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

How to control complexity of vertices? #26

Open
mridvankeles opened this issue Feb 29, 2024 · 1 comment
Open

How to control complexity of vertices? #26

mridvankeles opened this issue Feb 29, 2024 · 1 comment

Comments

@mridvankeles
Copy link

Hello,

As i can see we have c-iou metric which show us the complexity of our predictions. But im not sure how to control the number of vertex predictions. is it handled at the nms phase with topk parametre?

@SarahwXU
Copy link
Owner

SarahwXU commented Mar 1, 2024

Yes, the topk parameter impacts the number of vertex predictions. However, the value of topk is set to make sure that all proper junctions are detected. It barely influences the final complexity of building polygons. In fact, in our method, we suppose that the vertex detection is precise, which means the number of vertices matches the GT. There is no exact parameter for complex adjustment. If it has to be a parameter, the change of value of ''thres'' in the following function may slightly affect the complexity of polygons.

def simple_polygon(poly, thres=10):
By the way, there is a small bug in the code of c-iou metric. I will fix it later. I am still sweating over the draft of my doctoral dissertation.

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