loretoparisi/CapsNet

CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art

50
/ 100
Established

This project offers a collection of implementations and resources for Capsule Networks (CapsNets), a type of neural network capable of recognizing objects more effectively than traditional Convolutional Neural Networks, especially in complex scenarios. It takes image data as input and outputs highly accurate object classifications, even when objects overlap. Data scientists and machine learning researchers exploring advanced computer vision techniques would use this project.

448 stars. No commits in the last 6 months.

Use this if you are a data scientist or researcher working on image recognition tasks and want to explore state-of-the-art models that handle variations in object pose and overlapping objects well.

Not ideal if you are looking for a simple, off-the-shelf image classification tool for basic, non-overlapping object detection.

image-classification object-recognition machine-learning-research computer-vision deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

448

Forks

107

Language

License

MIT

Last pushed

Nov 14, 2021

Commits (30d)

0

Get this data via API

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

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