ycheng

Hi, did you solve this problem?

> > Hi, did you solve this problem? > > @Allencheng97 > > Yes, I forked this repo and changed torch.Dataset() to torch.CIFAR10() (line ~~ 721-719) Thanks!

same question

+1 same problem here.

Try to decrease your batch size, too big batch size may cause this problem and if it is too big it will be nan. Reduce the batch size to 1...

> @rwightman Thanks a lot. I am finetuning, so that ain't an issue as you said. I passed the '`img_size` argument, and everything is fine now. I downloaded the `dataset.py`...

> @etetteh yes, models work fine with arbitrary input channels but the data pipeline components are defaulted to RGB as they've really only been used with color images. > >...

For VTAB-1K, since its setting is very close to few shot which is highly depend on the random seed, my personal suggestion is fixed the cuda,pytorch,torch.backends seed, this also may...