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

Can't reproduce the results #114

Open
WesLee88524 opened this issue Dec 28, 2023 · 2 comments
Open

Can't reproduce the results #114

WesLee88524 opened this issue Dec 28, 2023 · 2 comments

Comments

@WesLee88524
Copy link

hi, I use the pre-trained models you released and follow the GET_STARTED.md to evaluate them on MOT17, MOT20, and dancetrack.

However I can't get the performance as you said in papers:
image

I am confused why it is worse.

@djdodsjsjx
Copy link

hi, I use the pre-trained models you released and follow the GET_STARTED.md to evaluate them on MOT17, MOT20, and dancetrack.

However I can't get the performance as you said in papers: image

I am confused why it is worse.

Hello,I noticed you had issues replicating the OC-SORT algorithm's performance as stated in the paper. Have you managed to resolve this? If yes, could you share your solution?

@noahcao
Copy link
Owner

noahcao commented May 15, 2024

Did you also run the linear interpolation stage? The results on MOT17 and MOT20 are by default after the post-processing of linear interpolation as in previous methods.

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