Update intermediate_source/char_rnn_classification_tutorial.py

mgs28 · jbschlosser · web-flow · commit 8258deb75c3d · 2024-09-23T20:32:32.000-04:00
Co-authored-by: Joel Schlosser &lt;75754324+jbschlosser@users.noreply.github.com&gt;
diff --git a/intermediate_source/char_rnn_classification_tutorial.py b/intermediate_source/char_rnn_classification_tutorial.py
@@ -220,7 +220,7 @@ def __getitem__(self, idx):
 # as regular feed-forward layers.
 # 
 # This CharRNN class implements an RNN with three components. 
-# First, we use the `nn.RNN implemnentation <https://pytorch.org/docs/stable/generated/torch.nn.RNN.html>`__ 
+# First, we use the `nn.RNN implementation <https://pytorch.org/docs/stable/generated/torch.nn.RNN.html>`__ 
 # , next we define a layer that maps the RNN hidden layers to our output and finally we apply a softmax. Using nn.RNN 
 # leads to a significant improvement in performance (e.g. cuDNN-accelerated kernals) versus implementing 
 # each layer as a nn.Linear. It also simplifies the implementation in forward().

Original file line number	Diff line number	Diff line change
`@@ -220,7 +220,7 @@ def __getitem__(self, idx):`
`220`	`220`	`# as regular feed-forward layers.`
`221`	`221`	`#`
`222`	`222`	`# This CharRNN class implements an RNN with three components.`
`223`		-# First, we use the `nn.RNN implemnentation <https://pytorch.org/docs/stable/generated/torch.nn.RNN.html>`__
	`223`	+# First, we use the `nn.RNN implementation <https://pytorch.org/docs/stable/generated/torch.nn.RNN.html>`__
`224`	`224`	`# , next we define a layer that maps the RNN hidden layers to our output and finally we apply a softmax. Using nn.RNN`
`225`	`225`	`# leads to a significant improvement in performance (e.g. cuDNN-accelerated kernals) versus implementing`
`226`	`226`	`# each layer as a nn.Linear. It also simplifies the implementation in forward().`