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.
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 installpython examples/softmax_loss.py -d viper -b 64 -j 2 -a resnet50 --logs-dir logs/softmax-loss/viper-resnet50This is just a quick example. VIPeR dataset may not be large enough to train a deep neural network.
Check about more examples and benchmarks.