convolution-vision-transformers icon indicating copy to clipboard operation
convolution-vision-transformers copied to clipboard
verified publisher icon rishikksh20

Whats the acc of this implementation on ImageNet ?

Open go2sea opened this issue 4 years ago • 1 comments

Thanks for releasing your CVT implementation.

Can you recurrent the accuracy in the paper?

go2sea avatar Apr 08 '21 10:04 go2sea

@go2sea Use this repo: https://github.com/rosinality/vision-transformers-pytorch pre-processing and training script for CvT model. I will try when I have vacant gpus and some extra time.

rishikksh20 avatar Apr 09 '21 06:04 rishikksh20