There are 2 repositories under xai-library topic.
Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
Neural network visualization toolkit for tf.keras
Principal Image Sections Mapping. Convolutional Neural Network Visualisation and Explanation Framework
The NLP Bias Identification Toolkit
a tool for comparing the predictions of any text classifiers
TrustyAI Explainability Toolkit
:tv: A Python library for pruning and visualizing Keras Neural Networks' structure and weights
A library that helps to explain AI models in a really quick & easy way
Model-agnostic Statistical/Machine Learning explainability (currently Python) for tabular data
Artificial Neural Networks for Java This package provides Object oriented Neural Networks for making Explainable Networks. Object Oriented Network structure is helpful for observing each and every element the model. This package is developed for XAI research and development.
Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curve.
Xi method
ibreakdown is model agnostic predictions explainer with interactions support, library can show contribution of each feature of your prediction value
CLI for XAISuite Library
A scoring system for explainability
Block code for the XAISuite library: 11301858.github.io/xaisuiteweb
XAI approaches based on the TensorFlow framework to understand neural networks decision
This repository contains the code for the XAIInferencerEngine PyPi library.
This project uses XAI to make AI-based Alzheimer's predictions understandable for doctors, aiming to improve diagnosis & treatment for patients