0

I have been trying to train a DCGAN implementation in PyTorch. I am getting the following error:

RuntimeError: Calculated padded input size per channel: (3 x 3). Kernel size: (4 x 4). Kernel size can't be greater than actual input size

I have modified the discriminator network defined in this implementation.

The modified discriminator network is as follows:

self.main = nn.Sequential(
           
            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf * 8, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf * 8, ndf * 16, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 16),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf * 16, ndf * 16, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 16),
            nn.LeakyReLU(0.2, inplace=True),
            
            nn.Conv2d(ndf * 16, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )

Thanks in advance!

Jash Rathod
  • 1
  • 1
  • The error is probably not here but in the way you pass your input to the sequential. The padded image is too small, only 3x3 pixels, hence you cannot use a kernel 4x4. – Neb Apr 14 '21 at 14:26
  • @Neb Thanks for sharing. I am still not able to debug it. The rest of the code is the same as [here](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html). I have just tried to modify the layers. – Jash Rathod Apr 15 '21 at 07:02

0 Answers0