The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

metric-learning 开源项目推荐(434 个)
metric-learning 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 434 个仓库Torchreid: Deep learning person re-identification in PyTorch.
:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Accelerated deep learning R&D
🎯 Task-oriented embedding tuning for BERT, CLIP, etc.
Metric learning algorithms in Python
Python中的开源人员重新识别库
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
捍卫说话人识别的度量学习
TensorFlow Similarity是一个python包,专注于使相似性学习变得快速简单。
Metric learning and retrieval pipelines, models and zoo.
Blazing fast framework for fine-tuning similarity learning models
https://www.kaggle.com/c/humpback-whale-identification
PyTorch Implementation for Deep Metric Learning Pipelines
Paper List for Contrastive Learning for Natural Language Processing
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
😎 A curated list of awesome practical Metric Learning and its applications
Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)
This is the implementation of paper <Additive Margin Softmax for Face Verification>
A simple yet effective loss function for face verification.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/metric-learning。
- 该话题在 GitHub 上共有 434 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 3.3 万 Star,覆盖 3 种主要语言,数据更新于 2026-11-08。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。