In Keras (tensorflow backend) I can weight the classes via a parameter, and there is another parameter that allows the weighting of the samples (as it was referenced in this question.)
In my case, I need to do both simultaneously: each sample should have an individual weight for each of the two classes that I have. My problem is that I don't just have one weight per sample for both classes, but the two classes need individual weights for each sample.
How can I achieve this?