Disable path regularization and lazy regularization

[nupurkmr9]

Hi, In the paper, for FFHQ 1k 256x256 training with DiffAugment, it is written that path length regularization and lazy regularization is disabled. If I am not wrong, in the DiffAugment-stylegan2-pytorch repo lazy regularization and path length regularization is still there, right? Just wanted to confirm this before I start any training. :) Thanks!

[zsyzzsoft]

Yes. You may need to change them and possibly some other hyperparameters as said in the paper, to fully reproduce our results in the TensorFlow version.

[nupurkmr9]

Thanks. Can you tell what other hyperparameters need to be changed for FFHQ with config "paper256"?

[zsyzzsoft]

mb=32, mbstd=4, lrate=0.002, and enable the mirror augmentation