Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
mAP stays at 0 when training coco128 example
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
I followed the tutorial closely and encountered multiple issues with my custom dataset, which is why I decided to try the provided example first.
What I did:
- extract coco128 to datasets/coco128
- execute
python3 tools/train.py -f exps/example/custom/yolox_s.py -d 1 -b 64 --fp16 -c yolox_s.pthwith yolox_s.pth laying in the current folder and being freshly downloaded.
The Problem:
Training does not seem to work properly; There are no errors, but AP values stay at 0 and average inference time is also 0ms.
Could it be that the sample is not working on the latest repo version?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the command in tools/train.py with exps/example/custom/yolox_s.py and the datasets/coco128 directory described in the report. Check the training output and screenshot conditions, then determine why AP and inference time remain at zero; done means the example runs with meaningful metrics or the failure is clearly documented.
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
- 35/100