RElbers/region-mutual-information-pytorch

PyTorch implementation of the Region Mutual Information Loss for Semantic Segmentation.

27
/ 100
Experimental

This is a tool for machine learning engineers and researchers working on computer vision tasks. It provides a specific type of loss function, the Region Mutual Information Loss, which helps train models to better distinguish and segment different objects or regions within an image. You input predicted segmentation maps and ground truth masks, and it outputs a value indicating the error, guiding model improvements.

No commits in the last 6 months.

Use this if you are developing semantic segmentation models and need a robust loss function to improve the accuracy of pixel-wise object classification.

Not ideal if you are looking for a complete deep learning framework or a general-purpose image processing library, as this focuses specifically on one loss function.

semantic-segmentation computer-vision deep-learning image-analysis model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

26

Forks

1

Language

Python

License

MIT

Last pushed

Oct 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RElbers/region-mutual-information-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.