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

offset的ground truth怎样产生的 #579

Open
JuvenileInWind opened this issue Jan 10, 2020 · 1 comment
Open

offset的ground truth怎样产生的 #579

JuvenileInWind opened this issue Jan 10, 2020 · 1 comment

Comments

@JuvenileInWind
Copy link

请问一下,在关节点检测问题中,预测的offset_map是nHW(n是关节点的个数)的,但一个关键点只会产生一个offset值,那么在构建offset_map的target的时候,是整张map都是这一个值吗?还是怎样构成的呢?

@macqueen09
Copy link

In paper “4.2 We considered the pose as a k x 2-dimensional property of the center point , and parametrize each keypoint bu an offset to the center point . **we directly regress to the joint offsets(in pixels) with an L1 loss ** ”
Why use pixels not a rate , that way vary unusual
问下姿态估计部分的归回,为什么要用像素来回归,这样好像就会缺少一些尺度不变性吧

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