gpu runnable

Author: jadore801120

main.py

@@ -75,7 +75,7 @@ def mr(text_field, label_field, **kargs):
 # update args and print
 args.embed_num = len(text_field.vocab)
 args.class_num = len(label_field.vocab) - 1
-args.cuda = args.no_cuda and torch.cuda.is_available(); del args.no_cuda
+args.cuda = (not args.no_cuda) and torch.cuda.is_available(); del args.no_cuda
 args.kernel_sizes = [int(k) for k in args.kernel_sizes.split(',')]
 args.save_dir = os.path.join(args.save_dir, datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
 
@@ -93,6 +93,9 @@ def mr(text_field, label_field, **kargs):
         cnn = torch.load(args.snapshot)
     except :
         print("Sorry, This snapshot doesn't exist."); exit()
+
+if args.cuda:
+    cnn = cnn.cuda()
 
 
 # train or predict

model.py

@@ -16,7 +16,8 @@ def __init__(self, args):
         Ks = args.kernel_sizes
 
         self.embed = nn.Embedding(V, D)
-        self.convs1 = [nn.Conv2d(Ci, Co, (K, D)) for K in Ks]
+        #self.convs1 = [nn.Conv2d(Ci, Co, (K, D)) for K in Ks]
+        self.convs1 = nn.ModuleList([nn.Conv2d(Ci, Co, (K, D)) for K in Ks])
         '''
         self.conv13 = nn.Conv2d(Ci, Co, (3, D))
         self.conv14 = nn.Conv2d(Ci, Co, (4, D))
@@ -38,9 +39,14 @@ def forward(self, x):
             x = Variable(x)
 
         x = x.unsqueeze(1) # (N,Ci,W,D)
+
         x = [F.relu(conv(x)).squeeze(3) for conv in self.convs1] #[(N,Co,W), ...]*len(Ks)
+
+
         x = [F.max_pool1d(i, i.size(2)).squeeze(2) for i in x] #[(N,Co), ...]*len(Ks)
+
         x = torch.cat(x, 1)
+
         '''
         x1 = self.conv_and_pool(x,self.conv13) #(N,Co)
         x2 = self.conv_and_pool(x,self.conv14) #(N,Co)
@@ -49,4 +55,4 @@ def forward(self, x):
         '''
         x = self.dropout(x) # (N,len(Ks)*Co)
         logit = self.fc1(x) # (N,C)
-        return logit
+        return logit

mydatasets.py

@@ -77,10 +77,10 @@ def clean_str(string):
         if examples is None:
             path = self.dirname if path is None else path
             examples = []
-            with open(os.path.join(path, 'rt-polarity.neg')) as f:
+            with open(os.path.join(path, 'rt-polarity.neg'), errors='ignore') as f:
                 examples += [
                     data.Example.fromlist([line, 'negative'], fields) for line in f]
-            with open(os.path.join(path, 'rt-polarity.pos')) as f:
+            with open(os.path.join(path, 'rt-polarity.pos'), errors='ignore') as f:
                 examples += [
                     data.Example.fromlist([line, 'positive'], fields) for line in f]
         super(MR, self).__init__(examples, fields, **kwargs)

train.py

@@ -18,10 +18,13 @@ def train(train_iter, dev_iter, model, args):
             feature, target = batch.text, batch.label
             feature.data.t_(), target.data.sub_(1)  # batch first, index align
             if args.cuda:
-                feature, target = feature.cuda(), feature.cuda()
+                feature, target = feature.cuda(), target.cuda()
 
             optimizer.zero_grad()
             logit = model(feature)
+
+            #print('logit vector', logit.size())
+            #print('target vector', target.size())
             loss = F.cross_entropy(logit, target)
             loss.backward()
             optimizer.step()
@@ -52,7 +55,7 @@ def eval(data_iter, model, args):
         feature, target = batch.text, batch.label
         feature.data.t_(), target.data.sub_(1)  # batch first, index align
         if args.cuda:
-            feature, target = feature.cuda(), feature.cuda()
+            feature, target = feature.cuda(), target.cuda()
 
         logit = model(feature)
         loss = F.cross_entropy(logit, target, size_average=False)