Christiaan Meijer
Christiaan Meijer
The example notebook for rise for time is missing a multivariate example.
It is getting a bit convoluted what the input types of specific functions are. We now have options: numpy array, xarray, string, list of strings. I think it would help...
LimeSegment assume convenient input including tests See #369 and #366 for background.
might be fixed automatically after fixing #435
  It should have given the valid options as well (RISE, LIME, kernelSHAP).
Currently we are masking images with zeros which is not always sensible. The behavior will be very different for a bright image as opposed to a dark image I would...
Rise outputs a numpy array with dimensions n_labels, height, width, while Lime outputs a list of numpy arrays with dimensions height, width. It should both output the same data structure.
It only seems to work with model objects which is inconsistent with how the other methods work. We always want to support model functions and model objects. We should think...
Output of rise can be added repeatedly so you don't have to know the final n_masks in advance. We can keep adding masks until the output doesn't change much anymore....
Create text visualization: ordered table with weights