Sealbook / Open source / Machine learning & data science

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.

attention-matrixattention-visualizationbertbert-modelcvpr2021deep-learningexplainabilityperturbationtransformer-interpretabilityvision-transformer

GitHub ↗

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 2 years ago.

Similar projects

	Repository	Stars	Language	License	Activity
1	shap/shapA game theoretic approach to explain the output of any machine learning model.	★ 25.8k	Jupyter Notebook	MIT	Active
2	amusi/CVPR2026-Papers-with-CodeCVPR 2026 论文和开源项目合集	★ 22.9k	—	—	Slowing
3	extreme-assistant/CVPR2024-Paper-Code-Interpretationcvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理	★ 12.5k	—	—	Stale
4	NielsRogge/Transformers-TutorialsThis repository contains demos I made with the Transformers library by HuggingFace.	★ 11.8k	Jupyter Notebook	MIT	Active
5	tensorflow/tensorflowAn Open Source Machine Learning Framework for Everyone	★ 201.1k	C++	Apache-2.0	Active
6	AUTOMATIC1111/stable-diffusion-webuiStable Diffusion web UI	★ 165.1k	Python	AGPL-3.0	Slowing
7	pytorch/pytorchTensors and Dynamic neural networks in Python with strong GPU acceleration	★ 104.8k	Python	Other	Active
8	opencv/opencvOpen Source Computer Vision Library	★ 91.2k	C++	Apache-2.0	Active