[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Outstanding Work!! I'm thinking to implement LRP for mean & sum function. How would you suggest implementing it? I'm thinking to use Linear layer if I know the dimensions beforehand. Is there any better way to do it? Do you suggest variants for sum & mean over elements of same tensor and sum and mean of 2 tensors?
Hi Hila,
Outstanding Work!! I'm thinking to implement LRP for
mean&sumfunction. How would you suggest implementing it? I'm thinking to useLinearlayer if I know the dimensions beforehand. Is there any better way to do it? Do you suggest variants forsum&meanover elements of same tensor andsumandmeanof 2 tensors?