Help -- factorize_weight --

[tengolagan]

Hi,
Please in factorize_weight, what does generator.synthesis.getattr(layer_name).style.weight correspond to exactly ??
i am trying to reimplement your paper and my stylegan is based on this version and I can't figure out the exact correspondances
thanks in advance for your help!!

[Coderx7]

I guess you already know the answer, but if not, or for those who also wonder, you need to grab the linear layer that transforms the w into style, in your modulated conv layer. that would be this line : https://github.com/NVlabs/stylegan2-ada/blob/43eca5156619dd6ee649c70c4bc3f3cab19a5b79/training/networks.py#L104

I'm not familiar with tensorflow, but you need to access the weight for that dense layer.