rom1504/image_embeddings

Using efficientnet to provide embeddings for retrieval

46
/ 100
Emerging

This tool helps you organize and search through large collections of images by their visual content. You feed it a folder of images, and it processes them to create numerical descriptions (embeddings). You can then use these descriptions to find visually similar images, like clicking on one rose picture and instantly seeing other roses, even if they aren't tagged that way. It's ideal for anyone managing image libraries who needs to quickly retrieve similar visuals without manual tagging.

160 stars. No commits in the last 6 months.

Use this if you need to perform content-based image retrieval or find visually similar images within a dataset without relying on text tags.

Not ideal if your primary need is exact image matching based on metadata or if you require advanced image manipulation capabilities.

image-search visual-asset-management content-based-retrieval image-library-organization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

160

Forks

32

Language

Jupyter Notebook

License

MIT

Last pushed

May 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/rom1504/image_embeddings"

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