https://github.com/cysu/open-reid

Open source person re-identification library in python
https://github.com/cysu/open-reid

deep-learning metric-learning person-reidentification python pytorch

Last synced: 3 days ago
JSON representation

Open source person re-identification library in python

• Host: GitHub
• URL: https://github.com/cysu/open-reid
• Owner: Cysu
• License: mit
• Created: 2017-02-20T03:30:29.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2019-04-23T11:49:54.000Z (over 5 years ago)
• Last Synced: 2024-12-15T15:04:23.091Z (10 days ago)
• Topics: deep-learning, metric-learning, person-reidentification, python, pytorch
• Language: Python
• Homepage: https://cysu.github.io/open-reid/
• Size: 4.86 MB
• Stars: 1,342
• Watchers: 40
• Forks: 351
• Open Issues: 37
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# 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](http://pytorch.org/) (version >= 0.2.0). Although we support

both python2 and python3, we recommend python3 for better performance.

```shell

git clone https://github.com/Cysu/open-reid.git

cd open-reid

python setup.py install

```

## Examples

```shell

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](https://cysu.github.io/open-reid/examples/training_id.html)

and [benchmarks](https://cysu.github.io/open-reid/examples/benchmarks.html).