fix bug

Author: L1aoXingyu

06-Natural Language Process/N-Gram.py

@@ -1,6 +1,6 @@
 import torch
-from torch import nn, optim
 import torch.nn.functional as F
+from torch import nn, optim
 from torch.autograd import Variable
 
 CONTEXT_SIZE = 2

06-Natural Language Process/LSTM.py renamed to 06-Natural Language Process/seq-lstm.py

@@ -1,14 +1,14 @@
 __author__ = 'SherlockLiao'
 
 import torch
+import torch.nn.functional as F
 from torch import nn, optim
 from torch.autograd import Variable
-import torch.nn.functional as F
 
-training_data = [
-    ("The dog ate the apple".split(), ["DET", "NN", "V", "DET", "NN"]),
-    ("Everybody read that book".split(), ["NN", "V", "DET", "NN"])
-]
+training_data = [("The dog ate the apple".split(),
+                  ["DET", "NN", "V", "DET", "NN"]),
+                 ("Everybody read that book".split(), ["NN", "V", "DET",
+                                                       "NN"])]
 
 word_to_idx = {}
 tag_to_idx = {}
@@ -38,12 +38,12 @@ def forward(self, x):
 
 
 class LSTMTagger(nn.Module):
-    def __init__(self, n_word, n_char, char_dim, n_dim, char_hidden,
-                 n_hidden, n_tag):
+    def __init__(self, n_word, n_char, char_dim, n_dim, char_hidden, n_hidden,
+                 n_tag):
         super(LSTMTagger, self).__init__()
         self.word_embedding = nn.Embedding(n_word, n_dim)
         self.char_lstm = CharLSTM(n_char, char_dim, char_hidden)
-        self.lstm = nn.LSTM(n_dim+char_hidden, n_hidden, batch_first=True)
+        self.lstm = nn.LSTM(n_dim + char_hidden, n_hidden, batch_first=True)
         self.linear1 = nn.Linear(n_hidden, n_tag)
 
     def forward(self, x, word):
@@ -54,11 +54,16 @@ def forward(self, x, word):
                 char_list.append(character_to_idx[letter.lower()])
             char_list = torch.LongTensor(char_list)
             char_list = char_list.unsqueeze(0)
-            tempchar = self.char_lstm(Variable(char_list).cuda())
+            if torch.cuda.is_available():
+                tempchar = self.char_lstm(Variable(char_list).cuda())
+            else:
+                tempchar = self.char_lstm(Variable(char_list))
             tempchar = tempchar.squeeze(0)
             char = torch.cat((char, tempchar.cpu().data), 0)
         char = char.squeeze(1)
-        char = Variable(char).cuda()
+        if torch.cuda.is_available():
+            char = char.cuda()
+        char = Variable(char)
         x = self.word_embedding(x)
         x = torch.cat((x, char), 1)
         x = x.unsqueeze(0)
@@ -69,8 +74,8 @@ def forward(self, x, word):
         return y
 
 
-model = LSTMTagger(len(word_to_idx), len(character_to_idx), 10,
-                   100, 50, 128, len(tag_to_idx))
+model = LSTMTagger(
+    len(word_to_idx), len(character_to_idx), 10, 100, 50, 128, len(tag_to_idx))
 if torch.cuda.is_available():
     model = model.cuda()
 criterion = nn.CrossEntropyLoss()
@@ -84,8 +89,8 @@ def make_sequence(x, dic):
 
 
 for epoch in range(300):
-    print('*'*10)
-    print('epoch {}'.format(epoch+1))
+    print('*' * 10)
+    print('epoch {}'.format(epoch + 1))
     running_loss = 0
     for data in training_data:
         word, tag = data