{"id":13415377,"url":"https://github.com/xingyizhou/CenterNet2","last_synced_at":"2025-03-14T22:33:24.056Z","repository":{"id":41388194,"uuid":"347789090","full_name":"xingyizhou/CenterNet2","owner":"xingyizhou","description":"Two-stage CenterNet","archived":false,"fork":false,"pushed_at":"2022-11-20T23:07:54.000Z","size":5112,"stargazers_count":1206,"open_issues_count":58,"forks_count":188,"subscribers_count":20,"default_branch":"master","last_synced_at":"2024-10-29T17:49:47.554Z","etag":null,"topics":["coco","object-detection"],"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/xingyizhou.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-03-15T00:27:22.000Z","updated_at":"2024-10-26T06:33:21.000Z","dependencies_parsed_at":"2022-08-10T02:07:09.272Z","dependency_job_id":null,"html_url":"https://github.com/xingyizhou/CenterNet2","commit_stats":null,"previous_names":[],"tags_count":8,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xingyizhou%2FCenterNet2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xingyizhou%2FCenterNet2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xingyizhou%2FCenterNet2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xingyizhou%2FCenterNet2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xingyizhou","download_url":"https://codeload.github.com/xingyizhou/CenterNet2/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243658060,"owners_count":20326459,"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":["coco","object-detection"],"created_at":"2024-07-30T21:00:47.853Z","updated_at":"2025-03-14T22:33:24.037Z","avatar_url":"https://github.com/xingyizhou.png","language":"Python","funding_links":[],"categories":["Frameworks","Python"],"sub_categories":[],"readme":"# Probabilistic two-stage detection\nTwo-stage object detectors that use class-agnostic one-stage detectors as the proposal network.\n\n\n\u003cp align=\"center\"\u003e \u003cimg src='docs/centernet2_teaser.jpg' align=\"center\" height=\"150px\"\u003e \u003c/p\u003e\n\n\u003e [**Probabilistic two-stage detection**](http://arxiv.org/abs/2103.07461),            \n\u003e Xingyi Zhou, Vladlen Koltun, Philipp Kr\u0026auml;henb\u0026uuml;hl,        \n\u003e *arXiv technical report ([arXiv 2103.07461](http://arxiv.org/abs/2103.07461))*         \n\nContact: [zhouxy@cs.utexas.edu](mailto:zhouxy@cs.utexas.edu). Any questions or discussions are welcomed! \n\n## Summary\n\n- Two-stage CenterNet: First stage estimates object probabilities, second stage conditionally classifies objects.\n\n- Resulting detector is faster and more accurate than both traditional two-stage detectors (fewer proposals required), and one-stage detectors (lighter first stage head).\n\n- Our best model achieves 56.4 mAP on COCO test-dev.\n\n- This repo also includes a detectron2-based CenterNet implementation with better accuracy (42.5 mAP at 70FPS) and a new FPN version of CenterNet (40.2 mAP with Res50_1x).\n\n## Main results\n\nAll models are trained with multi-scale training, and tested with a single scale. The FPS is tested on a Titan RTX GPU.\nMore models and details can be found in the [MODEL_ZOO](docs/MODEL_ZOO.md).\n\n#### COCO\n\n| Model                                     |  COCO val mAP |  FPS  |\n|-------------------------------------------|---------------|-------|\n| CenterNet-S4_DLA_8x                       |  42.5         |   71  |\n| CenterNet2_R50_1x                         |  42.9         |   24  |\n| CenterNet2_X101-DCN_2x                    |  49.9         |    8  |\n| CenterNet2_R2-101-DCN-BiFPN_4x+4x_1560_ST |  56.1         |    5  |\n| CenterNet2_DLA-BiFPN-P5_24x_ST            |  49.2         |   38  |\n\n\n#### LVIS \n\n| Model                     | val mAP box |\n| ------------------------- | ----------- |\n| CenterNet2_R50_1x         | 26.5        |\n| CenterNet2_FedLoss_R50_1x | 28.3        |\n\n\n#### Objects365\n\n| Model                                     |  val mAP |\n|-------------------------------------------|----------|\n| CenterNet2_R50_1x                         |  22.6    |\n\n## Installation\n\nOur project is developed on [detectron2](https://github.com/facebookresearch/detectron2). Please follow the official detectron2 [installation](https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md).\n\nWe use the default detectron2 demo script. To run inference on an image folder using our pre-trained model, run\n\n~~~\npython demo.py --config-file configs/CenterNet2_R50_1x.yaml --input path/to/image/ --opts MODEL.WEIGHTS models/CenterNet2_R50_1x.pth\n~~~\n\n## Benchmark evaluation and training\n\nPlease check detectron2 [GETTING_STARTED.md](https://github.com/facebookresearch/detectron2/blob/master/GETTING_STARTED.md) for running evaluation and training. Our config files are under `configs` and the pre-trained models are in the [MODEL_ZOO](docs/MODEL_ZOO.md).\n\n\n## License\n\nOur code is under [Apache 2.0 license](LICENSE). `centernet/modeling/backbone/bifpn_fcos.py` are from [AdelaiDet](https://github.com/aim-uofa/AdelaiDet), which follows the original [non-commercial license](https://github.com/aim-uofa/AdelaiDet/blob/master/LICENSE).\n\n## Citation\n\nIf you find this project useful for your research, please use the following BibTeX entry.\n\n    @inproceedings{zhou2021probablistic,\n      title={Probabilistic two-stage detection},\n      author={Zhou, Xingyi and Koltun, Vladlen and Kr{\\\"a}henb{\\\"u}hl, Philipp},\n      booktitle={arXiv preprint arXiv:2103.07461},\n      year={2021}\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxingyizhou%2FCenterNet2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxingyizhou%2FCenterNet2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxingyizhou%2FCenterNet2/lists"}