I have large high-res images (4000x4000px). And the ML problem at hand is image classification. 50 percent of important features present in the image are as small as 30x30px.
How to convert these images (grayscale or RGB) into graph format supported by spektral like in MNIST.
Will we have any advantages of features representation using GNNs because with CNN we usually resize the image causing loss in information.
I have large high-res images (4000x4000px). And the ML problem at hand is image classification. 50 percent of important features present in the image are as small as 30x30px.