Variational-Autoencoder-PyTorch
Variational-Autoencoder-PyTorch copied to clipboard
Input reshape
Why you reshape input before passing to encoder?
def forward(self, x):
mu, logvar = self.encode(x.view(-1, self.nc, self.ndf, self.ngf))
line 149 self.ndf, self.ngf - are numbers of filters(channels). Am I wrong?