About Mapper in Latent Mapper, does PixelNorm normalize the right dim?
Big-Brother-Pikachu opened this issue · 0 comments
Big-Brother-Pikachu commented
Thanks for sharing this wonderful work! Here I am a little confused with the normalization layer:
StyleCLIP/mapper/latent_mappers.py
Line 16 in adc836d
In the StyleGAN2 mapper, as the input is always (Batch, latent_dim), the normalization layer is right here.
StyleCLIP/models/stylegan2/model.py
Line 16 in adc836d
But in the latent mapper, I think the input is always (Batch, n_latent, latent_dim)(Maybe I am wrong here), thus the normalization layer seems doesn't do the right normalization.
I think for stylespace mapper, this reshape is right:
StyleCLIP/mapper/latent_mappers.py
Line 98 in adc836d
But for the others, some operations that are not intended may occur as PixelNorm normalize the wrong dim.
StyleCLIP/mapper/latent_mappers.py
Lines 62 to 67 in adc836d
Am I right or do I misunderstand something? Look forward to you reply, thanks.