deepinsight / deepinsight/insightface
A problem in 106 points alignment training !
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
1、when i use 3d datasets to train a 68 points alignement model, there is no problem.
2、but, when i use 2d datasets to train a 106 points alignement model, there is a problem
I think it is related to the datasets.
So, my question is :
1、what dataset should I use when i train a 106 points alignement model ？
2、What else should i pay attention to when train a 106 points alignement model ？
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.