{"id":13442078,"url":"https://github.com/JDAI-CV/fast-reid","last_synced_at":"2025-03-20T13:32:08.704Z","repository":{"id":37407207,"uuid":"136302835","full_name":"JDAI-CV/fast-reid","owner":"JDAI-CV","description":"SOTA Re-identification Methods and Toolbox","archived":false,"fork":false,"pushed_at":"2024-07-30T14:37:38.000Z","size":14083,"stargazers_count":3554,"open_issues_count":16,"forks_count":846,"subscribers_count":59,"default_branch":"master","last_synced_at":"2025-03-18T23:41:41.855Z","etag":null,"topics":["apex","baseline","computer-vision","image-retrieval","image-search","open-reid","person-reid","person-reidentification","pytorch","random-erasing","re-identification","re-ranking","reids","sota","toolbox"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JDAI-CV.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-06-06T09:08:20.000Z","updated_at":"2025-03-18T07:16:29.000Z","dependencies_parsed_at":"2023-02-15T13:15:27.213Z","dependency_job_id":"cf7e6081-0b98-4ef3-b961-e1b483caaf86","html_url":"https://github.com/JDAI-CV/fast-reid","commit_stats":{"total_commits":485,"total_committers":24,"mean_commits":"20.208333333333332","dds":"0.23092783505154635","last_synced_commit":"817c748e8c44ed8c12c3e95de355610c094fade1"},"previous_names":["l1aoxingyu/reid_baseline"],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JDAI-CV%2Ffast-reid","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JDAI-CV%2Ffast-reid/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JDAI-CV%2Ffast-reid/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JDAI-CV%2Ffast-reid/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JDAI-CV","download_url":"https://codeload.github.com/JDAI-CV/fast-reid/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244619148,"owners_count":20482369,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["apex","baseline","computer-vision","image-retrieval","image-search","open-reid","person-reid","person-reidentification","pytorch","random-erasing","re-identification","re-ranking","reids","sota","toolbox"],"created_at":"2024-07-31T03:01:41.413Z","updated_at":"2025-10-14T12:09:56.303Z","avatar_url":"https://github.com/JDAI-CV.png","language":"Python","funding_links":[],"categories":["Python","Uncategorized","1.5 Source-Free Domain Adaptive Re-ID","Toolbox"],"sub_categories":["Uncategorized","AI Algorithm"],"readme":"\u003cimg src=\".github/FastReID-Logo.png\" width=\"300\" \u003e\n\n[![Gitter](https://badges.gitter.im/fast-reid/community.svg)](https://gitter.im/fast-reid/community?utm_source=badge\u0026utm_medium=badge\u0026utm_campaign=pr-badge)\n\nGitter: [fast-reid/community](https://gitter.im/fast-reid/community?utm_source=share-link\u0026utm_medium=link\u0026utm_campaign=share-link)\n\nWechat: \n\n\u003cimg src=\".github/wechat_group.png\" width=\"150\" \u003e\n\n\nFastReID 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](https://github.com/michuanhaohao/reid-strong-baseline).\n\n## What's New\n\n- [Sep 2021] [DG-ReID](https://github.com/xiaomingzhid/sskd) is updated, you can check the [paper](https://arxiv.org/pdf/2108.05045.pdf).\n- [June 2021] [Contiguous parameters](https://github.com/PhilJd/contiguous_pytorch_params) is supported, now it can\n  accelerate ~20%.\n- [May 2021] Vision Transformer backbone supported, see `configs/Market1501/bagtricks_vit.yml`.\n- [Apr 2021] Partial FC supported in [FastFace](projects/FastFace)!\n- [Jan 2021] TRT network definition APIs in [FastRT](projects/FastRT) has been released! \nThanks for [Darren](https://github.com/TCHeish)'s contribution.\n- [Jan 2021] NAIC20(reid track) [1-st solution](projects/NAIC20) based on fastreid has been released！\n- [Jan 2021] FastReID V1.0 has been released！🎉\n  Support many tasks beyond reid, such image retrieval and face recognition. See [release notes](https://github.com/JDAI-CV/fast-reid/releases/tag/v1.0.0).\n- [Oct 2020] Added the [Hyper-Parameter Optimization](projects/FastTune) based on fastreid. See `projects/FastTune`.\n- [Sep 2020] Added the [person attribute recognition](projects/FastAttr) based on fastreid. See `projects/FastAttr`.\n- [Sep 2020] Automatic Mixed Precision training is supported with `apex`. Set `cfg.SOLVER.FP16_ENABLED=True` to switch it on.\n- [Aug 2020] [Model Distillation](projects/FastDistill) is supported, thanks for [guan'an wang](https://github.com/wangguanan)'s contribution.\n- [Aug 2020] ONNX/TensorRT converter is supported.\n- [Jul 2020] Distributed training with multiple GPUs, it trains much faster.\n- 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.\n- Can be used as a library to support [different projects](projects) on top of it. We'll open source more research projects in this way.\n- Remove [ignite](https://github.com/pytorch/ignite)(a high-level library) dependency and powered by [PyTorch](https://pytorch.org/).\n\nWe write a [fastreid intro](https://l1aoxingyu.github.io/blogpages/reid/fastreid/2020/05/29/fastreid.html) \nand [fastreid v1.0](https://l1aoxingyu.github.io/blogpages/reid/fastreid/2021/04/28/fastreid-v1.html) about this toolbox.\n\n## Changelog\n\nPlease refer to [changelog.md](CHANGELOG.md) for details and release history.\n\n## Installation\n\nSee [INSTALL.md](INSTALL.md).\n\n## Quick Start\n\nThe designed architecture follows this guide [PyTorch-Project-Template](https://github.com/L1aoXingyu/PyTorch-Project-Template), you can check each folder's purpose by yourself.\n\nSee [GETTING_STARTED.md](GETTING_STARTED.md).\n\nLearn more at out [documentation](https://fast-reid.readthedocs.io/). And see [projects/](projects) for some projects that are build on top of fastreid.\n\n## Model Zoo and Baselines\n\nWe provide a large set of baseline results and trained models available for download in the [Fastreid Model Zoo](MODEL_ZOO.md).\n\n## Deployment\n\nWe provide some examples and scripts to convert fastreid model to Caffe, ONNX and TensorRT format in [Fastreid deploy](tools/deploy).\n\n## License\n\nFastreid is released under the [Apache 2.0 license](LICENSE).\n\n## Citing FastReID\n\nIf 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.\n\n```BibTeX\n@article{he2020fastreid,\n  title={FastReID: A Pytorch Toolbox for General Instance Re-identification},\n  author={He, Lingxiao and Liao, Xingyu and Liu, Wu and Liu, Xinchen and Cheng, Peng and Mei, Tao},\n  journal={arXiv preprint arXiv:2006.02631},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FJDAI-CV%2Ffast-reid","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FJDAI-CV%2Ffast-reid","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FJDAI-CV%2Ffast-reid/lists"}