About ABMIL

[InfinityBox]

I have read ABMIL's code (https://github.com/AMLab-Amsterdam/AttentionDeepMIL), the input size of its model is: (1, bag_length, 1, width, height), due to the images of the dataset being very small, memory problems may not occur. But when using WSI, bag_length, width and height are very big, so how to apply ABMIL to WSIs for the comparison?

[binli123]

You need only to swap in the ABMIL aggregation head which takes precomputed feature vectors as inputs.

[InfinityBox]

Thank you for your reply.
Are these two lines of code the aggregation head which I need to swap? Then replace with an input layer suitable for precomputed feature vectors?
https://github.com/AMLab-Amsterdam/AttentionDeepMIL/blob/master/model.py#L41

        H = self.feature_extractor_part1(x)
        H = H.view(-1, 50 * 4 * 4)