Remove unused hidden state. (pytorch#435)

Author: darabos

beginner_source/nlp/sequence_models_tutorial.py

@@ -161,20 +161,10 @@ def __init__(self, embedding_dim, hidden_dim, vocab_size, tagset_size):
 
         # The linear layer that maps from hidden state space to tag space
         self.hidden2tag = nn.Linear(hidden_dim, tagset_size)
-        self.hidden = self.init_hidden()
-
-    def init_hidden(self):
-        # Before we've done anything, we dont have any hidden state.
-        # Refer to the Pytorch documentation to see exactly
-        # why they have this dimensionality.
-        # The axes semantics are (num_layers, minibatch_size, hidden_dim)
-        return (torch.zeros(1, 1, self.hidden_dim),
-                torch.zeros(1, 1, self.hidden_dim))
 
     def forward(self, sentence):
         embeds = self.word_embeddings(sentence)
-        lstm_out, self.hidden = self.lstm(
-            embeds.view(len(sentence), 1, -1), self.hidden)
+        lstm_out, _ = self.lstm(embeds.view(len(sentence), 1, -1))
         tag_space = self.hidden2tag(lstm_out.view(len(sentence), -1))
         tag_scores = F.log_softmax(tag_space, dim=1)
         return tag_scores
@@ -201,10 +191,6 @@ def forward(self, sentence):
         # We need to clear them out before each instance
         model.zero_grad()
 
-        # Also, we need to clear out the hidden state of the LSTM,
-        # detaching it from its history on the last instance.
-        model.hidden = model.init_hidden()
-
         # Step 2. Get our inputs ready for the network, that is, turn them into
         # Tensors of word indices.
         sentence_in = prepare_sequence(sentence, word_to_ix)