Automated tutorials push

Author: pytorchbot

_downloads/3195443a0ced3cabc0ad643537bdb5cd/introyt1_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ed0fac73",
+   "id": "d3c44a3b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1fac403b",
+   "id": "cadbfc27",
    "metadata": {},
    "source": [
     "\n",

_downloads/4355e2cef7d17548f1e25f97a62828c4/template_tutorial.ipynb

@@ -31,7 +31,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "cca9e040",
+   "id": "545968d6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d7537f93",
+   "id": "b9c43220",
    "metadata": {},
    "source": [
     "\n",

_downloads/63a0f0fc7b3ffb15d3a5ac8db3d521ee/tensors_deeper_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f605c109",
+   "id": "dfe3ad0c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "385743f6",
+   "id": "54349c43",
    "metadata": {},
    "source": [
     "\n",

_downloads/770632dd3941d2a51b831c52ded57aa2/trainingyt.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6e91dc77",
+   "id": "08989ae5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c4fcb891",
+   "id": "56db2c22",
    "metadata": {},
    "source": [
     "\n",

_downloads/c28f42852d456daf9af72da6c6909556/captumyt.ipynb

@@ -37,7 +37,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "da53bf76",
+   "id": "d51cb2b4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e5e459fa",
+   "id": "99578330",
    "metadata": {},
    "source": [
     "\n",

_downloads/e2e556f6b4693c2cef716dd7f40caaf6/tensorboardyt_tutorial.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "71cf7b6f",
+   "id": "e8ab2e66",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5df4ed87",
+   "id": "821eef43",
    "metadata": {},
    "source": [
     "\n",

_downloads/ed9d4f94afb79f7dada6742a06c486a5/autogradyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "16911d73",
+   "id": "2fc67b48",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5bab964e",
+   "id": "e948beaa",
    "metadata": {},
    "source": [
     "\n",

