deepinsight / deepinsight/insightface
Difference between net3, net4, net5, x3, x5 in Retinaface.py?
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
Is net3 a lightweight retinaface model? We are loading the weights of pre-trained retinaface model, RetinaFace-R50, using net3 for testing.
If I understand correctly, RetinaFace-50 are weights obtained by training network with Resnet50? This is net3. And net5 has Resnet-152 as its backbone.
It would help if you could clarify the differences in the network explicitly. Thank you.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.