You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
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.
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.
The text was updated successfully, but these errors were encountered: