minimaxir/imgbeddings

Python package to generate image embeddings with CLIP without PyTorch/TensorFlow

48
/ 100
Emerging

This tool helps data scientists and machine learning engineers analyze large collections of images. You input individual images or batches of image files, and it generates numerical representations (embeddings) for each. These embeddings can then be used for tasks like grouping similar images, finding specific images within a dataset, or preparing images for classification models.

161 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to transform images into numerical data for machine learning tasks like clustering, similarity search, or building image classifiers, especially when performance and efficiency are important.

Not ideal if your workflow requires linking image and text data directly within the embedding generation process, as this tool focuses solely on image-to-embedding conversion.

image-analysis machine-learning data-science image-search image-classification
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

161

Forks

15

Language

Python

License

MIT

Last pushed

Mar 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/minimaxir/imgbeddings"

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