{"id":18575209,"url":"https://github.com/tensorboy/centerpose","last_synced_at":"2025-05-07T21:40:34.475Z","repository":{"id":113036477,"uuid":"214506419","full_name":"tensorboy/centerpose","owner":"tensorboy","description":"Push the Extreme of the pose estimation","archived":false,"fork":false,"pushed_at":"2020-02-26T18:51:10.000Z","size":53989,"stargazers_count":239,"open_issues_count":16,"forks_count":45,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-05-05T02:55:14.267Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tensorboy.png","metadata":{"files":{"readme":"README.md","changelog":null,"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":"2019-10-11T18:38:50.000Z","updated_at":"2025-03-12T08:40:19.000Z","dependencies_parsed_at":"2023-06-03T04:10:03.708Z","dependency_job_id":null,"html_url":"https://github.com/tensorboy/centerpose","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorboy%2Fcenterpose","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorboy%2Fcenterpose/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorboy%2Fcenterpose/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorboy%2Fcenterpose/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tensorboy","download_url":"https://codeload.github.com/tensorboy/centerpose/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252961082,"owners_count":21832179,"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":[],"created_at":"2024-11-06T23:18:04.669Z","updated_at":"2025-05-07T21:40:34.437Z","avatar_url":"https://github.com/tensorboy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# The repo is based on [CenterNet](https://arxiv.org/abs/1904.07850), which aimed for push the boundary of human pose estimation\nmulti person pose estimation using center point detection:\n![](readme/fig2.png)\n\n## Main results\n\n### Keypoint detection on COCO validation 2017\n\u003cp align=\"center\"\u003e \u003cimg src='readme/performance.png' align=\"center\" height=\"512px\"\u003e\u003c/p\u003e\n\n| Backbone     |  AP       |  FPS         | TensorRT Speed | GFLOPs |Download |\n|--------------|-----------|--------------|----------|----------|----------|\n|DLA-34        | 62.7      |    23      |  - |  - |[model](https://drive.google.com/open?id=1IahJ3vpjTVu1p-Okf6lcn-bM7fVKNg6N)  |\n|Resnet-50     | 54.5     |    28      |  33 |  - |[model](https://drive.google.com/open?id=1oBgWrfigo2fGtpQJXQ0stADTgVFxPWGq)  |\n|MobilenetV3   | 46.0      |    30      |  - |  - |[model](https://drive.google.com/open?id=1snJnADAD1NUzyO1QXCftuZu1rsr8095G)  |\n|ShuffleNetV2  | 43.9      |    25      |  - |  - |[model](https://drive.google.com/open?id=1FK7YQzCB6mLcb0v4SOmlqtRJfA-PQSvN)  |\n|[HRNet_W32](https://drive.google.com/open?id=1mJoK7KEx35Wgf6uAZ-Ez5IwAeOk1RYw0)| 63.8 |    16      |  - |  - |[model](https://drive.google.com/open?id=1X0yxGeeNsD4VwU2caDo-BaH_MoCAnU_J)  |\n|[HardNet](https://github.com/PingoLH/FCHarDNet)| 46.0    |    30        | -  |  - |[model](https://drive.google.com/open?id=1CFc_qAAT4NFfrAG8JOxRVG8CAw9ySuYp)  |\n|[Darknet53]()| 34.2    |    30        | -  |  - |[model](https://drive.google.com/open?id=1S8spP_QKHqIYmWpfF9Bb4-4OoUXIOnkh)  |\n|[EfficientDet]()| 38.2    |    30        | -  |  - |[model](https://drive.google.com/open?id=1S8spP_QKHqIYmWpfF9Bb4-4OoUXIOnkh)  |\n\n## Installation\n\ngit submodule init\u0026git submodule update\nPlease refer to [INSTALL.md](readme/INSTALL.md) for installation instructions.\n\n## Use CenterNet\n\nWe support demo for image/ image folder, video, and webcam. \n\nFirst, download the model [DLA-34](https://drive.google.com/open?id=1OkHjjViB0dzbuicdtIam-YcoT0sYpmjP)\nfrom the [Model zoo](https://drive.google.com/open?id=1UG2l8XtjOfBtG_GLpSdxlWS2wxFR8hQF) and put them in anywhere.\n\nRun:\n    \n~~~\ncd tools; python demo.py --cfg ../experiments/dla_34_512x512.yaml --TESTMODEL /your/model/path/dla34_best.pth --DEMOFILE ../images/33823288584_1d21cf0a26_k.jpg --DEBUG 1\n~~~\nThe result for the example images should look like:\n\u003cp align=\"center\"\u003e \u003cimg src='readme/multi_pose_screenshot_27.11.2019.png' align=\"center\" height=\"512px\"\u003e\u003c/p\u003e\n\n## Evaluation \n~~~\ncd tools; python evaluate.py --cfg ../experiments/dla_34_512x512.yaml --TESTMODEL /your/model/path/dla34_best.pth --DEMOFILE --DEBUG 0\n~~~\n\n## Training\n\nAfter [installation](readme/INSTALL.md), follow the instructions in [DATA.md](readme/DATA.md) to setup the datasets.\n\nWe provide config files for all the experiments in the [experiments](experiments) folder.\n\n```\ncd ./tools python -m torch.distributed.launch --nproc_per_node 4 train.py --cfg ../experiments/*yalm\n```\n\n## Demo\n\nthe demo files located in the `demo` directory, which is would be a very robust human detection+tracking+face reid system.\n\n\u003cp align=\"left\"\u003e\n\u003cimg src=\"./readme/demo.gif\", width=\"720\"\u003e\n\u003c/p\u003e\n\n## License\n\nMIT License (refer to the LICENSE file for details).\n\n## Citation\n\nIf you find this project useful for your research, please use the following BibTeX entry.\n\n    @inproceedings{zhou2019objects,\n      title={Objects as Points},\n      author={Zhou, Xingyi and Wang, Dequan and Kr{\\\"a}henb{\\\"u}hl, Philipp},\n      booktitle={arXiv preprint arXiv:1904.07850},\n      year={2019}\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorboy%2Fcenterpose","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftensorboy%2Fcenterpose","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorboy%2Fcenterpose/lists"}