(explainer)=
# Explainer

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

## Goals

````{grid} 3

```{grid-item-card}
:text-align: center
:class-header: sd-font-weight-bold
:class-body: sd-font-italic
{octicon}`workflow` Composable
^^^
Add explainers to models methods with minimal code
```

```{grid-item-card}
:text-align: center
:class-header: sd-font-weight-bold
:class-body: sd-font-italic
{octicon}`stack` Extensible
^^^
Easy to add new methods
```

```{grid-item-card}
:text-align: center
:class-header: sd-font-weight-bold
:class-body: sd-font-italic
{octicon}`package-dependencies` Community
^^^
Contributions welcome
```

````

## Explainer Submodules

* {ref}`attributions`: visualize negative and positive attributions of tabular features, pixels, and word tokens for predictions
* {ref}`cam`: create heatmaps for CNN image classifications using gradient-weight class activation CAM mapping
* {ref}`metrics`: Gain insight into models with the measurements and visualizations needed during the machine learning workflow