facebookresearch/theseus

A library for differentiable nonlinear optimization

45
/ 100
Emerging

This library helps robotics and computer vision researchers develop advanced models by integrating complex optimization problems directly into their neural networks. You can input data like sensor readings or image pixels, define your optimization goals, and get optimized parameters or refined model predictions out. It's designed for researchers building sophisticated machine learning systems where traditional optimization needs to be part of the learning process.

2,008 stars. No commits in the last 6 months.

Use this if you are a researcher or advanced practitioner who needs to embed sophisticated, differentiable nonlinear optimization routines, like those found in robotics or computer vision algorithms, directly into PyTorch-based neural networks.

Not ideal if you are looking for a simple, off-the-shelf machine learning model or a general-purpose optimization library without the need for deep integration into neural network architectures.

robotics computer-vision machine-learning-research optimization-algorithms end-to-end-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,008

Forks

143

Language

Python

License

MIT

Last pushed

Jan 16, 2025

Commits (30d)

0

Get this data via API

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

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