arnab39/equiadapt

Library to make any existing neural network architecture equivariant

33
/ 100
Emerging

This tool helps machine learning engineers and researchers adapt existing neural network models to better handle transformed data, such as rotated images or shifted point clouds. It takes your pre-trained model and inputs (like images or 3D point cloud data) and outputs predictions that are consistent regardless of how the input data is oriented or positioned, without requiring you to retrain your original model from scratch. This is ideal for those working with computer vision, robotics, or scientific modeling where data symmetries are crucial.

No commits in the last 6 months.

Use this if you need your existing neural networks, especially large pre-trained models, to produce consistent results even when input data is rotated, translated, or otherwise transformed.

Not ideal if you are building a neural network from the ground up and prefer to design equivariance directly into the architecture rather than adapting an existing one.

computer-vision robotics scientific-modeling image-segmentation 3d-point-cloud-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

58

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/arnab39/equiadapt"

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