deepinsight / deepinsight/insightface
recognition部分中在backbone部分加入attention有用吗？
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
recognition部分中在backbone部分加入attention有用吗？我看mxnet和torch两种框架的训练代码里，mxnet默认是采用了没加注意力的iresnet50，而torch的backbone代码里根本没有attention模块，难道是加了attention没用？有谁做过这方面的对比实验吗？
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.