Open enryH opened 4 years ago
Hey, did you find any solution for composite LRP?
you can use the lrp.sequential_*
analyzers. see https://github.com/albermax/innvestigate/blob/c6ce89323d686a52d793177efd8d1dda3bd9526a/src/innvestigate/analyzer/__init__.py#L60
those are implemented by applying layer-conditional rule mapping.
Dear team,
if I would like to do composite LRP using iNNvestigate as described in the Figure 10.4 in your latest overview-paper:
I am thinking about how to do this in iNNvestigate. I guess I could split the network into different parts, and do respective analysis on each of them and pass the relevances backwards. Is there an easier way?
Thanks in advance!