Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
AP drop after some epochs
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
hi ，
i train YOLOX_X on my custom datasets: 98000 images, use 4 gpu, 288x288 inputsize , batchsize 48, base lr=0.005/64;
what do you have suggestion for my model AP drop after some epochs， show below illustration：
loss illustration：
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
The report only identifies YOLOX_X training on a custom dataset and provides AP and loss illustrations; it names no source files, tests, or entry points. Start by reproducing the reported training setup and tracing the training and evaluation configuration, but the issue does not define a concrete fix or a completion criterion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100