When --aug=noaug, is there some differences from tf-version stylegan2?

NVlabs / stylegan2-ada-pytorch

StyleGAN2-ADA - Official PyTorch implementation

https://arxiv.org/abs/2006.06676

Other

4.07k stars 1.16k forks source link

When --aug=noaug, is there some differences from tf-version stylegan2? #76

Open BlingHe opened 3 years ago

BlingHe commented 3 years ago

i want to set --aug=noaug to get pytorch-version stylegan2, so when i set --aug=noaug, is there some differences from tf-version stylegan2?

Y-JIE-CREATOR commented 6 months ago

Have you solved the problem? Are they both equivalent?

Y-JIE-CREATOR commented 6 months ago

I found an example in train.py,that is

   \b
    # Reproduce original StyleGAN2 config F.
    python train.py --outdir=~/training-runs --data=~/datasets/ffhq.zip \\
        --gpus=8 --cfg=stylegan2 --mirror=1 --aug=noaug

So what's mean of 'config F', and If this can prove they are equivalent