search

mdeff / cnn_graph

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
https://arxiv.org/abs/1606.09375
MIT License
1.34k stars 391 forks source link

Image Classification #48

Open sayands opened 5 years ago

sayands commented 5 years ago

I have an MNIST-like dataset for image classification using a Graph Convolutional Neural Network. Could you maybe suggest on how to make the adjacency matrix for such a dataset ?

It would be great. Please let me know.

sousoufa commented 4 years ago

I have the same problem. Can you help me

mdeff commented 4 years ago

The graph of an image is a 2D grid. You can generate a 10x10 grid (with adjacency and Laplacian matrices) with the PyGSP as graph = pygsp.graphs.Graph2d(10, 10) [doc].