zhyhan/TransPar

Learning Transferable Parameters for Unsupervised Domain Adaptation

19
/ 100
Experimental

When you have a trained machine learning model for tasks like image classification or keypoint detection, but want to use it on new data that looks slightly different from your original training data, this library helps your model adapt. It takes your existing model and new, unlabeled data, and outputs an updated model that performs better on the new data without needing to manually label it. This is useful for machine learning engineers or researchers working with computer vision models across varying datasets.

No commits in the last 6 months.

Use this if you need to improve the performance of a pre-trained image classification or object detection model on a target dataset that differs significantly from your source training data, without needing to manually label the new data.

Not ideal if you are looking for a general-purpose machine learning library for tasks outside of unsupervised domain adaptation for classification and keypoint detection, or if you prefer a graphical user interface.

computer-vision image-classification object-detection model-adaptation machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Python

License

Last pushed

Aug 11, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zhyhan/TransPar"

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