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

About NW-UCLA #33

Open
SunPengP opened this issue Apr 10, 2023 · 2 comments
Open

About NW-UCLA #33

SunPengP opened this issue Apr 10, 2023 · 2 comments

Comments

@SunPengP
Copy link

In the paper you have mentioned CTR-GCN to get 96.5 on NW-UCLA dataset. However when I trained and ensembled as mentioned in readme, the accuracy I got was only 95%.

Please clarify
@yanghhx
Copy link

yanghhx commented May 8, 2023

I have got only 95%, too. Have you dealt it ?

@hosamyousof
Copy link

@SunPengP @yanghhx
Me too they mentioned in the paper CTR-GCN got 96.8% on NTU60 - Cross View. But when I trained and ensembled the four modalities, I got only 96.51% as described in the issue #36

Please if you figure out what is the reason of the difference let me know. It will be a great help.
Thanks.

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
3 participants
@hosamyousof @SunPengP @yanghhx