Junyong You

Any clues?

There are many (nested) for loops, which can be improved. Would the author plan on it?

> > > @junyongyou hmm, i'm never doing tensorflow Aha, I know that. So I am just seeing there might be somebody else :).

Hi, I didn't think into your question carefully. However, I have some feelings that either your input shape (H=1) and/or such small number of training/val samples might be questionable.

> > > Hi, @junyongyou, > concerning H, I have even tried with H=224/W=224 > concerning the number of training/val I also have tried with large numbers ( 420) >...

> > > @junyongyou Did you solve this problem? I also have this problem. No. I didn't and I didn't work on this since then.

My current workaround solution is to use multiple images in a batch. However, it might be better to figure out how to solve the single image issue. In addition, the...

> 1. I have never encountered such a problem before ，you may refine the function of "validate(opt, model=model, loader=dataloader_test……" when bs=1，to see if you can solve this problem，see issue 8....

There are some sub-models that are not in eval mode even the whole model is set to eval. Thus, I don't know how to solve the problem.