Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
Low accuracy on custom coco format dataset
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
你好，感谢你们工作的开源，我把自己的数据转换成coco格式后，在大约20epoch的时候，训练100个epoch准确度还是很低，total_loss基本就不变了，请问下会是什么原因导致的呢
这个是我的训练命令：python tools/train.py -n yolox_tiny -f /YOLOX-main/exps/example/yolox_voc/yolox_my.py -d 2 -b 16 --fp16 -o
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 reviewing tools/train.py and the experiment file at /YOLOX-main/exps/example/yolox_voc/yolox_my.py, then compare the custom dataset configuration with the COCO-format expectations. Reproduce the training command if the dataset and configuration are available; done would mean identifying the cause of the unchanged total_loss and documenting a concrete correction or missing configuration.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- 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