Brian
same problem RuntimeError: Error(s) in loading state_dict for Generator: Missing key(s) in state_dict: "identity_embedding".
@akravchuk97 I got the same problem, the loss is always nan where should i add the reset_parameters??
@akravchuk97 i think we implement in different way... actually, i don't really understand how to use this loss function, I still use CrossEntropyLoss() as my criterion, and I put reset_parameters...
> I also encountered this problem and could not download data. Appreciate it if there are any solutions. https://mm.kaist.ac.kr/datasets/voxceleb/#downloads They have another link Only audio available for VoxCeleb1 Both audio...
I know this repo but it takes really really long time to run the script (download from youtube + crop) without 8 V100 GPU. I only have 1 3080, it...
same issue too
Same question
Thanks for replying, I have another question: I have about 70k real img, how many "number of samples used for each training phases" should I set is the best? my...
thank you. FID is really good, but there's another threshold in my homework, which is detecting faces for given images and my output seems generate some abnormal faces (e.g. wrong...
i didn't find truncation , ema generators in your codes, should I add it? i just use your original setting, and change the image size