Kevinz-code

Results 14 comments of Kevinz-code

About the pretrained vit.

Hi, prerained models has been released, see README.md.

img_path is different between "train" and "val"

Thanks for reminding me this error, and we have fixed this part in our code. Best, Ke Zhu

Cross Validation

Hi, Thanks for your question. For your first question, can refer to [ASL](https://github.com/Alibaba-MIIL/ASL), [Q2L](https://github.com/SlongLiu/query2labels) for a comprehensive pipeline of multi-label classification code (which contains standard validation code similar to ours)....

Some problems about vision transformer

Hi, thanks for reproducing our paper. "why set the class token in the code in "VIT_CSRA" ": setting class token at the beginning is the original structure of VIT, which...