SpecAugment icon indicating copy to clipboard operation
SpecAugment copied to clipboard

The training speed

Open xjwla opened this issue 5 years ago • 1 comments

When I use the spec_augment in my network,the training speed become very slowly.How to solve this problem?

xjwla avatar Aug 28 '20 01:08 xjwla

https://github.com/IMLHF/SpecAugmentPyTorch, this support batch and channel, and fix time wrap bugs by using torch functions. set batch=True in SpecAugmentTorch

IMLHF avatar Dec 31 '21 10:12 IMLHF