How to preprocess custom image dataset for graph classification?

Hello, I am new to GNN and have only recently begun learning it.
I have many images in various directories and wanted to classify them using graph classification. However, I am unable to convert the dataset to work with graph classification(wanted to classify using GCN). Is there a way to convert an image dataset so that it can be used for graph classification?? If so, please provide the solution.

Thanks

GNNs may not be the best option for image classification. You might want to take a look at the setting related to superpixels in this paper.

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.