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.

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

The linear evaluation is very low #3

Open
yanghhx opened this issue Apr 2, 2022 · 2 comments
Open

The linear evaluation is very low #3

yanghhx opened this issue Apr 2, 2022 · 2 comments

Comments

@yanghhx
Copy link

yanghhx commented Apr 2, 2022

I have run your code and the linear evaluation accuracy is only 45.84%. When I set the "param.requires_grad =True" in line 44,49,54 of linear.py, the linear evalution accuracy of NTU60 view can reach 83.3%. However , the operation may be the fine-tuning operation that is described in your paper. I am very confusing.

@2220666627
Copy link

I have the same issue, the linear evaluation is very low, only set the "param.requires_grad =True" of linear.py can reach the 83.3% accuracy.

@Xiangyue-Zhang
Copy link

Maybe try to check your torch version, make sure it is 1.4.0, works for me.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants