mirrors
/
fast-reid
mirror of https://github.com/JDAI-CV/fast-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
SOTA Re-identification Methods and Toolbox
380 Commits
1 Branch
4 Tags
15 MiB
Python 86.7%
C++ 11%
Cython 1.3%
CMake 0.6%
Dockerfile 0.4%
 
 
 
 
 
Go to file
liaoxingyu2 64bf78afee update rank_cylib 2020-11-06 11:00:13 +08:00
.github/ISSUE_TEMPLATE update issue template 2020-07-15 15:10:31 +08:00
configs change config file 2020-09-10 10:58:56 +08:00
datasets update training instruction 2020-06-16 19:43:36 +08:00
demo fix typro ##255 2020-09-10 11:10:40 +08:00
docs support set up with conda 2020-09-08 11:14:05 +08:00
fastreid update rank_cylib 2020-11-06 11:00:13 +08:00
projects update bohb search space 2020-10-12 20:21:47 +08:00
tests add unitest for feature alignment 2020-06-22 11:48:14 +08:00
tools support finetuning from trained models 2020-09-28 17:10:10 +08:00
.gitignore Change architecture: 2020-02-18 21:01:23 +08:00
LICENSE update LICENSE 2020-05-29 13:02:55 +08:00
README.md support hpo project 2020-10-01 18:10:02 +08:00

README.md

FastReID

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.

What's New

  • [Oct 2020] Added the Hyper-Parameter Optimization based on fastreid. See projects/HPOReID.
  • [Sep 2020] Added the person attribute recognition based on fastreid. See projects/attribute_recognition.
  • [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.

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}
}