Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

Model Map

Open
#1,296 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
10.6k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

many thanks for sharing YoloX, it's amaing model with really good speed.
I get a problem related to model performance. I notice that there is no image preprocessing (except padding), by using non-normalized img, can we get the same result as you mentioned in the paper? e.g. 0.5 mAP from YoloX-l

or do you have other pretrained weight for normalized-img?

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

Review YOLOX's reported image-preprocessing behavior and compare it with the YOLOX-L evaluation setup described in the paper. Verify whether the claimed 0.5 mAP assumes normalized images and whether normalized-image pretrained weights exist. Done means documenting the supported preprocessing and resolving the reported performance discrepancy.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.