hello, thanks a lot for your efforts on reproducing BeautyGAN.
I am also trying to reproduce this paper and can you provide a screenshot of different loss curves during training from tensorboard, which will help me a lot on adjusting the weights of different loss terms.
another question, in line 252-253 of main.py, you divide perc by percep_norm for normalization.
how about substract percep_norm from perc, then divide the result by sqrt(var)?
hello, thanks a lot for your efforts on reproducing BeautyGAN.
I am also trying to reproduce this paper and can you provide a screenshot of different loss curves during training from tensorboard, which will help me a lot on adjusting the weights of different loss terms.
thanks a again~