Lrp Python Packages

zennit

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

covidxai

Implementation of explainability algorithms (layer-wise relevance propagation, local interpretable model-agnostic explanations, gradient-weighted class activation mapping) on computer vision architectures to identify and explain regions of COVID 19 pneumonia in chest X-ray and CT scans.

zennit-crp

Concept Relevance Propagation and Relevance Maximization

lrp-pf-auc

Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curve.