naver/unic

PyTorch code and pretrained weights for the UNIC models.

27
/ 100
Experimental

UNIC helps machine learning practitioners create more efficient and powerful universal image classification models. By distilling knowledge from multiple high-performing 'teacher' models, it produces a single 'student' model that learns diverse visual patterns. This results in an image classification model that is smaller, faster, and more adaptable for various computer vision tasks.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher developing image classification systems and need a robust, general-purpose model that can perform well across many different vision tasks with reduced computational cost.

Not ideal if you are a non-technical end-user looking for a ready-to-use application, as this project requires significant technical expertise in machine learning model training and deployment.

image-classification computer-vision deep-learning model-optimization transfer-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

44

Forks

1

Language

Python

License

Last pushed

Aug 29, 2024

Commits (30d)

0

Get this data via API

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

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