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.

↗ Open on GitHub

Stars

2,014

Forks

261

Language

Jupyter Notebook

License

MIT

Last push

3 years ago

Jupyter Notebook deep-learning attention-visualization bert cvpr2021 vision-transformer vit explainability bert-model attention-matrix perturbation transformer-interpretability visualize-classifications

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.

Related intel (0)

No related intel yet