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.

Sign up for GitHub

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

Jump to bottom

embedding没有度量性问题（相同人不同人的embedding距离无差别） #77

Open
wensi2690 opened this issue Mar 12, 2021 · 0 comments
Open

embedding没有度量性问题（相同人不同人的embedding距离无差别） #77

wensi2690 opened this issue Mar 12, 2021 · 0 comments

Comments

@wensi2690
Copy link

使用预训练的模型，在lfw/agedb_30/cfp_ff这些验证数据集中进行了验证，精度确实都很高。但是当我自己构建相同人pair/不同人pair构建了两两为一组的数据集，并计算组内的两张图片之间的distance时，发现相同人和不同人的距离没有明显的一个大一个小的差别，这很奇怪？distance我尝试了多种方案，包含L2_dist、normed_L2_dist、angular_dist、cosine_dist，结果都是一样，没有度量性？这个不符合arcface损失函数设计的直觉
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@wensi2690