Installation Instructions

Installing the Package

The package releases are uploaded to PyPi, therefore allowing you to install it with pip:

$ pip install fat-forensics

If you want to install the latest (development) version of the package please see the instructions provided in the Developer Guide. Among others, it explains how to install the package from source.

Package Requirements

Hard Dependencies

The package is built upon NumPy and SciPy with the following minimal requirements:

Package	Version
NumPy	1.10.0
SciPy	0.13.3

These requirements are listed in the requirements.txt file in our GitHub repository.

Soft Dependencies

Some parts (modules) of FAT Forensics depend on other packages. These are not installed by default. The following table shows soft dependencies of fatf modules:

fatf module	Required package
fatf.transparency.predictions.surrogate_explainers	scikit-learn>=0.19.2
fatf.transparency.predictions.surrogate_image_explainers
fatf.transparency.sklearn
fatf.utils.data.feature_selection.sklearn
fatf.transparency.predictions.surrogate_image_explainers	scikit-image>=0.17.0
fatf.utils.data.occlusion
fatf.utils.data.segmentation
fatf.transparency.predictions.surrogate_image_explainers	Pillow>=8.4.0
fatf.utils.data.occlusion
fatf.utils.data.segmentation
fatf.vis	matplotlib>=3.0.0

These dependencies can either be installed manually or alongside fat-forensics via pip:

$ pip install fat-forensics[xxx]

where xxx can be replaced with any of the following to pull appropriate soft dependencies during the package installation:

all

Installs all soft dependencies: scikit-learn and matplotlib.

ml

Only installs scikit-learn as a soft dependency.

vis

Only installs matplotlib as a soft dependency.

dev

This option installs all the development requirements. Please consult the Developer Guide for more details.

The exact versions of these soft dependencies can be found in the requirements-aux.txt file.

Supported Platforms

At the moments we only test the package on Linux-based systems. From our experience the package also works on Mac OS and Windows, however these platforms are not officially supported.

---

Recommended Reading Order

We recommend going through the documentation in the following order:

• the description and some background,

• the tutorials, which will walk you through the basic concepts and tasks that can be solved with FAT Forensics step-by-step,

• the examples, which show a minimal code example for using every major functionality implemented by the package,

• the user guide, which describe the algorithms implemented by the package on a more conceptual level with their pros, cons, suggested applications, known shortcomings, best practices and alternative implementations,

• the how to guides, which show how to solve a particular problem with the package and, finally,

• the API reference, which should serve as a point of reference for every function and object within the package.

Developers and contributors may be interesting in the following pages as well:

• the Developers Guide and

• the package development Roadmap.