update for pytorch 1.0 with nograd

TCN/adding_problem/add_test.py

@@ -100,6 +100,7 @@ def train(epoch):
 
 def evaluate():
     model.eval()
+    with torch.no_grad():
         output = model(X_test)
         test_loss = F.mse_loss(output, Y_test)
         print('\nTest set: Average loss: {:.6f}\n'.format(test_loss.item()))

TCN/copy_memory/copymem_test.py

@@ -85,6 +85,7 @@ optimizer = getattr(optim, args.optim)(model.parameters(), lr=lr)
 
 def evaluate():
     model.eval()
+    with torch.no_grad():
         out = model(test_x.unsqueeze(1).contiguous())
         loss = criterion(out.view(-1, n_classes), test_y.view(-1))
         pred = out.view(-1, n_classes).data.max(1, keepdim=True)[1]

TCN/lambada_language/lambada_test.py

@@ -88,6 +88,7 @@ def evaluate(data_source):
     total_loss = 0
     processed_data_size = 0
     correct = 0
+    with torch.no_grad():
         for i in range(len(data_source)):
             data, targets = torch.LongTensor(data_source[i]).view(1, -1), torch.LongTensor([data_source[i][-1]]).view(1, -1)
             data, targets = Variable(data), Variable(targets)

TCN/mnist_pixel/pmnist_test.py

@@ -97,6 +97,7 @@ def test():
     model.eval()
     test_loss = 0
     correct = 0
+    with torch.no_grad():
         for data, target in test_loader:
             if args.cuda:
                 data, target = data.cuda(), target.cuda()

TCN/poly_music/music_test.py

@@ -68,6 +68,7 @@ def evaluate(X_data, name='Eval'):
     eval_idx_list = np.arange(len(X_data), dtype="int32")
     total_loss = 0.0
     count = 0
+    with torch.no_grad():
         for idx in eval_idx_list:
             data_line = X_data[idx]
             x, y = Variable(data_line[:-1]), Variable(data_line[1:])

TCN/word_cnn/word_cnn_test.py

@@ -92,6 +92,7 @@ def evaluate(data_source):
     model.eval()
     total_loss = 0
     processed_data_size = 0
+    with torch.no_grad():
         for i in range(0, data_source.size(1) - 1, args.validseqlen):
             if i + args.seq_len - args.validseqlen >= data_source.size(1) - 1:
                 continue