Kepan Nan
Thank you for your response!
I did use train_DAN.py and set num_workers=4.Then sometime it is possible to stuck.
Maybe you misunderstood my question. I mean, I trained 4 times with same code, and use 4 model_best.pth.tar to test. There is a big performance gap between 4 model_best.pth.tar
> It should only be `None` after `optimizer.zero_grad()`; `booster.backward` was doing `torch.optim.Optimizer.backward(loss)`. Would you mind printing the contents of `loss` to see if it is `NaN`? Thanks for reply. `loss`...
> > I trained an opensora model with webvid. The generated videos are shaking and unstable. Can you give me some reasons or suggestions？Is there some training tricks? > >...
> Thanks for the swift response. But the problem is, if the code finds the videos downloaded and tries to find them in the /tmp file, then even it fails,...
> Thanks for your reply. It worked using another IP. Hi, could teach me how to change IP? Thank you.