gram-ai/capsule-networks

A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules".

42
/ 100
Emerging

This project offers a PyTorch implementation of Capsule Networks, a neural network architecture particularly effective for image recognition. It takes an image as input and outputs a classification of the objects or parts within it, even when they overlap. This would be used by a machine learning engineer or researcher experimenting with advanced image classification models beyond standard convolutional neural networks.

1,753 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer interested in exploring Capsule Networks for robust image recognition, especially for scenarios involving overlapping objects, and prefer working with PyTorch.

Not ideal if you are a beginner looking for a simple, off-the-shelf image classification solution, as this requires some understanding of deep learning frameworks and model training.

image-classification deep-learning-research neural-networks computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 24 / 25

How are scores calculated?

Stars

1,753

Forks

313

Language

Python

License

Last pushed

Nov 09, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gram-ai/capsule-networks"

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