geometric-deep-learning
Here are 38 public repositories matching this topic...
Some algorithms supported in StellarGraph via demos aren't listed in documentation on readthedocs
Describe the bug
In StellarGraph, some algorithms are in demo notebooks or scripts, without being listed in our main documentation. This could mean that a user reading our docs thinks they're not supported in StellarGraph.
Convolutional Neural Network for 3D meshes in PyTorch
-
Updated
Mar 9, 2020 - Python
Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019 Oral & Best paper finalist)
-
Updated
Jan 17, 2020 - Python
import torch
from torch_cluster import graclus_cluster
row = torch.tensor([0, 1, 1, 2])
col = torch.tensor([1, 0, 2, 1])
weight = torch.Tensor([1, 1, 1, 1]) # Optional edge weights.
cluster = graclus_cluster(row, col, weight)
print(cluster)
tensor([0, 0, 1])
The result seems to be 'tensor([0, 0, 2])' in my mac
MaSIF- Molecular surface interaction fingerprints. Geometric deep learning to decipher patterns in molecular surfaces.
-
Updated
May 13, 2020 - Python
Geometric Deep Learning for Flux
-
Updated
May 20, 2020 - Julia
Geom-GCN: Geometric Graph Convolutional Networks
-
Updated
Feb 10, 2020 - Python
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (ICCV 2019)
-
Updated
Dec 16, 2019 - Python
Source code for CVPR 2018 Oral paper "Surface Networks"
-
Updated
Jan 29, 2020 - Python
Implementation of the Spline-Based Convolution Operator of SplineCNN in PyTorch
-
Updated
Apr 23, 2020 - C++
Implementation of Deep Graph Matching Consensus in PyTorch
-
Updated
Jan 17, 2020 - Python
Code for the paper 'An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem' (arXiv Pre-print)
-
Updated
Jan 28, 2020 - Python
PyTorch reimplementation for "KPConv: Flexible and Deformable Convolution for Point Clouds" https://arxiv.org/abs/1904.08889
-
Updated
Dec 23, 2019 - C++
code to train a neural network to align pairs of shapes without needing ground truth warps for supervision
-
Updated
Jul 21, 2019 - Cuda
This repo contains code to convert Structured Documents to Graphs and implement a Graph Convolution Neural Network for node classification
-
Updated
Mar 31, 2020 - Python
Code for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features
-
Updated
May 7, 2020 - Python
Code for the paper 'On Learning Paradigms for the Travelling Salesman Problem' (NeurIPS 2019 Graph Representation Learning Workshop)
-
Updated
Nov 9, 2019 - Python
A PyTorch Graph Neural Network Library
-
Updated
May 17, 2020 - Python
Protein Graph Library
-
Updated
May 23, 2020 - Jupyter Notebook
Fisher-Bures Adversary Graph Convolutional Networks
-
Updated
Aug 20, 2019 - Python
HADA (Hiearachical Adversarial Domain Alignment) for brain graph prediction and classification.
-
Updated
Nov 18, 2019 - Python
-
Updated
May 26, 2020 - Python
AIRI_pottery
-
Updated
Nov 30, 2018 - Jupyter Notebook
PyTorch implementation of "DeepSphere: a Graph-based Spherical CNN", Defferard et al., 2019.
-
Updated
Feb 10, 2020 - Python
-
Updated
Feb 29, 2020 - JavaScript
Repository for experiments with scattering transforms
-
Updated
Jan 25, 2019 - Jupyter Notebook
Simple task for mixed image-graph data
-
Updated
Jan 28, 2020 - Python
Learning-based partial point cloud completion system using kernel points convolution
-
Updated
Feb 15, 2020 - Python
-
Updated
Mar 11, 2019 - C++
Improve this page
Add a description, image, and links to the geometric-deep-learning topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the geometric-deep-learning topic, visit your repo's landing page and select "manage topics."


The documentation about edge orientation is inconsistent. In the Creating Message Passing Networks tutorial, the main expression says that e𝑖,𝑗 denotes (optional) edge features from node 𝑖 to node 𝑗., the attached expression also suggests it. However, in documentation to MessagePassing.message(), the documentation says Constructs messages from node 𝑗 to node 𝑖 (this is actually true).
I