deepinsight / deepinsight/insightface
为什么训练y1的时候会如此慢呢，求助
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
1*GPU, batch_size=128,训练集5.8k_id,21W, speed 886 samples/sec
1*GPU，batch_size=128,训练集95K_id, 280W, speed 99 samples/sec
2*GPU, batch_size=128,训练集95K_id, 280W, speed 136 samples/sec
这是哪里的问题呢？ fc7? 训练集？等等？
同样的训练集95k_id,280W,训练r100，2*GPU,batch_size=64, speed 256 samples/sec
运行的是../recognition/train.py
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.