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

seed targetness label #1

Closed
gongshichina opened this issue Apr 3, 2020 · 1 comment
Closed

seed targetness label #1

gongshichina opened this issue Apr 3, 2020 · 1 comment

Comments

@gongshichina
Copy link

label = label[0:128]

Hello, thanks for your good job. I have a question about this line in your code:

Why we can just take the first 128 numbers in the target mask as seed targetness label?

@HaozheQi
Copy link
Owner

HaozheQi commented Apr 4, 2020

Hi, @gongshichina ,

Thanks for your attention to our work.Given an input point cloud from search area, we normalize the component points into 1024 ones with random abandoning or duplicating. The result points are fed into three-layer PointNet++ with 8 times down-sampling and yielding 128 seeds. The downsampling is actually a random process. Since the input points have been randomized, here we sample the first 128 points as final seeds. This explains the number selection in your question.

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