deel-ai/xplique

👋 Xplique is a Neural Networks Explainability Toolbox

What it solves

Xplique is a Python toolkit designed to make complex neural network models explainable. It provides a centralized library of state-of-the-art Explainable AI (XAI) methods to help developers and researchers understand how their models make decisions, moving away from "black box" AI.

How it works

The library is organized into several specialized modules:

  • Attribution Methods: Implements techniques like Grad-CAM, Saliency, and Integrated Gradients to identify which parts of the input (images, tabular data, or time series) most influenced the model's output.
  • Feature Visualization: Finds specific inputs that maximize the activation of neurons, channels, or layers to visualize what the network has "learned" to recognize.
  • Concepts: Extracts human-understandable concepts from a model (using methods like CAV and CRAFT) to test their relevance to specific classes.
  • Metrics: Provides tools to evaluate the faithfulness and quality of the explanations generated by the attribution methods.
  • Example-based: Explains model behavior by retrieving similar, contrastive (counter-factual), or prototype examples from a dataset.

Who it’s for

It is primarily for AI practitioners and researchers using TensorFlow (optimally version 2.15 or earlier) or PyTorch (via a wrapper) who need to audit, debug, or explain the internal logic of their neural networks.

Highlights

  • Broad Task Support: Works across classification, regression, object detection, and semantic segmentation.
  • Multi-modal Data: Supports images, time series, and tabular data.
  • Framework Flexibility: Built for TensorFlow but includes a TorchWrapper for PyTorch model integration.
  • Comprehensive XAI Suite: Combines attribution, visualization, concept extraction, and quantitative metrics in one toolkit.

Related

  • Project
    jacobgil/pytorch-grad-cam

    A PyTorch library for explainable AI in computer vision that provides a wide range of pixel attribution methods to visualize and diagnose model predictions.

  • Project
    Trusted-AI/AIX360

    An open-source library providing a comprehensive set of algorithms and metrics to improve the interpretability and explainability of machine learning models and datasets across various data modalities.

  • Project
    MAIF/shapash

    A Python library that makes machine learning models interpretable for everyone by providing user-friendly visualizations, an interactive web app, and audit reports.

  • Project
    understandable-machine-intelligence-lab/Quantus

    Quantus is an open‑source Python library (PyTorch/TensorFlow) that provides 35+ quantitative metrics for evaluating neural‑network explanation methods across six categories (faithfulness, robustness, localisation, complexity, randomisation, axiomatic). It enables reproducible, batch‑efficient assessment of XAI techniques for image, time‑series, and tabular data, with tutorials, docs, and community support.

  • Project
    shap/shap

    A game theoretic framework for explaining the outputs of any machine learning model by attributing credit to input features using Shapley values.