Megvii-BaseDetection / Megvii-BaseDetection/AutoAssign
Performance on VOC
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 144
- Forks
- 17
- PR merge metrics
- No merged PRs in 30d
Description
Hi, 我最近在研究label assign，实验发现使用默认设置下的AutoAssign在VOC上的表现会低于GFL 3个点以上的AP。请问你们有在VOC上尝试过吗？我使用的是mmdet官方repo中的AutoAssign，最大epoch为4，学习率下降在第3 epoch之后，这是mmdet VOC的标准设置。GFL可取得51.8的AP，但AutoAssign只能取得48.4。请问有什么超参会对性能影响较大？
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
Reproduce AutoAssign on VOC using the mmdet official repository settings described: a maximum of 4 epochs and a learning-rate drop after epoch 3. Compare its 48.4 AP with GFL's 51.8 AP, then investigate which hyperparameters affect the difference most. Done means documenting the relevant settings and explaining or resolving the performance gap.
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