Fisher

Problems about Usage of SyncSN

12

Very nice work! I try to use your train code in face_recognition, but I met some problems. Frist, `rank = int(os.environ['RANK'])` and `world_size = int(os.environ['WORLD_SIZE'])` don't have values, so I...

A question about training code

2

Hi, nice code, but I'm confused about the training code of encoder. I think the training of encoder via CPC is unsupervised, however, you used some label information (made by...

Is focalloss2d implementation correct?

1

Hello, I found you use `pt = torch.exp(logpt)` to calculate probability, but which sample's probability is represented by `pt`. I think `pt` represents the probability of a sample, not the...