OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
This helps data scientists or machine learning engineers build powerful search and recommendation systems. It takes in collections of items (like images of products, documents, or user profiles) and transforms them into "embeddings" – numerical representations that capture their unique characteristics and relationships. The output allows you to efficiently find items that are highly similar to each other or to a query, making it ideal for tasks like visual search, content recommendations, or identifying duplicate entries.
985 stars. Available on PyPI.
Use this if you need to build robust retrieval systems where finding similar items based on their content or features is critical, and standard classification models don't provide the precision or search capabilities you need.
Not ideal if your primary goal is simple categorization or if you are not working with large datasets where efficient similarity search and model validation are crucial.
Stars
985
Forks
74
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 26, 2025
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OML-Team/open-metric-learning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
PaddlePaddle/models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models...
dasguptar/treelstm.pytorch
Tree LSTM implementation in PyTorch