Skip to content
Open source person re-identification library in python
Branch: master
Clone or download
Pull request Compare This branch is 40 commits ahead, 2 commits behind Cysu:master.
Latest commit 0ff2b0a Oct 31, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
docs
examples cotrain Oct 23, 2017
reid market1501 Oct 31, 2017
test
.gitignore
LICENSE
README.md
setup.cfg
setup.py
spaco.sh

README.md

Self-Paced Co-training Person-ReID

Pytorch implementaion based on Open-Reid

Run

bash spaco.sh

alternatively, you can run with

python examples/spaco.py --arch1 resnet50 --arch2 densenet121 --iter-step 5 --dataset market1501std --logs-dir logs/

Please cite spaco in your publications if it helps your research:
@inproceedings{ma2017self,
title={Self-Paced Co-training},
author={Ma, Fan and Meng, Deyu and Xie, Qi and Li, Zina and Dong, Xuanyi},
booktitle={International Conference on Machine Learning},
pages={2275--2284},
year={2017}
}

Open-ReID

Open-ReID is a lightweight library of person re-identification for research purpose. It aims to provide a uniform interface for different datasets, a full set of models and evaluation metrics, as well as examples to reproduce (near) state-of-the-art results.

Installation

Install PyTorch (version >= 0.2.0). Although we support both python2 and python3, we recommend python3 for better performance.

git clone https://github.com/Cysu/open-reid.git
cd open-reid
python setup.py install

Examples

python examples/softmax_loss.py -d viper -b 64 -j 2 -a resnet50 --logs-dir logs/softmax-loss/viper-resnet50

This is just a quick example. VIPeR dataset may not be large enough to train a deep neural network.

Check about more examples and benchmarks.

You can’t perform that action at this time.