adambielski/siamese-triplet

Siamese and triplet networks with online pair/triplet mining in PyTorch

51
/ 100
Established

This project helps you compare images by learning a compact representation that captures their similarity. You provide a collection of images, often with labels, and it produces a numerical "embedding" for each image. These embeddings can then be used to find similar images, group them, or act as features for other classification tasks. It's designed for machine learning practitioners, researchers, or data scientists working with image similarity tasks.

3,171 stars. No commits in the last 6 months.

Use this if you need to transform images into a standardized numerical format where the distance between numbers directly reflects how similar the original images are.

Not ideal if you are looking for a pre-trained, off-the-shelf solution for a very specific image similarity problem without needing to customize or train a model.

image-similarity feature-learning computer-vision image-retrieval few-shot-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

3,171

Forks

634

Language

Python

License

BSD-3-Clause

Last pushed

Apr 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adambielski/siamese-triplet"

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