-
Notifications
You must be signed in to change notification settings - Fork 52
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
简易版本复现问题 #66
Comments
我就是希望在这上面进行一些改进,大佬能给些参考的代码或者你在实现这部分代码时的参考吗 |
发现比较难做一个各种检测器通用的方法 |
代码都在都在这个repo里呀,ld_head.py 和 kd_loss.py |
通用的是很难做的,因为各个检测器都有一些不一样的结构 真正通用的话你可能得去改mmcv的trainer |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
您好!阅读了你们的LD,真是非常impressive的工作!我最近在尝试mmrazor的框架下复现LD。我发现LD的蒸馏直接写进了head里,我希望实现一个简易版的LD,即我直接取出网络的分类头输出的大小为NCHW的cls map,然后转化为(-1,80)类的logits,直接对选出logit进行分类蒸馏,然后再进一步完成对reg map蒸馏,但结果差强人意。分类头输出的是NCHW的map,无论我是用bce loss和kl loss,都没有出现比较好的结果。能问下您这边有类似这种实现方法的尝试或者参考经验吗 十分感谢!
The text was updated successfully, but these errors were encountered: