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

Separate the param.yaml file for ML model parameters and ML model handle node parameters #6590

Closed
7 tasks done
badai-nguyen opened this issue Mar 11, 2024 · 2 comments
Closed
7 tasks done
Assignees
Labels
component:perception Advanced sensor data processing and environment understanding. (auto-assigned) type:improvement Proposed enhancement

Comments

@badai-nguyen
Copy link
Contributor

badai-nguyen commented Mar 11, 2024

Checklist

  • I've read the contribution guidelines.
  • I've searched other issues and no duplicate issues were found.
  • I've agreed with the maintainers that I can plan this task.

Description

Currently, the parameters releated to ML model and its execution node, including centerpoint and pointpainting are intertwined.

Purpose

To clarify the fixed parameters which related to ML structure or training process and adjustable parameters which can modify by users.

Possible approaches

  1. Separate ML model structure releated paramters and ML model execution node's parameters to different files
  2. Locate ML model structure related param.yaml together with ML weights onnx files
  3. Locate execution's node param.yaml file inside autoware (autoware_launch)

Definition of done

@meliketanrikulu
Copy link
Contributor

Hello @badai-nguyen . Thanks for your effort. Your PR 's looks merged. Is there any other active PR related this issue or can we close this issue.

@badai-nguyen
Copy link
Contributor Author

I close this issue since all neccessary PRs were merged!

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) type:improvement Proposed enhancement
Projects
No open projects
Development

No branches or pull requests

3 participants