Pytorch DCGAN example for kernel 3

Question

I tried out the pytorch dcgan example and it worked fine but when I tried to change the kernel from 4x4 to 3x3. I only changed the kernel and It gave the following error. Why this error is occurring? To solve this what changes are needed?

ValueError: Using a target size (torch.Size([64])) that is different to the input size (torch.Size([256])) is deprecated. Please ensure they have the same size.

Here is the generator:

class Generator(nn.Module):
def __init__(self, ngpu):
    super(Generator, self).__init__()
    self.ngpu = ngpu
    self.main = nn.Sequential(
        # input is Z, going into a convolution
        nn.ConvTranspose2d( nz, ngf * 8, kernel_size, 1, 0, bias=False), 
        nn.BatchNorm2d(ngf * 8),
        nn.ReLU(True),
        # state size. (ngf*8) x 4 x 4
        nn.ConvTranspose2d(ngf * 8, ngf * 4, kernel_size, 2, 1, bias=False),
        nn.BatchNorm2d(ngf * 4),
        nn.ReLU(True),
        # state size. (ngf*4) x 8 x 8
        nn.ConvTranspose2d( ngf * 4, ngf * 2, kernel_size, 2, 1, bias=False),
        nn.BatchNorm2d(ngf * 2),
        nn.ReLU(True),
        # state size. (ngf*2) x 16 x 16
        nn.ConvTranspose2d( ngf * 2, ngf, kernel_size, 2, 1, bias=False),
        nn.BatchNorm2d(ngf),
        nn.ReLU(True),
        # state size. (ngf) x 32 x 32
        nn.ConvTranspose2d( ngf, nc, kernel_size, 2, 1, bias=False),
        nn.Tanh()
        # state size. (nc) x 64 x 64
    )

def forward(self, input):
    return self.main(input)

discriminator code:

class Discriminator(nn.Module):
def __init__(self, ngpu):
    super(Discriminator, self).__init__()
    self.ngpu = ngpu
    self.main = nn.Sequential(
        # input is (nc) x 64 x 64
        nn.Conv2d(nc, ndf, kernel_size, 2, 1, bias=False),  
        nn.LeakyReLU(0.2, inplace=True),
        # state size. (ndf) x 32 x 32
        nn.Conv2d(ndf, ndf * 2, kernel_size, 2, 1, bias=False),
        nn.BatchNorm2d(ndf * 2),
        nn.LeakyReLU(0.2, inplace=True),
        # state size. (ndf*2) x 16 x 16
        nn.Conv2d(ndf * 2, ndf * 4, kernel_size, 2, 1, bias=False),
        nn.BatchNorm2d(ndf * 4),
        nn.LeakyReLU(0.2, inplace=True),
        # state size. (ndf*4) x 8 x 8
        nn.Conv2d(ndf * 4, ndf * 8, kernel_size, 2, 1, bias=False),
        nn.BatchNorm2d(ndf * 8),
        nn.LeakyReLU(0.2, inplace=True),
        # state size. (ndf*8) x 4 x 4
        nn.Conv2d(ndf * 8, 1, kernel_size, 1, 0, bias=False),
        
        # 1x1x1
        nn.Sigmoid()
    )

def forward(self, input):
    return self.main(input)

The error showing line is: In the training loop

        # Calculate loss on all-real batch
    errD_real = criterion(output, label)

Here criterion = nn.BCELoss()

Whole training loop:

img_list = []
G_losses = []
D_losses = []
iters = 0
# For each epoch
for epoch in range(num_epochs):
    # For each batch in the dataloader
    for i, data in enumerate(dataloader, 0):
        
        ############################
        # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))
        ###########################
        ## Train with all-real batch
        netD.zero_grad()
        # Format batch
        real_cpu = data[0].to(device)
        #real_cpu = (data.unsqueeze(dim=1).type(torch.FloatTensor)).to(device)
        b_size = real_cpu.size(0)
        label = torch.full((b_size,), real_label,dtype=torch.float, device=device, )
        # Forward pass real batch through D
        output = netD(real_cpu).view(-1)
        # Calculate loss on all-real batch
        errD_real = criterion(output, label)#ERROR
        # Calculate gradients for D in backward pass
        errD_real.backward()
        D_x = output.mean().item()

        ## Train with all-fake batch
        # Generate batch of latent vectors
        noise = torch.randn(b_size, nz, 1, 1, device=device)
        # Generate fake image batch with G
        fake = netG(noise)
        label.fill_(fake_label)
        # Classify all fake batch with D
        output = netD(fake.detach()).view(-1)
        # Calculate D's loss on the all-fake batch
        errD_fake = criterion(output, label)
        # Calculate the gradients for this batch
        errD_fake.backward()
        D_G_z1 = output.mean().item()
        # Add the gradients from the all-real and all-fake batches
        errD = errD_real + errD_fake
        # Update D
        optimizerD.step()

        ############################
        # (2) Update G network: maximize log(D(G(z))) using 'log D' trick
        ###########################
        netG.zero_grad()
        label.fill_(real_label)  # fake labels are real for generator cost
        # Since we just updated D, perform another forward pass of all-fake batch through D
        output = netD(fake).view(-1)
        # Calculate G's loss based on this output
        errG = criterion(output, label)
        # Calculate gradients for G
        errG.backward()
        D_G_z2 = output.mean().item()
        # Update G
        optimizerG.step()
        
        # Output training stats
        if i % 50 == 0:
            print('[%d/%d][%d/%d]\tLoss_D: %.4f\tLoss_G: %.4f\tD(x): %.4f\tD(G(z)): %.4f / %.4f'
                  % (epoch, num_epochs, i, len(dataloader),
                     errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))
        
        # Save Losses for plotting later
        G_losses.append(errG.item())
        D_losses.append(errD.item())
        
        # Check how the generator is doing by saving G's output on fixed_noise
        if (iters % 500 == 0) or ((epoch == num_epochs-1) and (i == len(dataloader)-1)):
            with torch.no_grad():
                fake = netG(fixed_noise).detach().cpu()
            img_list.append(vutils.make_grid(fake, padding=2, normalize=True))
            
        iters += 1