.88, grad norm= 49.44, loss_value= 141.67, loss_actor= 16.39, target value: -16.19:  88%|########8 | 8800/10000 [00:14<00:03, 359.89it/s]
-    reward: -0.43 (r0 = -1.76), reward eval: reward: -5.42, reward normalized=-2.29/5.93, grad norm= 77.38, loss_value= 278.72, loss_actor= 13.01, target value: -15.99:  88%|########8 | 8800/10000 [00:17<00:03, 359.89it/s]
-    reward: -0.43 (r0 = -1.76), reward eval: reward: -5.42, reward normalized=-2.29/5.93, grad norm= 77.38, loss_value= 278.72, loss_actor= 13.01, target value: -15.99:  96%|#########6| 9600/10000 [00:18<00:01, 287.59it/s]
-    reward: -6.88 (r0 = -1.76), reward eval: reward: -5.42, reward normalized=-3.10/4.61, grad norm= 125.56, loss_value= 141.45, loss_actor= 19.85, target value: -22.21:  96%|#########6| 9600/10000 [00:20<00:01, 287.59it/s]
-    reward: -6.88 (r0 = -1.76), reward eval: reward: -5.42, reward normalized=-3.10/4.61, grad norm= 125.56, loss_value= 141.45, loss_actor= 19.85, target value: -22.21: : 10400it [00:22, 254.64it/s]                        
-    reward: -7.69 (r0 = -1.76), reward eval: reward: -5.42, reward normalized=-2.88/6.07, grad norm= 109.29, loss_value= 300.83, loss_actor= 21.91, target value: -20.79: : 10400it [00:24, 254.64it/s]
+      8%|8         | 800/10000 [00:00<00:03, 2865.54it/s]
+     16%|#6        | 1600/10000 [00:01<00:10, 764.01it/s]
+     24%|##4       | 2400/10000 [00:02<00:06, 1129.65it/s]
+     32%|###2      | 3200/10000 [00:02<00:04, 1464.27it/s]
+     40%|####      | 4000/10000 [00:02<00:03, 1743.21it/s]
+     48%|####8     | 4800/10000 [00:03<00:02, 1980.60it/s]
+     56%|#####6    | 5600/10000 [00:03<00:02, 2168.96it/s]
+    reward: -2.15 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-1.93/6.43, grad norm= 46.25, loss_value= 392.95, loss_actor= 12.56, target value: -13.07:  56%|#####6    | 5600/10000 [00:05<00:02, 2168.96it/s]
+    reward: -2.15 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-1.93/6.43, grad norm= 46.25, loss_value= 392.95, loss_actor= 12.56, target value: -13.07:  64%|######4   | 6400/10000 [00:05<00:04, 770.32it/s] 
+    reward: -2.25 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-3.09/5.77, grad norm= 350.55, loss_value= 343.68, loss_actor= 15.60, target value: -20.42:  64%|######4   | 6400/10000 [00:07<00:04, 770.32it/s]
+    reward: -2.25 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-3.09/5.77, grad norm= 350.55, loss_value= 343.68, loss_actor= 15.60, target value: -20.42:  72%|#######2  | 7200/10000 [00:08<00:05, 506.73it/s]
+    reward: -4.05 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-2.29/5.78, grad norm= 123.61, loss_value= 323.63, loss_actor= 14.73, target value: -13.32:  72%|#######2  | 7200/10000 [00:10<00:05, 506.73it/s]
+    reward: -4.05 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-2.29/5.78, grad norm= 123.61, loss_value= 323.63, loss_actor= 14.73, target value: -13.32:  80%|########  | 8000/10000 [00:11<00:04, 412.53it/s]
+    reward: -5.09 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-3.16/5.30, grad norm= 159.55, loss_value= 223.76, loss_actor= 18.63, target value: -20.20:  80%|########  | 8000/10000 [00:13<00:04, 412.53it/s]
+    reward: -5.09 (r0 = -2.13), reward eval: reward: -0.01, reward normalized=-3.16/5.30, grad norm= 159.55, loss_value= 223.76, loss_actor= 18.63, target value: -20.20:  88%|########8 | 8800/10000 [00:14<00:03, 363.29it/s]
+    reward: -3.35 (r0 = -2.13), reward eval: reward: -2.23, reward normalized=-2.44/5.63, grad norm= 80.14, loss_value= 254.06, loss_actor= 16.65, target value: -17.43:  88%|########8 | 8800/10000 [00:17<00:03, 363.29it/s] 
+    reward: -3.35 (r0 = -2.13), reward eval: reward: -2.23, reward normalized=-2.44/5.63, grad norm= 80.14, loss_value= 254.06, loss_actor= 16.65, target value: -17.43:  96%|#########6| 9600/10000 [00:18<00:01, 291.92it/s]
+    reward: -2.30 (r0 = -2.13), reward eval: reward: -2.23, reward normalized=-2.77/4.88, grad norm= 70.12, loss_value= 169.27, loss_actor= 15.45, target value: -19.94:  96%|#########6| 9600/10000 [00:19<00:01, 291.92it/s]
+    reward: -2.30 (r0 = -2.13), reward eval: reward: -2.23, reward normalized=-2.77/4.88, grad norm= 70.12, loss_value= 169.27, loss_actor= 15.45, target value: -19.94: : 10400it [00:22, 257.27it/s]                        
+    reward: -4.31 (r0 = -2.13), reward eval: reward: -2.23, reward normalized=-2.33/4.33, grad norm= 114.30, loss_value= 152.00, loss_actor= 13.96, target value: -15.90: : 10400it [00:24, 257.27it/s]
 