_downloads/fe726e041160526cf828806536922cf6/modelsyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "da367d56",
+   "id": "109c2d90",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a15c695d",
+   "id": "655c25fd",
    "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, 2906.66it/s]
-     16%|#6        | 1600/10000 [00:01<00:10, 765.70it/s]
-     24%|##4       | 2400/10000 [00:02<00:06, 1154.25it/s]
-     32%|###2      | 3200/10000 [00:02<00:04, 1518.98it/s]
-     40%|####      | 4000/10000 [00:02<00:03, 1834.60it/s]
-     48%|####8     | 4800/10000 [00:02<00:02, 2108.97it/s]
-     56%|#####6    | 5600/10000 [00:03<00:01, 2327.16it/s]
-    reward: -2.19 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.80/6.29, grad norm= 307.70, loss_value= 439.06, loss_actor= 12.75, target value: -18.85:  56%|#####6    | 5600/10000 [00:05<00:01, 2327.16it/s]
-    reward: -2.19 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.80/6.29, grad norm= 307.70, loss_value= 439.06, loss_actor= 12.75, target value: -18.85:  64%|######4   | 6400/10000 [00:05<00:04, 788.25it/s] 
-    reward: -1.84 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.67/5.37, grad norm= 113.56, loss_value= 254.95, loss_actor= 13.86, target value: -16.73:  64%|######4   | 6400/10000 [00:07<00:04, 788.25it/s]
-    reward: -1.84 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.67/5.37, grad norm= 113.56, loss_value= 254.95, loss_actor= 13.86, target value: -16.73:  72%|#######2  | 7200/10000 [00:08<00:05, 507.75it/s]
-    reward: -3.68 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.43/5.39, grad norm= 109.65, loss_value= 275.44, loss_actor= 15.73, target value: -14.91:  72%|#######2  | 7200/10000 [00:10<00:05, 507.75it/s]
-    reward: -3.68 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.43/5.39, grad norm= 109.65, loss_value= 275.44, loss_actor= 15.73, target value: -14.91:  80%|########  | 8000/10000 [00:11<00:04, 410.42it/s]
-    reward: -3.46 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.96/4.69, grad norm= 48.92, loss_value= 169.77, loss_actor= 18.82, target value: -19.16:  80%|########  | 8000/10000 [00:13<00:04, 410.42it/s] 
-    reward: -3.46 (r0 = -1.89), reward eval: reward: -0.01, reward normalized=-2.96/4.69, grad norm= 48.92, loss_value= 169.77, loss_actor= 18.82, target value: -19.16:  88%|########8 | 8800/10000 [00:14<00:03, 362.09it/s]
-    reward: -5.27 (r0 = -1.89), reward eval: reward: -4.71, reward normalized=-3.01/5.13, grad norm= 64.85, loss_value= 192.72, loss_actor= 19.04, target value: -19.81:  88%|########8 | 8800/10000 [00:17<00:03, 362.09it/s]
-    reward: -5.27 (r0 = -1.89), reward eval: reward: -4.71, reward normalized=-3.01/5.13, grad norm= 64.85, loss_value= 192.72, loss_actor= 19.04, target value: -19.81:  96%|#########6| 9600/10000 [00:18<00:01, 290.75it/s]
-    reward: -4.04 (r0 = -1.89), reward eval: reward: -4.71, reward normalized=-2.63/4.39, grad norm= 70.28, loss_value= 162.83, loss_actor= 15.91, target value: -19.09:  96%|#########6| 9600/10000 [00:19<00:01, 290.75it/s]
-    reward: -4.04 (r0 = -1.89), reward eval: reward: -4.71, reward normalized=-2.63/4.39, grad norm= 70.28, loss_value= 162.83, loss_actor= 15.91, target value: -19.09: : 10400it [00:21, 257.96it/s]                        
-    reward: -7.61 (r0 = -1.89), reward eval: reward: -4.71, reward normalized=-3.05/5.54, grad norm= 193.22, loss_value= 325.05, loss_actor= 19.07, target value: -19.84: : 10400it [00:24, 257.96it/s]
+      8%|8         | 800/10000 [00:00<00:03, 2743.96it/s]
