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

Our Interpreter Project is based on FastReID

• [Oct 2021] Quick Start of Interpreter Project.
• [Sep 2020] Automatic Mixed Precision training is supported with pytorch1.6 built-in torch.cuda.amp. Set cfg.SOLVER.AMP_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.
• [Jul 2020] MAX_ITER in config means epoch, it will auto scale to maximum iterations.
• 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 chinese blog about this toolbox.

See INSTALL.md and INSTALL_for_interpreter.md.

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.

GPU>=16GB memory

RAM>=128GB memory

Step 0, modify the PATH in the shell script to suit your computer.

Step 1, train ReID model:

bash shell/Market1501/0_train_market_bagtricks_euclidean.sh

Ps: release model on Market1501

Step 2, train Interpreter model:

bash shell/Market1501/1_train_market_interpretation.sh

In order to solve the requirements of demo, after several update iterations, the code of this version adds some functions, backbone for demo and Loss for specific datasets on the basis of the framework of our paper.

For the slightly inconsistent parts between this code and paper description, please feel free to use, it does not affect the final performance.

Positive Mask

Negative Mask

Person Sample

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

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

Fastreid is released under the Apache 2.0 license.

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.

@inproceedings{chen2021AMD,
  title={Explainable Person Re-Identification with Attribute-guided Metric Distillation},
  author={Chen, Liu and Liu, Zhang and Zhang, Mei},
  booktitle={IEEE International Conference on Computer Vision (ICCV)},
  year={2021}
}

@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}
}