Skip to content

adapt-python/adapt

Repository files navigation

ADAPT

PyPI version Build Status Python Version Codecov Status

Awesome Domain Adaptation Package Toolbox

ADAPT is a python library which provides several domain adaptation methods usefull to improve machine learning models.

Documentation Website

Find the details of all implemented methods as well as illustrative examples here: ADAPT Documentation Website

Installation

This package is available on Pypi and can be installed with the following command line:

pip install adaptation

The following dependencies are required and will be installed with the library:

  • numpy
  • scipy
  • tensorflow (>= 2.0)
  • scikit-learn
  • cvxopt

If for some reason, these packages failed to install, you can do it manually with:

pip install numpy scipy tensorflow scikit-learn cvxopt

Finally import the module in your python scripts with:

import adapt

Content

ADAPT package is divided in three sub-modules containing the following domain adaptation methods:

Feature-based methods

  • FE (Frustratingly Easy Domain Adaptation)
  • mSDA (marginalized Stacked Denoising Autoencoder)
  • DANN (Discriminative Adversarial Neural Network)
  • ADDA (Adversarial Discriminative Domain Adaptation)
  • CORAL (CORrelation ALignment)
  • DeepCORAL (Deep CORrelation ALignment)

Instance-based methods

Parameter-based methods

Examples

Examples for regression and classification DA on synthetic datasets are available here:

Classification Regression

Acknowledgement

Part of this work has been funded by the Industrial Data Analytics and Machine Learning chair from ENS Paris-Saclay, Borelli center.