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

Evaluate the metrics question #4

Open
Yippr opened this issue Nov 4, 2024 · 1 comment
Open

Evaluate the metrics question #4

Yippr opened this issue Nov 4, 2024 · 1 comment

Comments

@Yippr
Copy link

Yippr commented Nov 4, 2024

Thank you for your work. I used the 26.3M pretrained weights you provided, but the driving score I obtained is somewhat low. I'm having some problems evaluating metrics.Could you please confirm if the weights you provided were trained after using PlanKD? Is there anything I should pay attention to during the evaluation process?

@tulerfeng
Copy link
Owner

tulerfeng commented Nov 4, 2024

Thank you for your question. I can confirm that the weights are accurate. The evaluation results on Town05 Long and Town05 Short in the CARLA simulator often exhibit significant variance. Therefore, if your score in a single evaluation is somewhat lower or higher (e.g., ±10), this is normal. You can try to run multiple times for evaluations to observe a more consistent average score.

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

2 participants