PyTorch Adapt

TL;DR

PyTorch Adapt is a flexible, modular library that simplifies domain adaptation in machine learning, enabling easy customization and integration of complex training algorithms with minimal code.

Contribution

It introduces a highly customizable, modular toolkit for domain adaptation that allows easy creation and modification of training pipelines in PyTorch.

Findings

Supports complex training algorithm customization

Enables quick setup of domain adaptation pipelines

Provides a modular, framework-agnostic design

Abstract

PyTorch Adapt is a library for domain adaptation, a type of machine learning algorithm that re-purposes existing models to work in new domains. It is a fully-featured toolkit, allowing users to create a complete train/test pipeline in a few lines of code. It is also modular, so users can import just the parts they need, and not worry about being locked into a framework. One defining feature of this library is its customizability. In particular, complex training algorithms can be easily modified and combined, thanks to a system of composable, lazily-evaluated hooks. In this technical report, we explain in detail these features and the overall design of the library. Code is available at https://www.github.com/KevinMusgrave/pytorch-adapt