Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于TA策略与d_online #66

Open
StrongerzZ opened this issue Dec 21, 2021 · 1 comment
Open

关于TA策略与d_online #66

StrongerzZ opened this issue Dec 21, 2021 · 1 comment

Comments

@StrongerzZ
Copy link

大佬你好,感谢你开源的代码。

我在阅读蒸馏部分时有如下疑问,希望能得到你的解答:

1.d_online开与关的区别:是否为T网络是否参与蒸馏时的参数更新。如果是的话,train.py中的t_model似乎没有加入optimizer中,无法进行参数更新;

2.TA策略:没有找到strategy 3 的TA策略部分代码;

3.蒸馏特征:对于T与S网络分别选取的哪些层参与d_feature训练,大佬是否对这方面做过相关实验(是否通常选取骨干网络的较深层特征,特征蒸馏层数的多少与位置是否对结果有相关影响)。

期待大佬和各路大神们回复,一起交流进步!

@Syencil
Copy link
Owner

Syencil commented Dec 22, 2021

  1. 在线蒸馏是T和S一起训练,是需要将T加入optimizer中的,节约训练时间但是显存消耗大。做实验的时候已经训练了yolo5s作为T,离线做就行
  2. 离线策略
  3. 没有,你可以多试试

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants