Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Vit-B IN21K weights #17

Open
umarkhalidAI opened this issue Oct 13, 2022 · 4 comments
Open

Vit-B IN21K weights #17

umarkhalidAI opened this issue Oct 13, 2022 · 4 comments

Comments

@umarkhalidAI
Copy link

Can you please share the converted weights of IN21K that can be used to finetune for action recognition?
@ShoufaChen
Copy link
Owner

Hi,

Please find the checkpoint at https://github.com/ShoufaChen/AdaptFormer/releases/download/v0.1/vit_base_patch16_224_in21k_to_video_tz.pth

@umarkhalidAI
Copy link
Author

It gives the following error when I use the above weights:
File "/home/taoyang/PycharmProjects/AdaptFormer-main/util/pos_embed.py", line 122, in interpolate_pos_embed_ori
pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2)
RuntimeError: shape '[-1, 14, 14, 768]' is invalid for input of size 151296

@ShoufaChen
Copy link
Owner

Could you give post complete log?

@umarkhalidAI
Copy link
Author

I think we have to delete the following keys
del checkpoint_model['cls_token']
del checkpoint_model['pos_embed']

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ShoufaChen @umarkhalidAI