Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Metric learning and retrieval pipelines, models and zoo.
| Date | Stars |
|---|---|
| 2026-07-24 | 995 |
| 2026-07-25 | 995 |
| 2026-07-28 | 995 |
| 2026-07-30 | 995 |
| 2026-08-06 | 995 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="https://i.ibb.co/wsmD5r4/photo-2022-06-06-17-40-52.jpg" width="400px"> [](https://open-metric-learning.readthedocs.io/en/latest/?badge=latest) [](https://pepy.tech/project/open-metric-learning) [](https://pypi.org/project/open-metric-learning/) [](https://github.com/OML-Team/open-metric-learning/actions/workflows/tests.yaml/badge.svg?) [](https://github.com/OML-Team/open-metric-learning/actions/workflows/tests.yaml/badge.svg?) [](https://github.com/OML-Team/open-metric-learning/actions/workflows/tests.yaml/badge.svg?) OML is a PyTorch-based framework to train and validate the models producing high-quality embeddings. ### Trusted by <div align="center"> <a href="https://docs.neptune.ai/integrations/community_developed/" target="_blank"><img src="https://i.ibb.co/bMDShKDx/neptune-logo-less-margin-e1611939742683.png" width="100"/></a>ㅤㅤ <a href="https://www.newyorker.de/" target="_blank"><img src="https://upload.wikimedia.org/wikipedia/commons/thumb/d/d8/New_Yorker.svg/1280px-New_Yorker.svg.png" width="100"/></a>ㅤㅤ <a href="https://www.epoch8.co/" target="_blank"><img src="https://i.ibb.co/GdNVTyt/Screenshot-2023-07-04-at-11-19-24.png" width="100"/></a>ㅤㅤ <a href="https://www.meituan.com" target="_blank"><img src="https://upload.wikimedia.org/wikipedia/commons/6/61/Meituan_English_Logo.png" width="100"/></a>ㅤㅤ <a href="https://constructor.io/" target="_blank"><img src="https://rethink.industries/wp-content/uploads/2022/04/constructor.io-logo.png" width="100"/></a>ㅤㅤ <a href="https://edgify.ai/" target="_blank"><img src="https://edgify.ai/wp-content/uploads/2024/04/new-edgify-logo.svg" width="100" height="30"/></a>ㅤㅤ <a href="https://inspector-cloud.ru/" target="_blank"><img src="https://thumb.tildacdn.com/tild6533-6433-4137-a266-613963373637/-/resize/540x/-/format/webp/photo.png" width="150" height="30"/></a>ㅤㅤ <a href="https://yango-tech.com/" target="_blank"><img src="https://yango-backend.sborkademo.com/media/pages/home/205f66f309-1717169752/opengr4-1200x630-crop-q85.jpg" width="100" height="30"/></a>ㅤㅤ <a href="https://www.adagrad.ai/" target="_blank"><img src="https://cdn.prod.website-files.com/619cafd224a31d1835ece5bd/66b5e8e2818e2231e4734805_Frame%201.2.png" width="100" height="30"/></a> <a href="https://www.ox.ac.uk/" target="_blank"><img src="https://i.ibb.co/zhWL6tD/21-05-2019-16-08-10-6922268.png" width="120"/></a>ㅤㅤ <a href="https://www.hse.ru/en/" target="_blank"><img src="https://www.hse.ru/data/2020/11/16/1367274044/HSE_University_blue.jpg.(230x86x123).jpg" width="100"/></a> There is a number of people from [Oxford](https://www.ox.ac.uk/) and [HSE](https://www.hse.ru/en/) universities who have used OML in their theses. [[1]](https://github.com/nilomr/open-metric-learning/tree/great-tit/great-tit-train) [[2]](https://github.com/nastygorodi/PROJECT-Deep_Metric_Learning) [[3]](https://github.com/nik-fedorov/term_paper_metric_learning) <div align="left"> ## [Documentation](https://open-metric-learning.readthedocs.io/en/latest/index.html) <details> <summary>FAQ</summary> <details> <summary>Why do I need OML?</summary> <p> You may think *"If I need image embeddings I can simply train a vanilla classifier and take its penultimate layer"*. Well, it makes sense as a starting point. But there are several possible drawbacks: * If you want to use embeddings to perform searching you need to calculate some distance among them (for example, cosine or L2). Usually, **you don't directly optimize these distances during the training** in the classification setu
Excerpt of 43,802 characters
Read on GitHub
Aleksei Shabanov · Edgify · Thailand
335
23
18
10
6
5
5
4
3
Julia Shenshina
3
Guocheng
2
Andrei Yasyrev · Self-emloyed
2
2
2
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e0cd0ed20c3cd214, topic:deep-learning, topic:pytorch
matched fp:e0cd0ed20c3cd214, topic:computer-vision
matched fp:e0cd0ed20c3cd214, topic:representation-learning