Removed unused references to encoder_output in the attention decoder

Author: Vineet John

intermediate_source/seq2seq_translation_tutorial.py

@@ -466,7 +466,7 @@ def __init__(self, hidden_size, output_size, n_layers=1, dropout_p=0.1, max_leng
         self.gru = nn.GRU(self.hidden_size, self.hidden_size)
         self.out = nn.Linear(self.hidden_size, self.output_size)
 
-    def forward(self, input, hidden, encoder_output, encoder_outputs):
+    def forward(self, input, hidden, encoder_outputs):
         embedded = self.embedding(input).view(1, 1, -1)
         embedded = self.dropout(embedded)
 
@@ -591,15 +591,15 @@ def train(input_variable, target_variable, encoder, decoder, encoder_optimizer,
         # Teacher forcing: Feed the target as the next input
         for di in range(target_length):
             decoder_output, decoder_hidden, decoder_attention = decoder(
-                decoder_input, decoder_hidden, encoder_output, encoder_outputs)
+                decoder_input, decoder_hidden, encoder_outputs)
             loss += criterion(decoder_output, target_variable[di])
             decoder_input = target_variable[di]  # Teacher forcing
 
     else:
         # Without teacher forcing: use its own predictions as the next input
         for di in range(target_length):
             decoder_output, decoder_hidden, decoder_attention = decoder(
-                decoder_input, decoder_hidden, encoder_output, encoder_outputs)
+                decoder_input, decoder_hidden, encoder_outputs)
             topv, topi = decoder_output.data.topk(1)
             ni = topi[0][0]
 
@@ -745,7 +745,7 @@ def evaluate(encoder, decoder, sentence, max_length=MAX_LENGTH):
 
     for di in range(max_length):
         decoder_output, decoder_hidden, decoder_attention = decoder(
-            decoder_input, decoder_hidden, encoder_output, encoder_outputs)
+            decoder_input, decoder_hidden, encoder_outputs)
         decoder_attentions[di] = decoder_attention.data
         topv, topi = decoder_output.data.topk(1)
         ni = topi[0][0]