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

About Train And Test in Other Datasets #9

Open
Akina2001 opened this issue Dec 4, 2024 · 1 comment
Open

About Train And Test in Other Datasets #9

Akina2001 opened this issue Dec 4, 2024 · 1 comment

Comments

@Akina2001
Copy link

Hello,
Thank you for open-sourcing this work. I have a few questions regarding it. When I tried to reproduce this work on a similar snowykitti dataset, I found that I was able to train the model normally, but when using the trained weights for evaluation, all predictions were incorrect, with both TP and FN being 0. Interestingly, when I used a model pre-trained with WADS without changing anything else, I was able to get reasonable results, although the recall also tended towards 0.

@tn00364361
Copy link
Member

Unfortunately, this repo has not been tested on SnowKITTI.

Interestingly, when I used a model pre-trained with WADS without changing anything else, I was able to get reasonable results, although the recall also tended towards 0.

Can you post some example visualizations showing positive & negative points separately?

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