{"id":13856928,"url":"https://github.com/yqyao/FCOS_PLUS","last_synced_at":"2025-07-13T19:33:23.467Z","repository":{"id":172245421,"uuid":"197902822","full_name":"yqyao/FCOS_PLUS","owner":"yqyao","description":"Some improvements (center sample) about FCOS (FCOS: Fully Convolutional One-Stage Object Detection).","archived":false,"fork":false,"pushed_at":"2019-08-06T05:43:36.000Z","size":8979,"stargazers_count":316,"open_issues_count":8,"forks_count":46,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-05-15T04:39:49.433Z","etag":null,"topics":["anchor-free","computer-vision","fcos","object-detection","one-stage","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yqyao.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2019-07-20T08:34:11.000Z","updated_at":"2024-04-11T09:10:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"ab0b2ab1-fc95-4a50-af00-8298880b370b","html_url":"https://github.com/yqyao/FCOS_PLUS","commit_stats":null,"previous_names":["yqyao/fcos_plus"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yqyao%2FFCOS_PLUS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yqyao%2FFCOS_PLUS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yqyao%2FFCOS_PLUS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yqyao%2FFCOS_PLUS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yqyao","download_url":"https://codeload.github.com/yqyao/FCOS_PLUS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":213988289,"owners_count":15666956,"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":["anchor-free","computer-vision","fcos","object-detection","one-stage","pytorch"],"created_at":"2024-08-05T03:01:19.204Z","updated_at":"2024-08-05T03:02:22.961Z","avatar_url":"https://github.com/yqyao.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# FCOS_PLUS\n\nThis project contains some improvements about FCOS (Fully Convolutional One-Stage Object Detection).\n\n\n## Installation\n\nPlease check [INSTALL.md](INSTALL.md) (same as original FCOS) for installation instructions. \n\n\n**Results**\n\n\nModel | Total training mem (GB) | Multi-scale training | Testing time / im | AP (minival) | link \n---   |:---:|:---:|:---:|:---:|:---:|\nFCOS_R_50_FPN_1x | 29.3 | No | 71ms | 37.0 | [model](https://pan.baidu.com/s/1Xcbx7EfOGvwnexXAuovM0A) |\nFCOS_R_50_FPN_1x_center | 30.61 | No | 71ms | 37.8 | [model](https://pan.baidu.com/s/1Gs7AzmJRmeYhXUPDQZuSLA) |\nFCOS_R_50_FPN_1x_center_liou | 30.61 | No | 71ms | 38.1 | [model](https://pan.baidu.com/s/1HpYrkAsVXNvXRFTd06SGgA) |\nFCOS_R_50_FPN_1x_center_giou | 30.61 | No | 71ms | 38.2 | [model](https://pan.baidu.com/s/13_o6343Ikg4td01kVXxGSw) |\nFCOS_R_101_FPN_2x | 44.1 | Yes | 74ms | 41.4 | [model](https://pan.baidu.com/s/1u_5OD5NURYe1EYFWnohgEA) |\nFCOS_R_101_FPN_2x_center_giou | 44.1 | Yes | 74ms | 42.5 | [model](https://pan.baidu.com/s/1qhHM067ywwlEXfamaFq23g) |\n\n[1] *1x and 2x mean the model is trained for 90K and 180K iterations, respectively.* \\\n[2] center means [center sample](fcos.pdf) is used in our training. \\\n[3] liou means the model use linear iou loss function. (1 - iou) \\\n[4] giou means the use giou loss function. (1 - giou) \n\n\n## Training\n\nThe following command line will train FCOS_R_50_FPN_1x on 8 GPUs with Synchronous Stochastic Gradient Descent (SGD):\n\n    python -m torch.distributed.launch \\\n        --nproc_per_node=8 \\\n        --master_port=$((RANDOM + 10000)) \\\n        tools/train_net.py \\\n        --skip-test \\\n        --config-file configs/fcos/fcos_R_50_FPN_1x_center_giou.yaml \\\n        DATALOADER.NUM_WORKERS 2 \\\n        OUTPUT_DIR training_dir/fcos_R_50_FPN_1x_center_giou\n        \nNote that:\n1) If you want to use fewer GPUs, please change `--nproc_per_node` to the number of GPUs. No other settings need to be changed. The total batch size does not depends on `nproc_per_node`. If you want to change the total batch size, please change `SOLVER.IMS_PER_BATCH` in [configs/fcos/fcos_R_50_FPN_1x_center_giou.yaml](configs/fcos/fcos_R_50_FPN_1x_center_giou.yaml).\n2) The models will be saved into `OUTPUT_DIR`.\n3) If you want to train FCOS with other backbones, please change `--config-file`.\n\n## Citations\nPlease consider citing original paper in your publications if the project helps your research. \n```\n@article{tian2019fcos,\n  title   =  {{FCOS}: Fully Convolutional One-Stage Object Detection},\n  author  =  {Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},\n  journal =  {arXiv preprint arXiv:1904.01355},\n  year    =  {2019}\n}\n```\n\n\n## License\n\nFor academic use, this project is licensed under the 2-clause BSD License - see the LICENSE file for details. For commercial use, please contact the authors. \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyqyao%2FFCOS_PLUS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyqyao%2FFCOS_PLUS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyqyao%2FFCOS_PLUS/lists"}