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

feat(lidar_centerpoint, pointpainting)!: move max_voxel_count from _ml_package.param.yaml #9578

Draft
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

kminoda
Copy link
Contributor

@kminoda kminoda commented Dec 5, 2024

Description

Since max_voxel_count is likely to be tuned for each vehicle / environment, I would like to move this parameter from *_ml_package.param.yaml to *.param.yaml.

Related links

Must be merged with autowarefoundation/autoware_launch#1258

How was this PR tested?

Works for centerpoint

$ ros2 param get /perception/object_recognition/detection/centerpoint/lidar_centerpoint max_voxel_size
Integer value is: 40000

image

Works for pointpainting

$ ros2 param get /perception/object_recognition/detection/pointpainting/pointpainting max_voxel_size
Integer value is: 40000

image

Notes for reviewers

None.

Interface changes

Modifications

Version Parameter Name
Old model_params.max_voxel_count
New max_voxel_count

To TIER IV members:
This PR will be a breaking change for ML models. Please contact the perception team in TIER IV for a proper update of ML models in Web.Auto.

For pointpainting, please use this model: https://evaluation.tier4.jp/evaluation/mlpackages/5b56c824-de65-406e-b12f-d7271589cc70/releases/cfe1a125-84d0-42b2-845c-c03efe896d3e?project_id=zWhWRzei&tab=reports
For centerpoint, please use base/2.0 and the latter version

Effects on system behavior

None.

@github-actions github-actions bot added type:documentation Creating or refining documentation. (auto-assigned) component:perception Advanced sensor data processing and environment understanding. (auto-assigned) tag:require-cuda-build-and-test labels Dec 5, 2024
Copy link

github-actions bot commented Dec 5, 2024

Thank you for contributing to the Autoware project!

🚧 If your pull request is in progress, switch it to draft mode.

Please ensure:

Copy link

codecov bot commented Dec 5, 2024

Codecov Report

Attention: Patch coverage is 0% with 2 lines in your changes missing coverage. Please review.

Project coverage is 29.37%. Comparing base (0b73c13) to head (f75f6b9).

Files with missing lines Patch % Lines
...ion_based_fusion/src/pointpainting_fusion/node.cpp 0.00% 1 Missing ⚠️
perception/autoware_lidar_centerpoint/src/node.cpp 0.00% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #9578      +/-   ##
==========================================
- Coverage   29.37%   29.37%   -0.01%     
==========================================
  Files        1446     1447       +1     
  Lines      108400   108408       +8     
  Branches    42236    42232       -4     
==========================================
+ Hits        31844    31846       +2     
- Misses      73472    73478       +6     
  Partials     3084     3084              
Flag Coverage Δ *Carryforward flag
differential 3.52% <ø> (?)
differential-cuda 6.04% <0.00%> (?)
total 29.37% <ø> (+<0.01%) ⬆️ Carriedforward from 56ff9b8

*This pull request uses carry forward flags. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:perception Advanced sensor data processing and environment understanding. (auto-assigned) run:build-and-test-differential Mark to enable build-and-test-differential workflow. (used-by-ci) tag:require-cuda-build-and-test type:documentation Creating or refining documentation. (auto-assigned)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant