Describe the origin of pre-trained models

[miursh]

Checklist

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

Description

As mentioned here, TIER IV member should describe the details of provided ML models.

Purpose

Clarify what kind of dataset was used for training.

Possible approaches

Write the following information.

• If trained on a private dataset, at least some information on the nature of the data (e.g. camera images from Japanese traffic lights, lidar data from urban traffic in Europe...)
• training/testing set size, number of objects by types, etc
• test accuracy

Definition of done

Complete the description of the following 5 nodes

• [x] https://github.com/autowarefoundation/autoware.universe/tree/main/perception/lidar_apollo_instance_segmentation
• [ ] https://github.com/autowarefoundation/autoware.universe/tree/main/perception/lidar_centerpoint
• [ ] https://github.com/autowarefoundation/autoware.universe/tree/main/perception/traffic_light_ssd_fine_detector
• [x] https://github.com/autowarefoundation/autoware.universe/tree/main/perception/tensorrt_yolo
• [ ] https://github.com/autowarefoundation/autoware.universe/tree/main/perception/traffic_light_classifier

[xczhanjun]

great

[miursh]

Update for tensorrt_yolo https://github.com/autowarefoundation/autoware.universe/pull/1339

[ktro2828]

For lidar_apollo_instance_segmentation, there is already description of model in README.md

[stale[bot]]

This pull request has been automatically marked as stale because it has not had recent activity.

[stale[bot]]

This pull request has been automatically marked as stale because it has not had recent activity.

[yukke42]

The document of centerpoint has updated in https://github.com/autowarefoundation/autoware.universe/pull/2553.

[yukke42]

All of the task has completed.