deepinsight / deepinsight/insightface
Issue after converting RetinaFace model to openVino
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I have tried to convert the RetinaFace(R-50 model) to openVino but the accuracy and no. of detection is getting less. I am getting FPS of 7 on GPU and 0.01 on CPU with original R-50 model and no. of detection is 427 and precision - 0.721 recall 0.744. But after conversion FPS on CPU increased but no of detection decreased to 12.
Please help if you have tried.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.