Closed eps696 closed 4 years ago
Hi @eps696, have not tried that though I'm not quite sure it will work: the dimension seems to be too high and I suspect that the training would be too unstable.
same feeling, thanks
@eps696 we also performed the rectification after the BigGAN's first linear layer. Though it worked, as far as I remember, it was worse compared to the original z.
i'm just not sure it makes real sense to go w from z, as far as we keep the same power (dimensionality) of latents
it does as the w-space has different inner geometry.
is it possible to discover directions in full w space (e.g. [18,512], one [512] latent per layer), instead of single tiled/repeated [512]? that provided way better results for the task of encoding ("projecting") foreign images into StyleGAN latent space, so should also work here.