Skip to content

A strong implementation of PCB (Beyond Part Models), outperforming all existing implementations.

Notifications You must be signed in to change notification settings

wangguanan/Pytorch-Person-ReID-Baseline-PCB-Beyond-Part-Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

58 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pytorch-Person-ReID-PCB-Beyond-Part-Models

  • A Strong Implementation of PCB (Beyond Part Models, ECCV2018) on Market-1501 and DukeMTMC-reID datasets.

  • We support:

    • A strong PCB implementation which outperforms most existing implementations.
    • A simple and clear implementation, and end-to-end training and evaluation.

News

  • We re-write a strong Re-ID baseline Bag of Tricks (BoT) with a more simple and clear implementation, which is more friendly with researchers and newers. Our code can be found here. BoT outperforms PCB by using only the global feature. Our implementation of BoT achieves the same performance with the offical one.

Dependencies

Dataset Preparation

Train and Test

python main.py --market_path market_path --duke_path duke_path

Experiments

1. Settings

  • We conduct our experiments on 2 GTX1080ti GPUs

2. Results

Implementations market2market duke2duke market2duke duke2market
PCB w/ REA (Ours) 0.939 (0.832) <model.pth> 0.856 (0.753) <model.pth> 0.384 (0.237) 0.555 (0.285)
PCB (Ours) 0.934 (0.809) 0.867 (0.746) 0.440(0.265) 0.592 (0.308)
PCB (layumi) 0.926 (0.774) 0.642 (0.439) - -
PCB (huanghoujing) 0.928 (0.785) 0.845 (0.700) - -
PCB (Xiaoccer) 0.927 (0.796) - - -
PCB (Paper) 0.924 (0.773) 0.819 (0.653) - -

Contacts

If you have any question about the project, please feel free to contact with me.

E-mail: [email protected]

About

A strong implementation of PCB (Beyond Part Models), outperforming all existing implementations.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published