ShotaDeguchi/PINN_Torch

Implementation of PINNs in PyTorch

28
/ 100
Experimental

This tool helps computational scientists and engineers find solutions to complex physics problems described by differential equations, like fluid dynamics or heat transfer. You input the governing equations and boundary conditions, and it outputs a highly accurate solution for the system's behavior. It's designed for researchers and practitioners in fields requiring numerical solutions to PDEs without extensive traditional numerical solver expertise.

No commits in the last 6 months.

Use this if you need to solve partial differential equations (PDEs) by embedding physical laws directly into a neural network, especially for problems where traditional numerical methods are complex or data is scarce.

Not ideal if you are looking for a general-purpose machine learning framework for image recognition or natural language processing, or if you prefer established finite element/difference methods.

computational-physics fluid-dynamics numerical-analysis differential-equations scientific-machine-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

MIT

Last pushed

Apr 09, 2023

Commits (30d)

0

Get this data via API

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

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