diff --git a/README.md b/README.md
index 4209c2d0..af95fe39 100644
--- a/README.md
+++ b/README.md
@@ -32,7 +32,7 @@ Alternatively you can build your own dataset by setting up the following directo
     |   |   └── test               # Testing
     |   |   |   ├── A              # Contains domain A images (i.e. Bruce Wayne)
     |   |   |   └── B              # Contains domain B images (i.e. Batman)
-    
+
 ### 2. Train!
 ```
 ./train --dataroot datasets/<dataset_name>/ --cuda
@@ -43,7 +43,7 @@ Both generators and discriminators weights will be saved under the output direct
 
 If you don't own a GPU remove the --cuda option, although I advise you to get one!
 
-You can also view the training progress as well as live output images by running ```python3 -m visdom``` in another terminal and opening [http://localhost:8097/](http://localhost:8097/) in your favourite web browser. This should generate training loss progress as shown below (default params, horse2zebra dataset):
+You can also view the training progress as well as live output images by running ```python3 -m visdom.server``` in another terminal and opening [http://localhost:8097/](http://localhost:8097/) in your favourite web browser. This should generate training loss progress as shown below (default params, horse2zebra dataset):
 
 ![Generator loss](https://github.com/ai-tor/PyTorch-CycleGAN/raw/master/output/loss_G.png)
 ![Discriminator loss](https://github.com/ai-tor/PyTorch-CycleGAN/raw/master/output/loss_D.png)
diff --git a/train b/train
index 95160b51..21e53592 100755
--- a/train
+++ b/train
@@ -72,19 +72,19 @@ lr_scheduler_D_B = torch.optim.lr_scheduler.LambdaLR(optimizer_D_B, lr_lambda=La
 Tensor = torch.cuda.FloatTensor if opt.cuda else torch.Tensor
 input_A = Tensor(opt.batchSize, opt.input_nc, opt.size, opt.size)
 input_B = Tensor(opt.batchSize, opt.output_nc, opt.size, opt.size)
-target_real = Variable(Tensor(opt.batchSize).fill_(1.0), requires_grad=False)
-target_fake = Variable(Tensor(opt.batchSize).fill_(0.0), requires_grad=False)
+target_real = Variable(Tensor(opt.batchSize,1).fill_(1.0), requires_grad=False)
+target_fake = Variable(Tensor(opt.batchSize,1).fill_(0.0), requires_grad=False)
 
 fake_A_buffer = ReplayBuffer()
 fake_B_buffer = ReplayBuffer()
 
 # Dataset loader
-transforms_ = [ transforms.Resize(int(opt.size*1.12), Image.BICUBIC), 
-                transforms.RandomCrop(opt.size), 
+transforms_ = [ transforms.Resize(int(opt.size*1.12), Image.BICUBIC),
+                transforms.RandomCrop(opt.size),
                 transforms.RandomHorizontalFlip(),
                 transforms.ToTensor(),
                 transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5)) ]
-dataloader = DataLoader(ImageDataset(opt.dataroot, transforms_=transforms_, unaligned=True), 
+dataloader = DataLoader(ImageDataset(opt.dataroot, transforms_=transforms_, unaligned=True),
                         batch_size=opt.batchSize, shuffle=True, num_workers=opt.n_cpu)
 
 # Loss plot
@@ -128,7 +128,7 @@ for epoch in range(opt.epoch, opt.n_epochs):
         # Total loss
         loss_G = loss_identity_A + loss_identity_B + loss_GAN_A2B + loss_GAN_B2A + loss_cycle_ABA + loss_cycle_BAB
         loss_G.backward()
-        
+
         optimizer_G.step()
         ###################################
 
@@ -157,7 +157,7 @@ for epoch in range(opt.epoch, opt.n_epochs):
         # Real loss
         pred_real = netD_B(real_B)
         loss_D_real = criterion_GAN(pred_real, target_real)
-        
+
         # Fake loss
         fake_B = fake_B_buffer.push_and_pop(fake_B)
         pred_fake = netD_B(fake_B.detach())
@@ -172,7 +172,7 @@ for epoch in range(opt.epoch, opt.n_epochs):
 
         # Progress report (http://localhost:8097)
         logger.log({'loss_G': loss_G, 'loss_G_identity': (loss_identity_A + loss_identity_B), 'loss_G_GAN': (loss_GAN_A2B + loss_GAN_B2A),
-                    'loss_G_cycle': (loss_cycle_ABA + loss_cycle_BAB), 'loss_D': (loss_D_A + loss_D_B)}, 
+                    'loss_G_cycle': (loss_cycle_ABA + loss_cycle_BAB), 'loss_D': (loss_D_A + loss_D_B)},
                     images={'real_A': real_A, 'real_B': real_B, 'fake_A': fake_A, 'fake_B': fake_B})
 
     # Update learning rates