+     16%|#6        | 1600/10000 [00:01<00:11, 763.17it/s]
+     24%|##4       | 2400/10000 [00:02<00:06, 1135.11it/s]
+     32%|###2      | 3200/10000 [00:02<00:04, 1499.19it/s]
+     40%|####      | 4000/10000 [00:02<00:03, 1815.64it/s]
+     48%|####8     | 4800/10000 [00:02<00:02, 2086.49it/s]
+     56%|#####6    | 5600/10000 [00:03<00:01, 2296.08it/s]
+    reward: -1.88 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-1.03/6.27, grad norm= 311.07, loss_value= 446.30, loss_actor= 12.66, target value: -6.03:  56%|#####6    | 5600/10000 [00:05<00:01, 2296.08it/s]
+    reward: -1.88 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-1.03/6.27, grad norm= 311.07, loss_value= 446.30, loss_actor= 12.66, target value: -6.03:  64%|######4   | 6400/10000 [00:05<00:04, 746.08it/s] 
+    reward: -2.00 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-2.21/5.59, grad norm= 95.63, loss_value= 265.29, loss_actor= 13.03, target value: -14.48:  64%|######4   | 6400/10000 [00:07<00:04, 746.08it/s]
+    reward: -2.00 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-2.21/5.59, grad norm= 95.63, loss_value= 265.29, loss_actor= 13.03, target value: -14.48:  72%|#######2  | 7200/10000 [00:08<00:05, 493.59it/s]
+    reward: -4.82 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-2.49/5.17, grad norm= 53.90, loss_value= 204.50, loss_actor= 14.36, target value: -15.45:  72%|#######2  | 7200/10000 [00:10<00:05, 493.59it/s]
+    reward: -4.82 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-2.49/5.17, grad norm= 53.90, loss_value= 204.50, loss_actor= 14.36, target value: -15.45:  80%|########  | 8000/10000 [00:11<00:04, 401.43it/s]
+    reward: -5.29 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-2.87/5.49, grad norm= 188.91, loss_value= 289.90, loss_actor= 17.97, target value: -19.30:  80%|########  | 8000/10000 [00:13<00:04, 401.43it/s]
+    reward: -5.29 (r0 = -2.36), reward eval: reward: -0.00, reward normalized=-2.87/5.49, grad norm= 188.91, loss_value= 289.90, loss_actor= 17.97, target value: -19.30:  88%|########8 | 8800/10000 [00:14<00:03, 356.31it/s]
+    reward: -3.86 (r0 = -2.36), reward eval: reward: -5.69, reward normalized=-2.50/5.87, grad norm= 115.25, loss_value= 303.35, loss_actor= 18.57, target value: -17.39:  88%|########8 | 8800/10000 [00:17<00:03, 356.31it/s]
+    reward: -3.86 (r0 = -2.36), reward eval: reward: -5.69, reward normalized=-2.50/5.87, grad norm= 115.25, loss_value= 303.35, loss_actor= 18.57, target value: -17.39:  96%|#########6| 9600/10000 [00:18<00:01, 287.48it/s]
+    reward: -4.78 (r0 = -2.36), reward eval: reward: -5.69, reward normalized=-3.09/4.74, grad norm= 56.83, loss_value= 192.36, loss_actor= 19.61, target value: -21.98:  96%|#########6| 9600/10000 [00:20<00:01, 287.48it/s] 
+    reward: -4.78 (r0 = -2.36), reward eval: reward: -5.69, reward normalized=-3.09/4.74, grad norm= 56.83, loss_value= 192.36, loss_actor= 19.61, target value: -21.98: : 10400it [00:22, 254.71it/s]                        
+    reward: -5.00 (r0 = -2.36), reward eval: reward: -5.69, reward normalized=-3.24/4.47, grad norm= 111.75, loss_value= 225.29, loss_actor= 17.31, target value: -21.10: : 10400it [00:24, 254.71it/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  28.285 seconds)
+   **Total running time of the script:** ( 0 minutes  28.685 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): 202.4
+    elapsed time (seconds): 210.7
     loss: 5.168
-    elapsed time (seconds): 118.4
+    elapsed time (seconds): 120.7
 
