Skip to main content

A library that helps to explain AI models in a really quick & easy way

Project description

Easy explain

Python Version Code style: black License

Explain AI models easily

Requirements

Python version

  • Main supported version : 3.9
  • Other supported versions : 3.7 & 3.8

To use the scripts on your computer, please make sure you have one of these versions installed.

Install environment & dependencies

In order to install the current repo you have 2 options:

  • Pip install it directly from git inside your prefered repo and use it as a package

Installation as a package

In order to use the current repo as a package you need to run the command below inside your project.

pip install easy-explain

Information about the functionality

easy-explain uses under the hood Captum. Captum aids to comprehend how the data properties impact the model predictions or neuron activations, offering insights on how the model performs. Captum comes together with Pytorch library.

Currently easy-explain is working only for images and only for Pytorch.

You can import the main function of the package 'run_easy_explain' directly as:

from easy_explain.easy_explain import run_easy_explain

For more information about how to begin have a look at the examples notebooks.

How to contribute?

We welcome any suggestions, problem reports, and contributions! For any changes you would like to make to this project, we invite you to submit an issue.

For more information, see CONTRIBUTING instructions.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

easy_explain-0.2.1.tar.gz (5.0 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page