adapt-python/adapt
Awesome Domain Adaptation Python Toolbox
This toolbox helps data scientists and machine learning engineers build predictive models that perform well even when the data used for training is different from the data they will be used on. You feed it existing data from one domain (source) and new data from a related but different domain (target), and it outputs a refined machine learning model tailored for the target domain. This is useful for anyone applying machine learning models in evolving real-world scenarios.
366 stars. Available on PyPI.
Use this if your machine learning model's performance drops when deployed because the real-world data it encounters is subtly different from your training data, or if you want to adapt a pre-trained model to a new but related task.
Not ideal if your source and target datasets are entirely unrelated, or if you need a solution that doesn't involve Python programming and integration with Scikit-learn or TensorFlow.
Stars
366
Forks
54
Language
Python
License
BSD-2-Clause
Category
Last pushed
Dec 02, 2025
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adapt-python/adapt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
corenel/pytorch-adda
A PyTorch implementation for Adversarial Discriminative Domain Adaptation
jindongwang/transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers,...
thuml/Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
KaiyangZhou/Dassl.pytorch
A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.
google-deepmind/distribution_shift_framework
This repository contains the code of the distribution shift framework presented in A...