Explainer

Explainer is a Python module in Intel® Explainable AI Tools that provides explainability methods for PyTorch and Tensorflow models.

Goals

Composable

Add explainers to models methods with minimal code

Extensible

Easy to add new methods

Community

Contributions welcome

Explainer Submodules

• attributions: visualize negative and positive attributions of tabular features, pixels, and word tokens for predictions

• cam: create heatmaps for CNN image classifications using gradient-weight class activation CAM mapping

• API Refrence: Gain insight into models with the measurements and visualizations needed during the machine learning workflow