gram-ai/capsule-networks

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

42
/ 100
Emerging

Implements the iterative routing-by-agreement mechanism where lower-level capsules route outputs to higher-level capsules based on prediction agreement, enabling the network to learn instantiation parameters (pose, scale, rotation) rather than just class probabilities. Integrates with TorchNet for training, TorchVision for MNIST preprocessing, and Visdom for real-time visualization, achieving 99.7% accuracy on MNIST with configurable routing iterations and batch sizes.

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

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.