JDAI-CV / fast-reid

SOTA Re-identification Methods and Toolbox

Gitter: fast-reid/community

Wechat:

FastReID is a research platform that implements state-of-the-art re-identification algorithms. It is a ground-up rewrite of the previous version, reid strong baseline.

What's New

• [Sep 2021] DG-ReID is updated, you can check the paper.
• [June 2021] Contiguous parameters is supported, now it can accelerate ~20%.
• [May 2021] Vision Transformer backbone supported, see configs/Market1501/bagtricks_vit.yml.
• [Apr 2021] Partial FC supported in FastFace!
• [Jan 2021] TRT network definition APIs in FastRT has been released! Thanks for Darren's contribution.
• [Jan 2021] NAIC20(reid track) 1-st solution based on fastreid has been released！
• [Jan 2021] FastReID V1.0 has been released！🎉 Support many tasks beyond reid, such image retrieval and face recognition. See release notes.
• [Oct 2020] Added the Hyper-Parameter Optimization based on fastreid. See projects/FastTune.
• [Sep 2020] Added the person attribute recognition based on fastreid. See projects/FastAttr.
• [Sep 2020] Automatic Mixed Precision training is supported with apex. Set cfg.SOLVER.FP16_ENABLED=True to switch it on.
• [Aug 2020] Model Distillation is supported, thanks for guan'an wang's contribution.
• [Aug 2020] ONNX/TensorRT converter is supported.
• [Jul 2020] Distributed training with multiple GPUs, it trains much faster.
• Includes more features such as circle loss, abundant visualization methods and evaluation metrics, SoTA results on conventional, cross-domain, partial and vehicle re-id, testing on multi-datasets simultaneously, etc.
• Can be used as a library to support different projects on top of it. We'll open source more research projects in this way.
• Remove ignite(a high-level library) dependency and powered by PyTorch.

We write a fastreid intro and fastreid v1.0 about this toolbox.

Changelog

Please refer to changelog.md for details and release history.

Installation

See INSTALL.md.

Quick Start

The designed architecture follows this guide PyTorch-Project-Template, you can check each folder's purpose by yourself.

See GETTING_STARTED.md.

Learn more at out documentation. And see projects/ for some projects that are build on top of fastreid.

Model Zoo and Baselines

We provide a large set of baseline results and trained models available for download in the Fastreid Model Zoo.

Deployment

We provide some examples and scripts to convert fastreid model to Caffe, ONNX and TensorRT format in Fastreid deploy.

License

Fastreid is released under the Apache 2.0 license.

Citing FastReID

If you use FastReID in your research or wish to refer to the baseline results published in the Model Zoo, please use the following BibTeX entry.

@article{he2020fastreid,
  title={FastReID: A Pytorch Toolbox for General Instance Re-identification},
  author={He, Lingxiao and Liao, Xingyu and Liu, Wu and Liu, Xinchen and Cheng, Peng and Mei, Tao},
  journal={arXiv preprint arXiv:2006.02631},
  year={2020}
}