hila-chefer/Transformer-Explainability

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

语言：Jupyter Notebook · GitHub 星标：2,021 · Fork：260

话题：attention-matrix · attention-visualization · bert · bert-model · cvpr2021 · deep-learning · explainability · perturbation

在 GitHub 上查看原仓库