 
 
@@ -1721,7 +1721,7 @@ To iterate further on this loss module we might consider:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  28.544 seconds)
+   **Total running time of the script:** ( 0 minutes  28.395 seconds)
 
 
 .. _sphx_glr_download_advanced_coding_ddpg.py:

_images/sphx_glr_dqn_with_rnn_tutorial_001.png

@@ -516,9 +516,9 @@ models run single threaded.
  .. code-block:: none
 
     loss: 5.167
-    elapsed time (seconds): 207.3
+    elapsed time (seconds): 207.0
     loss: 5.168
-    elapsed time (seconds): 120.2
+    elapsed time (seconds): 117.5
 
 
 
@@ -540,7 +540,7 @@ 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  36.133 seconds)
+   **Total running time of the script:** ( 5 minutes  33.228 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_neural_style_tutorial_004.png

@@ -410,37 +410,38 @@ 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         | 17.1M/548M [00:00<00:03, 179MB/s]
-      6%|6         | 35.0M/548M [00:00<00:02, 184MB/s]
-     10%|9         | 52.8M/548M [00:00<00:02, 185MB/s]
-     13%|#2        | 70.4M/548M [00:00<00:03, 162MB/s]
-     16%|#5        | 87.6M/548M [00:00<00:02, 168MB/s]
-     19%|#9        | 106M/548M [00:00<00:02, 174MB/s] 
-     23%|##2       | 124M/548M [00:00<00:02, 179MB/s]
-     26%|##5       | 142M/548M [00:00<00:02, 181MB/s]
-     29%|##9       | 160M/548M [00:00<00:02, 183MB/s]
-     32%|###2      | 177M/548M [00:01<00:02, 184MB/s]
-     36%|###5      | 195M/548M [00:01<00:01, 185MB/s]
-     39%|###8      | 213M/548M [00:01<00:01, 186MB/s]
-     42%|####2     | 231M/548M [00:01<00:01, 186MB/s]
-     45%|####5     | 249M/548M [00:01<00:01, 187MB/s]
-     49%|####8     | 267M/548M [00:01<00:01, 187MB/s]
-     52%|#####2    | 285M/548M [00:01<00:01, 187MB/s]
-     55%|#####5    | 303M/548M [00:01<00:01, 188MB/s]
-     59%|#####8    | 321M/548M [00:01<00:01, 188MB/s]
-     62%|######1   | 339M/548M [00:01<00:01, 188MB/s]
-     65%|######5   | 357M/548M [00:02<00:01, 188MB/s]
-     68%|######8   | 375M/548M [00:02<00:00, 188MB/s]
-     72%|#######1  | 393M/548M [00:02<00:00, 188MB/s]
-     75%|#######5  | 411M/548M [00:02<00:00, 188MB/s]
-     78%|#######8  | 429M/548M [00:02<00:00, 188MB/s]
-     82%|########1 | 447M/548M [00:02<00:00, 188MB/s]
-     85%|########4 | 465M/548M [00:02<00:00, 188MB/s]
-     88%|########8 | 483M/548M [00:02<00:00, 188MB/s]
-     91%|#########1| 501M/548M [00:02<00:00, 188MB/s]
-     95%|#########4| 519M/548M [00:02<00:00, 188MB/s]
-     98%|#########8| 537M/548M [00:03<00:00, 188MB/s]
-    100%|##########| 548M/548M [00:03<00:00, 185MB/s]
+      3%|3         | 16.8M/548M [00:00<00:03, 175MB/s]
+      6%|6         | 34.0M/548M [00:00<00:03, 178MB/s]
+      9%|9         | 51.2M/548M [00:00<00:02, 179MB/s]
