jni / jni/ray

add trainable normalized cut

Open
#26 0 comments 0 reactions 0 assignees View on GitHub
new-feature
Dominant language
Python
Stars
30
Forks
9
PR merge metrics
No merged PRs in 30d

Description

Timothée Cour, Nicolas Gogin, and Jianbo Shi have a [paper](http://www.cis.upenn.edu/~jshi/papers/AISTATS2005.pdf) describing how to learn a spectral graph segmentation function. This could be implemented in ray.

Contributor guide

No contributing guide indexed for this repository

Research direction

No files, tests, or entry points are named. Start by reading the linked AISTATS 2005 paper and inspecting the ray package structure to identify the relevant segmentation entry point. Done means agreeing on the intended trainable normalized-cut behavior and implementing it with coverage for the expected use case.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.