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

instance segmentation #17

Closed

CF2220160244 opened this issue Dec 16, 2019 · 1 comment

CF2220160244 commented Dec 16, 2019

During the inference, i predict instance vectors for x/y coordinates,
How can i get the final instance output?

Collaborator

ozansener commented Dec 17, 2019

You need to run some sort of clustering algorithm to get instance labels. Our metrics and loss only use x/y coordinates. You can check http://openaccess.thecvf.com/content_cvpr_2018/papers/Kendall_Multi-Task_Learning_Using_CVPR_2018_paper.pdf for details as they use OPTICS algorithm. Their implementation is here: https://github.com/alexgkendall/OPTICS_Clustering

ozansener closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment