Instructions to use AutowareFoundation/lidar_centerpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use AutowareFoundation/lidar_centerpoint with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Add manifest version and per-class yaw_norm_thresholds (v4.1)
yaw_norm_thresholds is indexed by the predicted class in the node's postprocess kernel, so it belongs to the model manifest next to class_names. Each manifest also declares the bundle version, which autoware_lidar_centerpoint checks at startup (major 4, minor 1 or later).
Please tag this revision as v4.1 once merged: contributors cannot push tags. The matching code changes are autowarefoundation/autoware_universe#13211, autowarefoundation/autoware_launch#1949 and autowarefoundation/autoware#7274.
- https://github.com/autowarefoundation/autoware_universe/pull/13211
- https://github.com/autowarefoundation/autoware_launch/pull/1949
- https://github.com/autowarefoundation/autoware/pull/7274
Since this pr should be reviewed with this context, I'm posting the references as links for easy navigation.
This is under development. I will contact you when it is ready.
The PRs are reviewed and ready.
btw, can you add me to the autoware huggingface community member? I could not find how to request.
I removed deploy_metadata.yaml and moved contents to standard ml_package.param.yaml.
Please let me know your opinion.
btw, can you add me to the autoware huggingface community member? I could not find how to request.
Sent you an invitation for write access β
Reviewing now.
All look alright! Thanks for the PR.
refs/pr/2 ref