corenel/pytorch-adda

A PyTorch implementation for Adversarial Discriminative Domain Adaptation

51
/ 100
Established

This project helps machine learning engineers or researchers adapt a trained model from one dataset to a similar but different dataset without extensive retraining. It takes an image classification model trained on a 'source' set of images (like MNIST handwritten digits) and adapts it to perform well on a 'target' set (like USPS handwritten digits), even if the target data looks slightly different. This is useful for researchers and ML engineers working with computer vision tasks.

493 stars. No commits in the last 6 months.

Use this if you have an image classification model that performs well on your existing training data, but struggles with similar images from a new source or domain, and you want to improve its performance on the new data without fully retraining from scratch.

Not ideal if you are looking for a general-purpose machine learning library or if your task involves domains completely unrelated to image classification.

domain-adaptation image-classification transfer-learning computer-vision neural-networks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

493

Forks

141

Language

Python

License

MIT

Last pushed

Apr 12, 2022

Commits (30d)

0

Get this data via API

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

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