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

负样本K=8192 ,怎么选取,有什么讲究吗? #35

Open
zyf1040895256 opened this issue Aug 31, 2021 · 1 comment
Open

负样本K=8192 ,怎么选取,有什么讲究吗? #35

zyf1040895256 opened this issue Aug 31, 2021 · 1 comment

Comments

@zyf1040895256
Copy link

作者您好,请问您有做过关于对比学习中的K的设置,对模型性能有何影响的实验吗?

@LongguangWang
Copy link
Member

Hi @zyf1040895256, 我们这里的取值参考里moco中K的设置。moco中K默认取值为65536,batch size为256,我们的batch size是32,所以将K设置为8192。关于K对性能的影响,我们之前做过一个简单的实验,减小K会造成性能轻微的下降,而进一步增大K基本不会带来性能增益。

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