cenalzw

Training loss becomes nan after a few thousands iterations

4

Thanks for your impressive contribution. I ran the 'train.py' script to directly train a ResNet50 model with 'msceleb_ align_112' training set. The loss functions I applied are ArcFace and Focal...

Thanks for your contribution of SimSwap training code. I saw you choose to use CelebA as your training set, instead of VGGFace2 which is choosen by the author. Considering VGGFace2...