deepinsight / deepinsight/insightface
onnx conversion performance
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, thank you for the good work.
I have converted arcface model from both mxnet and pytorch to onnx but when I tested this on LFW, there is a performance drop (from 99% to 90%). I wanted to ask if this is just me, or if anyone else noticed this too.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.