ESOD精度复现与论文有差异
Open
- Dominant language
- Python
- Stars
- 140
- Forks
- 21
- PR merge metrics
- No merged PRs in 30d
Description
使用同样的设定复现出YOLOv5 Vanilla跟论文报告的精度相近，但是跑ESOD-YOLOv5的visdrone-yolov5.yaml发现mAP50差了大概两个点，想请教一下是我哪里没有注意到吗？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the visdrone-yolov5.yaml configuration and compare the reported ESOD-YOLOv5 setup against the paper and the successful YOLOv5 Vanilla reproduction. Re-run the mAP50 evaluation with the same settings, then identify and document the setting or procedural difference needed to explain the roughly two-point gap.
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
- Mostly clear
- Newbie friendliness
- 35/100