 
 
@@ -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  29.609 seconds)
+   **Total running time of the script:** ( 5 minutes  40.322 seconds)
 
 
 .. _sphx_glr_download_advanced_dynamic_quantization_tutorial.py:

_images/sphx_glr_neural_style_tutorial_004.png

@@ -410,40 +410,37 @@ 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%|2         | 15.6M/548M [00:00<00:03, 164MB/s]
-      6%|5         | 31.9M/548M [00:00<00:03, 167MB/s]
-      9%|8         | 48.4M/548M [00:00<00:03, 169MB/s]
-     12%|#1        | 64.9M/548M [00:00<00:02, 171MB/s]
-     15%|#4        | 81.4M/548M [00:00<00:02, 171MB/s]
-     18%|#7        | 97.9M/548M [00:00<00:02, 171MB/s]
-     21%|##        | 114M/548M [00:00<00:02, 172MB/s] 
-     24%|##3       | 131M/548M [00:00<00:02, 172MB/s]
-     27%|##6       | 148M/548M [00:00<00:02, 172MB/s]
-     30%|##9       | 164M/548M [00:01<00:02, 173MB/s]
-     33%|###2      | 181M/548M [00:01<00:02, 173MB/s]
-     36%|###5      | 197M/548M [00:01<00:02, 172MB/s]
-     39%|###9      | 214M/548M [00:01<00:02, 173MB/s]
-     42%|####2     | 230M/548M [00:01<00:01, 173MB/s]
-     45%|####5     | 247M/548M [00:01<00:01, 173MB/s]
-     48%|####8     | 264M/548M [00:01<00:01, 172MB/s]
-     51%|#####1    | 280M/548M [00:01<00:01, 172MB/s]
-     54%|#####4    | 296M/548M [00:01<00:01, 172MB/s]
-     57%|#####7    | 313M/548M [00:01<00:01, 173MB/s]
-     60%|######    | 330M/548M [00:02<00:01, 173MB/s]
-     63%|######3   | 346M/548M [00:02<00:01, 173MB/s]
-     66%|######6   | 363M/548M [00:02<00:01, 173MB/s]
-     69%|######9   | 380M/548M [00:02<00:01, 173MB/s]
-     72%|#######2  | 396M/548M [00:02<00:00, 173MB/s]
-     75%|#######5  | 413M/548M [00:02<00:00, 173MB/s]
-     78%|#######8  | 430M/548M [00:02<00:00, 173MB/s]
-     81%|########1 | 446M/548M [00:02<00:00, 173MB/s]
-     84%|########4 | 463M/548M [00:02<00:00, 173MB/s]
-     87%|########7 | 480M/548M [00:02<00:00, 173MB/s]
-     91%|######### | 496M/548M [00:03<00:00, 173MB/s]
-     94%|#########3| 513M/548M [00:03<00:00, 173MB/s]
-     97%|#########6| 529M/548M [00:03<00:00, 174MB/s]
-    100%|#########9| 546M/548M [00:03<00:00, 174MB/s]
-    100%|##########| 548M/548M [00:03<00:00, 173MB/s]
+      3%|3         | 17.6M/548M [00:00<00:03, 184MB/s]
+      7%|6         | 35.6M/548M [00:00<00:02, 186MB/s]
+     10%|9         | 53.8M/548M [00:00<00:02, 188MB/s]
+     13%|#3        | 72.0M/548M [00:00<00:02, 189MB/s]
+     16%|#6        | 90.1M/548M [00:00<00:02, 189MB/s]
+     20%|#9        | 108M/548M [00:00<00:02, 189MB/s] 
+     23%|##3       | 126M/548M [00:00<00:02, 189MB/s]
+     26%|##6       | 144M/548M [00:00<00:02, 189MB/s]
+     30%|##9       | 163M/548M [00:00<00:02, 190MB/s]
+     33%|###3      | 181M/548M [00:01<00:02, 190MB/s]
+     36%|###6      | 199M/548M [00:01<00:01, 190MB/s]
+     40%|###9      | 217M/548M [00:01<00:01, 190MB/s]
+     43%|####2     | 236M/548M [00:01<00:01, 190MB/s]
+     46%|####6     | 254M/548M [00:01<00:01, 190MB/s]
+     50%|####9     | 272M/548M [00:01<00:01, 190MB/s]
+     53%|#####2    | 290M/548M [00:01<00:01, 190MB/s]
+     56%|#####6    | 309M/548M [00:01<00:01, 190MB/s]
+     60%|#####9    | 327M/548M [00:01<00:01, 190MB/s]
+     63%|######2   | 345M/548M [00:01<00:01, 190MB/s]
+     66%|######6   | 363M/548M [00:02<00:01, 190MB/s]
+     70%|######9   | 382M/548M [00:02<00:00, 190MB/s]
+     73%|#######2  | 400M/548M [00:02<00:00, 190MB/s]
+     76%|#######6  | 418M/548M [00:02<00:00, 190MB/s]
+     80%|#######9  | 436M/548M [00:02<00:00, 190MB/s]
+     83%|########2 | 454M/548M [00:02<00:00, 189MB/s]
+     86%|########6 | 472M/548M [00:02<00:00, 189MB/s]
+     89%|########9 | 490M/548M [00:02<00:00, 188MB/s]
+     93%|#########2| 508M/548M [00:02<00:00, 189MB/s]
+     96%|#########6| 527M/548M [00:02<00:00, 189MB/s]
+     99%|#########9| 545M/548M [00:03<00:00, 189MB/s]
+    100%|##########| 548M/548M [00:03<00:00, 189MB/s]
 
 
 
@@ -764,22 +761,22 @@ Finally, we can run the algorithm.
 
     Optimizing..
     run [50]:
-    Style Loss : 3.975973 Content Loss: 4.121006
+    Style Loss : 4.251205 Content Loss: 4.215905
 
     run [100]:
-    Style Loss : 1.140689 Content Loss: 3.033468
+    Style Loss : 1.166493 Content Loss: 3.052896
 
     run [150]:
-    Style Loss : 0.720279 Content Loss: 2.653354
+    Style Loss : 0.716793 Content Loss: 2.662554
 
     run [200]:
-    Style Loss : 0.492001 Content Loss: 2.500135
+    Style Loss : 0.478618 Content Loss: 2.496649
 
     run [250]:
-    Style Loss : 0.353916 Content Loss: 2.407208
+    Style Loss : 0.348233 Content Loss: 2.406508
 
     run [300]:
-    Style Loss : 0.270373 Content Loss: 2.350080
+    Style Loss : 0.266141 Content Loss: 2.351221
 
 
 
@@ -788,7 +785,7 @@ Finally, we can run the algorithm.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  36.929 seconds)
+   **Total running time of the script:** ( 0 minutes  36.865 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  0.566 seconds)
+   **Total running time of the script:** ( 0 minutes  0.591 seconds)
 
 
 .. _sphx_glr_download_advanced_numpy_extensions_tutorial.py: