lululxvi/deepxde

A library for scientific machine learning and physics-informed learning

71
/ 100
Verified

Implements physics-informed neural networks (PINNs), DeepONet operators, and multifidelity learning to solve forward/inverse differential equations and learn solution operators without explicit meshing. Supports five interchangeable tensor backends (TensorFlow, PyTorch, JAX, PaddlePaddle) and provides domain geometry handling through constructive solid geometry, multiple boundary condition types, and adaptive sampling strategies to improve accuracy.

3,954 stars. Used by 1 other package. Available on PyPI.

Maintenance 10 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

3,954

Forks

936

Language

Python

License

LGPL-2.1

Last pushed

Mar 01, 2026

Commits (30d)

0

Dependencies

5

Reverse dependents

1

Get this data via API

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

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