Why no ReflectionPad2d in the two downsampling layers of ResNetGenerator?
j314erre opened this issue · comments
j314erre commented
Why do the 2nd and 3rd Conv2d layers use normal zero padding while all the other Conv2d layers including the ResnetBlocks use ReflectionPad2d?
n_downsampling = 2
for i in range(n_downsampling): # add downsampling layers
mult = 2 ** i
model += [nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, padding=1, bias=use_bias),
norm_layer(ngf * mult * 2),
nn.ReLU(True)]
Jun-Yan Zhu commented
We adopted the network architectures from the fast neural style transfer paper. They did not use reflection padding for the downsampling layers. See this line.
j314erre commented
Thanks for the info!