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

performacne gap #8

Open
RichardChen20 opened this issue May 8, 2022 · 2 comments
Open

performacne gap #8

RichardChen20 opened this issue May 8, 2022 · 2 comments

Comments

@RichardChen20
Copy link

Hi, I trained your model using your released codes and datasets, but the performance (~357 mm MPJPE and ~121mm reconst. error) seems to be very large compared to using your pretrained model. Is there any config settings I did not notice? (I didn't change the default setting in your codes)
@xuxy09
Copy link
Owner

xuxy09 commented May 10, 2022

Thanks for your interest in our work. 121mm seems way too high. Can you properly run the evaluation with the pretrained model?

@RichardChen20
Copy link
Author

The performance of your pretrained model is similar to that in your paper (~55mm I didn't remember the precise error), I don't know what's wrong with my training.

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
@xuxy09 @RichardChen20