Skip to content

Two Implements of Simple GNN (Basic Pytorch Version and PyG Version) 图卷积网络/图神经网络的简单实现

Notifications You must be signed in to change notification settings

TenshGU/GNN-Demo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Environment:

The dependencies involved have been written down in requirements.txt

run as follows:

pip install -r requirements.txt

DataBase:

  • cora
    • cora.cites
    • cora.content

Implements:

0 Data Loader

The .py files in data_loader package are as follows:

  • loader.py : loading cora dataset, extracting node features and edge information, and calculating D-1/2 A D-1/2...

1 Basic Pytorch Version:

The .py files in basic_version package are as follows:

  • layer.py : Defined Graph Convolution Layer (GraphConv)
  • model.py : Defined GCN Model which composed by GraphConv
  • evaluator.py : Used to evaluate our model

2 PyG Version

The .py files in pyg_version package are as follows:

  • model.py : Defined GCN Model composed by GCNConv which provided by torch_geometric
  • evaluator.py : Used to evaluate our model

Result:

  • PyG Version:
    • image

About

Two Implements of Simple GNN (Basic Pytorch Version and PyG Version) 图卷积网络/图神经网络的简单实现

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages