Merge branch 'main' into jingxu10/2629

pytorch · Nov 8, 2023 · 1f159ad · 1f159ad
2 parents a5eee63 + ab4e99a
commit 1f159ad
Show file tree

Hide file tree

Showing 7 changed files with 455 additions and 7 deletions.
diff --git a/_static/img/rollout_recurrent.png b/_static/img/rollout_recurrent.png
diff --git a/beginner_source/introyt/tensorboardyt_tutorial.py b/beginner_source/introyt/tensorboardyt_tutorial.py
@@ -214,13 +214,14 @@ def forward(self, x):
             # Check against the validation set
             running_vloss = 0.0
 
-            net.train(False) # Don't need to track gradents for validation
+            # In evaluation mode some model specific operations can be omitted eg. dropout layer
+            net.train(False) # Switching to evaluation mode, eg. turning off regularisation
             for j, vdata in enumerate(validation_loader, 0):
                 vinputs, vlabels = vdata
                 voutputs = net(vinputs)
                 vloss = criterion(voutputs, vlabels)
                 running_vloss += vloss.item()
-            net.train(True) # Turn gradients back on for training
+            net.train(True) # Switching back to training mode, eg. turning on regularisation
 
             avg_loss = running_loss / 1000
             avg_vloss = running_vloss / len(validation_loader)

diff --git a/en-wordlist.txt b/en-wordlist.txt
@@ -62,6 +62,7 @@ Colab
 Conv
 ConvNet
 ConvNets
+customizable
 DCGAN
 DCGANs
 DDP

diff --git a/index.rst b/index.rst
@@ -312,15 +312,20 @@ What's new in PyTorch tutorials?
    :link: intermediate/mario_rl_tutorial.html
    :tags: Reinforcement-Learning
 
+.. customcarditem::
+   :header: Recurrent DQN
+   :card_description: Use TorchRL to train recurrent policies
+   :image: _static/img/rollout_recurrent.png
+   :link: intermediate/dqn_with_rnn_tutorial.html
+   :tags: Reinforcement-Learning
+
 .. customcarditem::
    :header: Code a DDPG Loss
    :card_description: Use TorchRL to code a DDPG Loss
    :image: _static/img/half_cheetah.gif
    :link: advanced/coding_ddpg.html
    :tags: Reinforcement-Learning
 
-
-
 .. Deploying PyTorch Models in Production
-Original file line number
+Diff line change
@@ Expand Up / @@ -62,6 +62,7 @@ Colab @@
     Conv
     ConvNet
     ConvNets
+    customizable
     DCGAN
     DCGANs
     DDP
@@ Expand Down @@