KevinMusgrave/pytorch-adapt

Domain adaptation made easy. Fully featured, modular, and customizable.

46
/ 100
Emerging

This tool helps machine learning engineers and researchers adapt existing models to perform well on new, related datasets without needing to retrain from scratch. You provide your pre-trained model and data from a new 'target' domain, and it outputs an adapted model ready for use. It's designed for practitioners who work with machine learning models and need to deploy them in varied environments or with evolving data.

394 stars. No commits in the last 6 months. Available on PyPI.

Use this if you have a machine learning model that works well on one type of data but performs poorly on a new, similar type of data, and you want to quickly improve its performance without extensive new labeling or model development.

Not ideal if you are a non-technical user looking for a no-code solution, or if your 'new' data is completely different from your original training data, requiring a fresh model build.

machine-learning model-deployment data-drift AI-research predictive-modeling
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 11 / 25

How are scores calculated?

Stars

394

Forks

19

Language

Python

License

MIT

Last pushed

Jan 30, 2023

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KevinMusgrave/pytorch-adapt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.