{"id":13640727,"url":"https://github.com/megvii-model/YOLOF","last_synced_at":"2025-04-20T06:34:31.792Z","repository":{"id":41471284,"uuid":"346604303","full_name":"megvii-model/YOLOF","owner":"megvii-model","description":null,"archived":false,"fork":false,"pushed_at":"2021-04-12T15:14:17.000Z","size":812,"stargazers_count":804,"open_issues_count":27,"forks_count":115,"subscribers_count":20,"default_branch":"main","last_synced_at":"2024-08-03T01:17:37.540Z","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/megvii-model.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-03-11T06:42:12.000Z","updated_at":"2024-06-29T04:48:22.000Z","dependencies_parsed_at":"2022-07-07T16:21:23.875Z","dependency_job_id":null,"html_url":"https://github.com/megvii-model/YOLOF","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/megvii-model%2FYOLOF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/megvii-model%2FYOLOF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/megvii-model%2FYOLOF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/megvii-model%2FYOLOF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/megvii-model","download_url":"https://codeload.github.com/megvii-model/YOLOF/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223821884,"owners_count":17208752,"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":"2024-08-02T01:01:13.894Z","updated_at":"2024-11-09T11:30:19.710Z","avatar_url":"https://github.com/megvii-model.png","language":"Python","funding_links":[],"categories":["Python","Uncategorized","对象检测、分割","Summary"],"sub_categories":["Uncategorized","网络服务_其他"],"readme":"# You Only Look One-level Feature (YOLOF), CVPR2021\nA simple, fast, and efficient object detector **without** FPN.\n\n- This repo provides an implementation for YOLOF based on [cvpods](https://github.com/Megvii-BaseDetection/cvpods). A neat and re-organized \nDetectron2 version of YOLOF is available at [https://github.\ncom/chensnathan/YOLOF](https://github.com/chensnathan/YOLOF).\n\n\u003e [**You Only Look One-level Feature**](https://arxiv.org/abs/2103.09460),            \n\u003e Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun\n\n![image](images/yolof.png)\n\n## Getting Started\n\n- Install `cvpods`\n  ```shell\n  cd YOLOF/\n  python setup.py develop\n  ```\n- Install `mish-cuda` to speed up the training and inference when using `CSPDarkNet-53` as the backbone (**optional**)\n    ```shell\n    git clone https://github.com/thomasbrandon/mish-cuda\n    cd mish-cuda\n    python setup.py build install\n    cd ..\n    ```\n- Download the pretrained model in [OneDrive](https://1drv.ms/u/s!AgM0VtBH3kV9imGxZX3n_TMQGtbP?e=YMgpGJ) or in the [Baidu Cloud](https://pan.baidu.com/s/1BSOncRYq6HeCQ8q2hrWowA) with code `qr6o` to train with the **CSPDarkNet-53** backbone (**optional**)\n    ```shell\n    mkdir pretrained_models\n    # download the `cspdarknet53.pth` to the `pretrained_models` directory\n    ```\n- Train\n    ```shell\n    cd playground/detection/coco/yolof/yolof.res50.C5.1x\n    pods_train --num-gpus 8\n    ```\n- Test\n    ```shell\n    cd playground/detection/coco/yolof/yolof.res50.C5.1x\n    pods_test --num-gpus 8 MODEL.WEIGHTS /path/to/checkpoint_file\n    ```\n  \n## Main results\n\nThe models listed below can be found in [this onedrive link](https://1drv.ms/u/s!AgM0VtBH3kV9imGxZX3n_TMQGtbP?e=YMgpGJ) or in the [BaiduCloud link](https://pan.baidu.com/s/1BSOncRYq6HeCQ8q2hrWowA) with code `qr6o`. The FPS is tested on a 2080Ti GPU.\nMore models will be available in the near future.\n\n| Model                                     |  COCO val mAP |  FPS  |\n|-------------------------------------------|---------------|-------|\n| YOLOF_R_50_C5_1x                          |  37.7         |   32  |\n| YOLOF_R_50_DC5_1x                         |  39.2         |   20  |\n| YOLOF_R_101_C5_1x                         |  39.8         |   21  |\n| YOLOF_R_101_DC5_1x                        |  40.5         |   15  |\n| YOLOF_X_101_64x4d_C5_1x                   |  42.2         |   10  |\n| YOLOF_CSP_D_53_DC5_3x                     |  41.2         |   39  |\n| YOLOF_CSP_D_53_DC5_9x                     |  42.8         |   39  |\n| YOLOF_CSP_D_53_DC5_9x_stage2_3x           |  43.2         |   39  |\n\n\n## Citation\n\nIf you find this project useful for your research, please use the following BibTeX entry.\n\n    @inproceedings{chen2021you,\n      title={You Only Look One-level Feature},\n      author={Chen, Qiang and Wang, Yingming and Yang, Tong and Zhang, Xiangyu and Cheng, Jian and Sun, Jian},\n      booktitle={IEEE Conference on Computer Vision and Pattern Recognition},\n      year={2021}\n    }","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmegvii-model%2FYOLOF","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmegvii-model%2FYOLOF","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmegvii-model%2FYOLOF/lists"}