Captum
  • Docs
  • Tutorials
  • API Reference
  • GitHub

›General

About

  • Introduction

General

  • Getting Started
  • Captum Insights
  • Algorithm Descriptions
  • Algorithm Comparison Matrix
  • FAQ
  • The Captum Contribution Process

Usage

  • Integrated Gradients
Edit

Getting Started

This section shows you how to get up and running with Captum.

Installing Captum

Installation Requirements:

  • Python >= 3.6
  • PyTorch >= 1.2
  • numpy

Captum is easily installed via Anaconda (recommended) or pip:

conda
pip
conda install captum -c pytorch
pip install captum

For more detailed installation instructions, please see the Project Readme on GitHub.

Tutorials

We have several tutorials to help get you off the ground with Captum. The tutorials are Jupyter notebooks and cover the basics along with demonstrating usage of Captum with models of different modalities.

View the tutorials page here.

API Reference

For an in-depth reference of the various Captum internals, see our API Reference.

Contributing

You'd like to contribute to Captum? Great! Please see here for how to help out.

← IntroductionCaptum Insights →
  • Installing Captum
  • Tutorials
  • API Reference
  • Contributing
Docs
IntroductionGetting StartedTutorialsAPI Reference
Legal
PrivacyTerms
Social
captum
Facebook Open Source
Copyright © 2023 Facebook Inc.