+     13%|#2        | 68.6M/548M [00:00<00:02, 180MB/s]
+     16%|#5        | 85.9M/548M [00:00<00:02, 180MB/s]
+     19%|#8        | 103M/548M [00:00<00:02, 180MB/s] 
+     22%|##1       | 120M/548M [00:00<00:02, 180MB/s]
+     25%|##5       | 138M/548M [00:00<00:02, 180MB/s]
+     28%|##8       | 155M/548M [00:00<00:02, 180MB/s]
+     31%|###1      | 172M/548M [00:01<00:02, 180MB/s]
+     35%|###4      | 190M/548M [00:01<00:02, 181MB/s]
+     38%|###7      | 207M/548M [00:01<00:01, 181MB/s]
+     41%|####      | 224M/548M [00:01<00:01, 181MB/s]
+     44%|####4     | 242M/548M [00:01<00:01, 182MB/s]
+     47%|####7     | 259M/548M [00:01<00:01, 182MB/s]
+     51%|#####     | 277M/548M [00:01<00:01, 182MB/s]
+     54%|#####3    | 294M/548M [00:01<00:01, 182MB/s]
+     57%|#####6    | 312M/548M [00:01<00:01, 182MB/s]
+     60%|######    | 329M/548M [00:01<00:01, 182MB/s]
+     63%|######3   | 347M/548M [00:02<00:01, 182MB/s]
+     66%|######6   | 364M/548M [00:02<00:01, 182MB/s]
+     70%|######9   | 382M/548M [00:02<00:00, 182MB/s]
+     73%|#######2  | 400M/548M [00:02<00:00, 183MB/s]
+     76%|#######6  | 417M/548M [00:02<00:00, 177MB/s]
+     79%|#######9  | 434M/548M [00:02<00:00, 178MB/s]
+     82%|########2 | 452M/548M [00:02<00:00, 179MB/s]
+     86%|########5 | 469M/548M [00:02<00:00, 180MB/s]
+     89%|########8 | 486M/548M [00:02<00:00, 180MB/s]
+     92%|#########1| 504M/548M [00:02<00:00, 181MB/s]
+     95%|#########5| 521M/548M [00:03<00:00, 181MB/s]
+     98%|#########8| 538M/548M [00:03<00:00, 181MB/s]
+    100%|##########| 548M/548M [00:03<00:00, 181MB/s]
 
 
 
@@ -761,22 +762,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 4.192042 Content Loss: 4.210833
+    Style Loss : 4.149775 Content Loss: 4.157228
 
     run [100]:
-    Style Loss : 1.140357 Content Loss: 3.024562
+    Style Loss : 1.104719 Content Loss: 3.005375
 
     run [150]:
-    Style Loss : 0.711638 Content Loss: 2.643950
+    Style Loss : 0.700091 Content Loss: 2.638469
 
     run [200]:
-    Style Loss : 0.472736 Content Loss: 2.487448
+    Style Loss : 0.471553 Content Loss: 2.486511
 
     run [250]:
-    Style Loss : 0.342926 Content Loss: 2.400339
+    Style Loss : 0.344631 Content Loss: 2.400878
 
     run [300]:
-    Style Loss : 0.263489 Content Loss: 2.349221
+    Style Loss : 0.263820 Content Loss: 2.348750
 
 
 
@@ -785,7 +786,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  36.713 seconds)
+   **Total running time of the script:** ( 0 minutes  36.749 seconds)
 
 
 .. _sphx_glr_download_advanced_neural_style_tutorial.py:

_images/sphx_glr_reinforcement_ppo_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  0.596 seconds)
+   **Total running time of the script:** ( 0 minutes  0.575 seconds)
 
 
 .. _sphx_glr_download_advanced_numpy_extensions_tutorial.py: