I have trained the stylegan2 + DiffAugment (DiffAugment-stylegan2-pytorch) with a simple model (64*64pixel), like following.
But the model collapse occurred. Like following,
I think the main reason is that the network is too strong(Filters in conv2D keep same). But there are no parameters to adjust that. As I want to generated high quantity images with limited data, the wgan-gp cannot produce attractive results although with DiffAugment. So can you give me some suggestions on this?
Dear,
I have trained the stylegan2 + DiffAugment (DiffAugment-stylegan2-pytorch) with a simple model (64*64pixel), like following.
But the model collapse occurred. Like following,
I think the main reason is that the network is too strong(Filters in conv2D keep same). But there are no parameters to adjust that. As I want to generated high quantity images with limited data, the wgan-gp cannot produce attractive results although with DiffAugment. So can you give me some suggestions on this?