jonkahana/CLIPPR

An official PyTorch implementation for CLIPPR

19
/ 100
Experimental

This helps data scientists or researchers analyze large image datasets to categorize items or assign numerical values (like age or object type) even when manual labels are scarce or nonexistent. You provide images and some general knowledge about how labels are distributed, and it outputs improved classifications or predictions without needing individually labeled images. This is for professionals who work with computer vision and need to extract insights from vast, unlabeled visual data.

No commits in the last 6 months.

Use this if you need to classify or predict attributes from large image collections, and you have some general statistical knowledge about how those attributes are distributed, but lack specific, manually labeled examples for every image.

Not ideal if you already have extensive, high-quality labeled datasets for your specific task, or if you cannot provide any information about the expected distribution of labels in your dataset.

computer-vision image-analysis unsupervised-learning predictive-modeling data-science
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

30

Forks

1

Language

Python

License

Last pushed

Jul 22, 2023

Commits (30d)

0

Get this data via API

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

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