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

How to generate the Neural Modules? #4

Open
BoMingZhao opened this issue Mar 27, 2024 · 1 comment
Open

How to generate the Neural Modules? #4

BoMingZhao opened this issue Mar 27, 2024 · 1 comment

Comments

@BoMingZhao
Copy link

I appreciate your excellent work. I would like to ask how the Neural Modules mentioned in the paper are generated. Because when I read the code, I feel that the data is preprocessed, and the tool box only reads information from the .pkl file.

@PointsCoder
Copy link
Collaborator

Thanks for your interest in our work! We pre-processed the perception results from the modules in uniad. The data caching process is deeply integrated into the uniad repo, so it is hard to move the code into this repo. If you'd like to reproduce the data caching part, you can simply load the pretrained checkpoint from the uniad model and hook the detection/prediction/map/occ results from its intermediate outputs. You will get the same cached data.

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