yellowshippo/isogcn-iclr2021
IsoGCN code for ICLR2021
This project offers a specialized graph convolutional network (GCN) designed to analyze and predict properties on complex 3D shapes and meshes used in engineering. It takes in geometric data, such as finite element analysis results or mesh information, and outputs predictions like scalar fields, gradients, or Hessians, which are crucial for understanding material behavior or structural integrity. Structural engineers, computational physicists, or researchers working with advanced simulations would use this.
No commits in the last 6 months.
Use this if you need to perform machine learning tasks on complex geometries while preserving critical geometric transformation properties.
Not ideal if your data is not inherently graph-structured or if you primarily work with simpler, Euclidean grid-based data.
Stars
50
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 12, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yellowshippo/isogcn-iclr2021"
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.