Updated comment section of "Training the Model" (pytorch#110)

oya163 · chsasank · commit 94e3fb3727c2 · 2017-07-07T11:00:18.000+05:30
I believe "The decoder is given the ``&lt;SOS&gt;`` token as its first input, and the last hidden state of the encoder as its first hidden state."
Minute correction on comment section.
diff --git a/intermediate_source/seq2seq_translation_tutorial.py b/intermediate_source/seq2seq_translation_tutorial.py
@@ -538,7 +538,7 @@ def variablesFromPair(pair):
 # To train we run the input sentence through the encoder, and keep track
 # of every output and the latest hidden state. Then the decoder is given
 # the ``<SOS>`` token as its first input, and the last hidden state of the
-# decoder as its first hidden state.
+# encoder as its first hidden state.
 #
 # "Teacher forcing" is the concept of using the real target outputs as
 # each next input, instead of using the decoder's guess as the next input.

Original file line number	Diff line number	Diff line change
`@@ -538,7 +538,7 @@ def variablesFromPair(pair):`
`538`	`538`	`# To train we run the input sentence through the encoder, and keep track`
`539`	`539`	`# of every output and the latest hidden state. Then the decoder is given`
`540`	`540`	# the ``<SOS>`` token as its first input, and the last hidden state of the
`541`		`-# decoder as its first hidden state.`
	`541`	`+# encoder as its first hidden state.`
`542`	`542`	`#`
`543`	`543`	`# "Teacher forcing" is the concept of using the real target outputs as`
`544`	`544`	`# each next input, instead of using the decoder's guess as the next input.`