AlibabaResearch / AlibabaResearch/efficientteacher
从标准的yolov5s.pt转换过来的efficient-yolov5s.pt对相同的数据集验证效果有偏差
Open
- Dominant language
- Python
- Stars
- 813
- Forks
- 126
- PR merge metrics
- No merged PRs in 30d
Description
作者您好，准确率和mAP.5:.95大概低了两个点，召回率和mAp.5低了零点几，请问这种现象是正常的吗？是因为验证部分的代码机制不一样吗？
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.