Skip to content

1069066484/gcn_mnist

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

gcn_mnist

Use GCN to classify Mnist

The implementation refers to "Semi-supervised classification with graph convolutional networks" and "Hierarchical graph representation learning with differentiable pooling".

Each digit, a 28x28 matrix, is viewed as a 28-node graph. Each node is a 28d vector. We do this just to study GCN.

About

Use GCN to classify Mnist

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages