cocoalex00/Mamba2D

Official PyTorch Implementation of Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks

25
/ 100
Experimental

Mamba2D helps computer vision engineers and researchers process images more efficiently and accurately for tasks like classifying objects, detecting their location, and segmenting different parts of an image. You feed it raw image data, and it outputs labels, bounding boxes, or pixel-level masks, often with greater speed and less computational demand than existing methods. This is ideal for those working on advanced image understanding applications.

Use this if you need to perform high-performance image classification, object detection, or semantic segmentation and are looking for models that offer superior speed and accuracy compared to other state-space models or even some transformer-based approaches.

Not ideal if you are looking for a general-purpose image processing library for basic tasks or are not familiar with deep learning frameworks like PyTorch and MMDetection/MMSegmentation.

computer-vision image-classification object-detection semantic-segmentation AI-research
No License No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

Last pushed

Nov 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cocoalex00/Mamba2D"

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