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

Code

• github.com/KaiyangZhou/deep-person-reid
  OfficialIn paperpytorch★ 4,786
• github.com/openvinotoolkit/deep-object-reid
  pytorch★ 57
• github.com/jacobtyo/mudd
  pytorch★ 4
• github.com/hukefei/deep-person-reid-master
  pytorch★ 0
• github.com/goksenin-uav/torchreid-pip
  pytorch★ 0
• github.com/tomektarabasz/deep_person_reid
  pytorch★ 0
• github.com/LeDuySon/torchreid_uet_lab
  pytorch★ 0
• github.com/MatthewAbugeja/osnet
  pytorch★ 0
• github.com/aslialp/HATCNN
  pytorch★ 0

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.

Tasks

Reproductions