lightaime/deep_gcns_torch

Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org

47
/ 100
Emerging

This project provides advanced methods for training very deep Graph Convolutional Networks (GCNs). It takes structured data, such as point clouds or social networks, and processes it to classify objects, segment scenes, or predict properties within the graph. Researchers and practitioners working with complex relational data who need to analyze intricate patterns would use this.

1,187 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or data scientist developing deep learning models for graph-structured data and need to overcome the limitations of shallow GCNs.

Not ideal if you are looking for a plug-and-play solution for common machine learning tasks without needing to delve into graph neural network architecture design.

graph-analysis point-cloud-segmentation node-classification 3d-object-recognition graph-property-prediction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,187

Forks

154

Language

Python

License

MIT

Last pushed

Jul 31, 2022

Commits (30d)

0

Get this data via API

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

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