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

作者您好,请问anchor是为什么设计成,16,32,64开始吗? #36

Open
wenjunx opened this issue Jun 27, 2023 · 4 comments

Comments

@wenjunx
Copy link

wenjunx commented Jun 27, 2023

我见这部分在论文中没有说明

@Krasjet-Yu
Copy link
Owner

在数据集中取了多张单人脸的图像在原yolov5代码中做inference,再可视化热力图,根据热图设计初始anchor取的整数均值(在均值附近也做了多次取值实验,最后取的16,因为这种做法并没有很好的泛化性,有噪声)。

@wenjunx
Copy link
Author

wenjunx commented Jun 27, 2023

在数据集中取了多张单人脸的图像在原yolov5代码中做inference,再可视化热力图,根据热图设计初始anchor取的整数均值(在均值附近也做了多次取值实验,最后取的16,因为这种做法并没有很好的泛化性,有噪声)。

谢谢解答,请教一下是具体怎么根据热力图取得呢?是根据三个检测层的热力图特征占真实框区域的比例,来估算的吗?16到20.16再到25.40是按照乘以1.26这个规律来取的吗?想学习一下,多谢! @Krasjet-Yu

@Krasjet-Yu
Copy link
Owner

  1. 热力图可以通过CAM(神经网络热力图)得到。
  2. 是的
  3. 具体我忘记了,好像是根据高斯分布的3δ

@wenjunx
Copy link
Author

wenjunx commented Jul 3, 2023

  1. 热力图可以通过CAM(神经网络热力图)得到。
  2. 是的
  3. 具体我忘记了,好像是根据高斯分布的3δ

好的,多谢!

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