Megvii-BaseDetection / Megvii-BaseDetection/OTA
关于训练期间正样本数量的问题
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 246
- Forks
- 24
- PR merge metrics
- No merged PRs in 30d
Description
很感谢OTA这个工作被提出，省去了FCOS中的很多人工参数的麻烦。
这里我有一个小疑问，就是使用OTA的时候，训练期间的正样本数量是不是会比原生的FCOS少一些？还是说只在训练的早期会少（可能是这个时候模型还没有收敛到一个比较好的性能，致使不好的预测可能会占比多一些）？
期待作者的解答~
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 the OTA and FCOS positive-sample assignment behavior in the repository; the issue names no file, entry point, or test. Done means documenting a maintainer-confirmed answer about whether OTA produces fewer positive samples overall or mainly during early training.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100