saurabhdeshpande93/MAgNET
A novel graph U-net architecture
This project helps mechanical and civil engineers, or anyone working with finite element method (FEM) simulations, to quickly predict outcomes for non-linear solid mechanics problems. It takes your existing FEM simulation data and uses a specialized deep learning model to generate faster predictions than traditional simulation methods. This is ideal for researchers and practitioners who perform many mesh-based simulations.
No commits in the last 6 months.
Use this if you need to accelerate non-linear finite element simulations, especially for solid mechanics, and have existing simulation datasets you can leverage.
Not ideal if you are looking for a general-purpose graph neural network tool unrelated to mesh-based scientific simulations.
Stars
24
Forks
4
Language
Mathematica
License
MIT
Category
Last pushed
Apr 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/saurabhdeshpande93/MAgNET"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.