Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch

Kaiyang Zhou, Tao Xiang
10/22/2019
cs.CV

Official code: KaiyangZhou/deep-person-reid (4,930 stars, MIT, PyTorch, last commit 2026-01-09).

Abstract

Person re-identification (re-ID), which aims to re-identify people across different camera views, has been significantly advanced by deep learning in recent years, particularly with convolutional neural networks (CNNs). In this paper, we present Torchreid, a software library built on PyTorch that allows fast development and end-to-end training and evaluation of deep re-ID models. As a general-purpose framework for person re-ID research, Torchreid provides (1) unified data loaders that support 15 commonly used re-ID benchmark datasets covering both image and video domains, (2) streamlined pipelines for quick development and benchmarking of deep re-ID models, and (3) implementations of the latest re-ID CNN architectures along with their pre-trained models to facilitate reproducibility as well as future research. With a high-level modularity in its design, Torchreid offers a great flexibility to allow easy extension to new datasets, CNN models and loss functions.

View on arXivView PDF

Code Implementations(1)

KaiyangZhou/deep-person-reidOfficial100%
PyTorchMIT

Torchreid: Deep learning person re-identification in PyTorch.

4,9301,219C++, CudaMar 11, 20189 months agoMIT
computer-visioncross-domaindeep-learningdeep-neural-networksimage-retrieval+6 more

Similar Papers

Deep Learning for Person Re-identification: A Survey and Outlook

87% match1 repo7542020

CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Models

86% match1 repo92024

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

86% match1 repo2.4k2019

CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification

85% match2024

Semi-Supervised Domain Generalizable Person Re-Identification

85% match1 repo4.0k2021

Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification

85% match2024

Cite this paper

@article{zhou2019torchreid,
  title  = {Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch},
  author = {Kaiyang Zhou and Tao Xiang},
  year   = {2019},
  eprint = {1910.10093},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1910.10093}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1910.10093.svg)](https://codeofpaper.com/paper/1910.10093)

Discussion