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

训练loss的一些问题 #17

Closed
Z0211 opened this issue Oct 28, 2019 · 2 comments
Closed

训练loss的一些问题 #17

Z0211 opened this issue Oct 28, 2019 · 2 comments

Comments

@Z0211
Copy link

Z0211 commented Oct 28, 2019

您好,很感谢您的分享。在读论文的时候关于训练loss有些不太明白,想请教下您:
Loss的部分为什么可以用Mean-max(X)以及FL_(p)替代呢?这里不是很懂,可以说下推导过程么?谢谢您!

@zhangxiaosong18
Copy link
Owner

1.Mean-max是一种选择机制,替换学习目标中的max,在训练的开始更平滑,最终学习目标等价于max。
2.FL(p)这里暂无推导的过程,只是用Focal Loss替换 -log(1 - p)交叉熵损失以解决负样本太多的问题。
欢迎致信 zhangxiaosong18@mails.ucas.ac.cn 进一步讨论!

@Z0211
Copy link
Author

Z0211 commented Oct 30, 2019

恩恩,明白了,非常感谢您的回复!谢谢!

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