data-efficient-gans
data-efficient-gans copied to clipboard
drange of the generative model
Does the drange affect the quality of the generated images? I think the default is [-1,1] in the code. Is there a reason why this as opposed to [0,1]? e.g., does this make training easier?
This is borrowed from recent GAN implementations like StyleGAN2, but I think maybe they do not make much difference.