Model Interpretability Python Packages

kserve

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

kfserving

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

irapy

Impact Range Assessment (IRA): An Interpretable Sensitivity Measure for Regression Modeling

streamlit-recommenders

Lightweight Python library for interactive demo and inspection of recommender systems in Streamlit.

mlxlmprobe

Universal probing and interpretability tool for MLX language models on Apple Silicon

ptame

Scripts and trained models from our paper: M. Ntrougkas, V. Mezaris, I. Patras, "P-TAME: Explain Any Image Classifier with Trained Perturbations", IEEE Open Journal of Signal Processing, 2025. DOI:10.1109/OJSP.2025.3568756.

aizenx-xai

AizenX is an open-source Explainable AI (XAI) framework for model interpretation, counterfactual analysis, bias detection, and visualization.

decision-boundary-plot

Universal visualization library for N-dimensional machine learning decision boundaries. Works with PyTorch, Keras, Sklearn, and any custom model or dimensionality reducer (PCA, UMAP, t-SNE, and more) to render interactive 2D/3D plots.

kserve-mathking

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes