[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
if i want to use this model, just load your pretrained model to author's model and change output numbers ... is there other issues i should pay attention to.
if i want to use this model, just load your pretrained model to author's model and change output numbers ... is there other issues i should pay attention to.