I am Asad, a recent graduate from Bahria University Islamabad.

I have a request for you all. I have been stuck on my Image Classification project using Graph Transformers for the past two weeks. I came across a paper titled “A Graph-Transformer for Whole Slide Image Classification” on the internet. I want to apply this approach to regular images (specifically the DermaMNIST dataset).

I have made some progress, but I am now stuck on how to convert my DermaMNIST dataset into a format suitable as input for the Graph Transformer (i.e., edge, node, and adjacency matrix or graph features compatible with the Graph Transformer).

Please help me with this task. If anyone is experienced in this field, we can also arrange a Zoom class.

Thank you for your consideration.