Tutorials: Notebooks 📔¶

We propose here several tutorials to discover the different functionalities that the library has to offer.

We decided to host those tutorials on Google Colab mainly because you will be able to play the notebooks with a GPU which should greatly improve your User eXperience.

Here is the lists of the availables tutorial for now:

Getting Started¶

Tutorial Name	Notebook
Getting Started
Sanity checks for Saliency Maps
Times Series and Regression
Tabular data and Regression
Object detection
Semantic Segmentation
Metrics
Concept Activation Vectors
Feature Visualization
Example-Based Methods
Prototypes

Attributions¶

Category	Tutorial Name	Notebook
BlackBox	KernelShap
BlackBox	Lime
BlackBox	Occlusion
BlackBox	Rise

WhiteBox	DeconvNet
WhiteBox	GradCAM
WhiteBox	GradCAM++
WhiteBox	GradientInput
WhiteBox	GuidedBackpropagation
WhiteBox	IntegratedGradients
WhiteBox	Saliency
WhiteBox	SmoothGrad
WhiteBox	SquareGrad
WhiteBox	VarGrad

Tabular Data	Regression Tabular Data
Times Series	Regression Time Series

Metrics¶

Category	Tutorial Name	Notebook
Fidelity	MuFidelity
Fidelity	Insertion
Fidelity	Deletion
Stability	AverageStability	(WIP)

PyTorch Wrapper¶

Tutorial Name	Notebook
PyTorch models: Getting started
Metrics: With PyTorch models
Object detection on PyTorch model
Semantic Segmentation on PyTorch model

Concepts extraction¶

Category	Tutorial Name	Notebook
Labelled concept methods	CAV + TCAV

Automatic concept extraction	CRAFT Tensorflow
Automatic concept extraction	CRAFT Pytorch

Feature Visualization¶

Tutorial Name	Notebook
Feature Visualization: Getting started
Modern Feature Visualization: MaCo

Example-Based Methods¶

Tutorial Name	Notebook
Example-Based Methods: Getting started
Example-based: Prototypes