jaggbow/magnet
This repository contains code for the paper "MAgNet: Mesh-Agnostic Neural PDE Solver" https://arxiv.org/abs/2210.05495
This project helps researchers and engineers quickly predict solutions to complex Partial Differential Equations (PDEs). You provide existing simulation data on various computational grids, and it outputs predictions for the PDE's behavior at any point within the problem domain, even on new, previously unseen grids or resolutions. This is for computational scientists, physicists, or engineers who work with simulations and need to generalize their models without retraining.
No commits in the last 6 months.
Use this if you need to predict the outcomes of physical or engineering simulations (governed by PDEs) on diverse computational grids without having to regenerate or retrain models for each new grid resolution or structure.
Not ideal if your problems are not described by Partial Differential Equations or if you always work with fixed, regular simulation grids.
Stars
38
Forks
4
Language
Python
License
—
Category
Last pushed
Jun 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jaggbow/magnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE