explainability

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

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

UpdatedJan 24, 2024
Jupyter Notebook

microsoft /responsible-ai-toolbox

Star1.7k

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.

visualization data-science machine-learning widget ui jupyter widgets ml data-visualization data-analysis machinelearning fairness interpretability error-analysis explainable-ai explainable-ml fairness-ai explainability fairness-ml responsible-ai

UpdatedFeb 7, 2025
TypeScript

EthicalML /xai

Star1.2k

XAI - An eXplainability toolbox for machine learning

machine-learning ai evaluation ml artificial-intelligence upsampling bias interpretability feature-importance explainable-ai explainable-ml xai imbalance downsampling explainability bias-evaluation machine-learning-explainability xai-library

UpdatedNov 29, 2025
Python

CodeBoarding /CodeBoarding

Star913

🪄 Interactive Diagrams for Code

golang typescript static-analysis language-server-protocol python3 agents hacktoberfest typescipt lsp codedocs codedocumentator explainability language-server-client lsp-client llms aiagentic hacktoberfest-2025

UpdatedNov 24, 2025
Python

hila-chefer /Transformer-MM-Explainability

Star878

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

visualization transformers transformer vqa clip interpretability explainable-ai explainability detr lxmert visualbert

UpdatedAug 24, 2023
Jupyter Notebook

h1st-ai /h1st

Star794

Power Tools for AI Engineers With Deadlines

home-automation data-science time-series collaboration cybersecurity cold-start autonomous-vehicles hacktoberfest automl avionics human-in-the-loop predictive-maintenance ensemble-machine-learning datascience-environment explainability industrial-iot trustworthy-datascience energy-optimization

UpdatedJul 31, 2023
Jupyter Notebook

flyingdoog /awesome-graph-explainability-papers

Star773

Papers about explainability of GNNs

machine-learning deep-learning graph-mining explainable-ai xai graph-neural-networks explainability

UpdatedOct 27, 2025

MisaOgura /flashtorch

Star744

Visualization toolkit for neural networks in PyTorch! Demo -->

visualization machine-learning deep-learning cnn pytorch neural-networks interpretability explainability

UpdatedSep 21, 2023
HTML

mmschlk /shapiq

Star641

Shapley Interactions and Shapley Values for Machine Learning

python machine-learning game-theory interpretability feature-importance explainable-ai banzhaf-index shapley interpretable-machine-learning shap explainability feature-attribution feature-interactions shapley-interactions shapiq

UpdatedNov 26, 2025
Python

alvinwan /neural-backed-decision-trees

Star624

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

pytorch neural-networks imagenet image-classification pretrained-models decision-trees cifar10 interpretability pretrained-weights cifar100 tiny-imagenet explainability neural-backed-decision-trees

UpdatedMay 1, 2023
Python

xmed-lab /CLIP_Surgery

Star449

[Pattern Recognition 25] CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks

sam segmentation clip interpretability multilabel multimodal explainability vision-transformer open-vocabulary segment-anything

UpdatedMar 1, 2025
Jupyter Notebook

explainX /explainx

Star442

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms8909@nyu.edu

machine-learning scikit-learn transparency blackbox bias interpretability explainable-artificial-intelligence interpretable-ai explainable-ai explainable-ml xai interpretable-machine-learning machine-learning-interpretability explainability aws-sagemaker explainx

UpdatedAug 21, 2024
Jupyter Notebook

haofanwang /Score-CAM

Star431

Official implementation of Score-CAM in PyTorch

heatmap grad-cam pytorch cam saliency class-activation-maps cnn-visualization-technique gradcam gradient-free cnn-visualization visual-explanations explainability score-cam scorecam

UpdatedAug 6, 2022
Python

keisen /tf-keras-vis

Star336

Neural network visualization toolkit for tf.keras

visualization python deep-learning tensorflow keras grad-cam keras-visualization saliency explainable-ai explainable-ml xai gradcam gradcam-plus-plus keras-vis explainability xai-library saliency-maps activation-maximization score-cam

UpdatedMar 12, 2025
Python

hbaniecki /adversarial-explainable-ai

Star330

💡 Adversarial attacks on explanations and how to defend them

security model evaluation deep adversarial defense attacks interpretability robustness adversarial-machine-learning adversarial-examples counterfactual adversarial-attacks explainable-ai xai interpretable interpretable-machine-learning iml explainability responsible-ai

UpdatedNov 30, 2024

wisent-ai /wisent

Star324

This is an open-source version of the representation engineering framework for stopping harmful outputs or hallucinations on the level of activations. 100% free, self-hosted and open-source.

security ai safeguards explainability llms

UpdatedNov 29, 2025
Python

Improve this page

Add a description, image, and links to theexplainability topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with theexplainability topic, visit your repo's landing page and select "manage topics."

Learn more

Movatterモバイル変換

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

Saved searches

Use saved searches to filter your results more quickly