Closed tmramalho closed 3 years ago
yes, it was one of the experiments which I want to validate if tanh is necessary. It turns out tanh seems not to play a key role here, so I forget to add them back. Please see also the official stylegan2 implementation where they also do not use tanh for the output image. I cannot make the conclusion if tanh is useful or not, I suggest try it on your own dataset to verify, I also would like to see the outcome.
In models.py on lines 168 - 178
It looks like when returning an image of size 1024, the output of modules
to_128
andto_big
are wrapped by a tanh, while for images 256 and 512 they are not. I guess they were all supposed to be wrapped in tanh?