search

zihangJiang / TokenLabeling

Pytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"
Apache License 2.0
425 stars 36 forks source link

[ LV-ViT-S pretrained model ] #27

Open IemProg opened 2 years ago

IemProg commented 2 years ago

Hi,

Thanks for the wonderful work. Could you share with us the password to unzip LV-ViT-S pretrained model ?

Thanks !

zihangJiang commented 2 years ago

Hi, I believe no password is needed. Simply download the checkpoint here and use torch.load.

HJQjob commented 3 months ago

Thanks for your excellent work. The checkpoint for LV-ViT small downloaded is a compressed file and cannot be decompressed. It shows that the compressed file is damaged or the compression format is unknown and cannot be opened.

notjzh commented 3 months ago

Thanks for your excellent work. The checkpoint for LV-ViT small downloaded is a compressed file and cannot be decompressed. It shows that the compressed file is damaged or the compression format is unknown and cannot be opened.

It can be directly loaded using torch.load(). Please refer to #8 for more information.