deepinsight / deepinsight/insightface
About the parallel training time.
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
The training speed is mentioned in paper(8*1080it,8*64,800samples/s),i really want to know the training time with the class number ranging from 10k to 100M.How long does it take to converge?Do you use pretrained model?
Looking for your replay.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.