Closed rodrigobdz closed 2 years ago
Hey Rodrigo, Max-Pooling is supported, as its gradient distributes the relevance in the correct way for LRP, ie. winner-takes-all.
Hi, Christopher, thanks for your prompt reply. I see, proceeding to close this issue then.
In the code there seems to be no mention of max-pooling layers, is LRP for this type of layers already (implicitly) supported?