deepinsight / deepinsight/insightface
Train scrfd very low
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I retrain scrfd model with scrfd_10g_bnkps.py config file on 4 A100 gpus. But training speed is very low. The log file show "lr: 1.666e-05, eta: 76 days, 3:05:39, time: 0.565, data_time: 0.139, memory: 8009, loss_cls: 0.0006, loss_bbox: 2.0173, loss_kps: 2.2101, loss: 4.2280". How long does it take you to train the model?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.