TuSimple/TuSimple-DUC

Understanding Convolution for Semantic Segmentation

49
/ 100
Emerging

This project helps developers and researchers working with computer vision tasks like autonomous driving or medical image analysis. It takes raw images (e.g., from a car's camera or medical scans) and outputs a detailed, pixel-by-pixel map where each pixel is labeled with the type of object it represents (e.g., road, car, pedestrian, tumor). This is specifically for those building or evaluating image segmentation models.

611 stars. No commits in the last 6 months.

Use this if you are a computer vision engineer or researcher focused on developing and evaluating state-of-the-art semantic segmentation models for visual scene understanding.

Not ideal if you need an out-of-the-box application for general image editing or object detection without delving into the underlying model architecture and training.

semantic-segmentation autonomous-driving image-analysis computer-vision deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

611

Forks

112

Language

Python

License

Apache-2.0

Last pushed

Oct 26, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TuSimple/TuSimple-DUC"

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