christiansafka/img2vec

:fire: Use pre-trained models in PyTorch to extract vector embeddings for any image

50
/ 100
Established

This tool helps you analyze images by converting them into numerical descriptions, called vector embeddings. You input an image or a collection of images, and it outputs a list of numbers that capture the image's key visual characteristics. This is ideal for data scientists, machine learning engineers, or researchers working with image datasets who need to quantify visual information.

622 stars. No commits in the last 6 months.

Use this if you need to transform images into numerical data for tasks like grouping similar images, building recommendation engines, or training classification models.

Not ideal if you need a user-friendly application with a graphical interface, as this requires coding knowledge to operate.

image-analysis computer-vision machine-learning data-science image-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

622

Forks

98

Language

Python

License

MIT

Last pushed

May 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/christiansafka/img2vec"

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