Thinklab-SJTU / Thinklab-SJTU/Bench2Drive

About evaluation metric confusion

Open
#159 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.9k
Forks
144
PR merge metrics
No merged PRs in 30d

Description

I tried to evaluate TCP with official ckpt file in my device. However, I find that the results of Merging and Overtaking reversed.
The official are Merging:8.89 and Overtaking:24.29.Mine are Merging:21.43 and Merging:11.11. That's really confusing.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the TCP evaluation on the device with the official checkpoint and compare the Merging and Overtaking outputs with the reported values. The issue names no source file or test, so trace the evaluation entry point used for the checkpoint and verify how these two metrics are produced; done when the discrepancy is explained or corrected.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
autonomous-driving
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.