Vision-Transformer-ViT icon indicating copy to clipboard operation
Vision-Transformer-ViT copied to clipboard

`total_steps` in train.py

Open JJJYmmm opened this issue 1 year ago • 1 comments

There seems to be a problem in train.py.

total_steps = (len(trainloader) // args.batch_size + 1)  * args.epoches

len(train_loader) is already divided by batch_size. Change it to total_steps = len(trainloader) * args.epoches and it should work!

JJJYmmm avatar Nov 08 '23 08:11 JJJYmmm