Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
1.95k
stars
374
forks
source link
Missing check of when (step+1) == len(trainset) in gradient_accumulation #48
Open
animesh-007 opened 2 years ago
Here in the if condition code, is check for (step+1) == len(trainset) missing?
Reference --> Reference code