{"id":13415393,"url":"https://github.com/braun-steven/DAFNe","last_synced_at":"2025-03-14T22:33:29.360Z","repository":{"id":52037842,"uuid":"404965534","full_name":"braun-steven/DAFNe","owner":"braun-steven","description":"Code for our paper \"DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection\".","archived":false,"fork":false,"pushed_at":"2022-04-01T05:50:11.000Z","size":3137,"stargazers_count":60,"open_issues_count":1,"forks_count":12,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-08-05T01:07:26.260Z","etag":null,"topics":["anchor-free","deep-learning","machine-learning","object-detection","one-stage-detector","oriented-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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/braun-steven.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}},"created_at":"2021-09-10T05:22:04.000Z","updated_at":"2024-06-11T08:38:22.000Z","dependencies_parsed_at":"2022-09-02T18:22:22.596Z","dependency_job_id":null,"html_url":"https://github.com/braun-steven/DAFNe","commit_stats":null,"previous_names":["steven-lang/dafne"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/braun-steven%2FDAFNe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/braun-steven%2FDAFNe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/braun-steven%2FDAFNe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/braun-steven%2FDAFNe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/braun-steven","download_url":"https://codeload.github.com/braun-steven/DAFNe/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":["anchor-free","deep-learning","machine-learning","object-detection","one-stage-detector","oriented-object-detection"],"created_at":"2024-07-30T21:00:48.081Z","updated_at":"2025-03-14T22:33:29.352Z","avatar_url":"https://github.com/braun-steven.png","language":"Python","funding_links":[],"categories":["Frameworks"],"sub_categories":[],"readme":"# DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection\n\n\n\u003cimg src=\"./res/header.png\"/\u003e\n\nCode for our Paper [DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection](https://arxiv.org/abs/2109.06148).\n \t\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dafne-a-one-stage-anchor-free-deep-model-for/one-stage-anchor-free-oriented-object-1)](https://paperswithcode.com/sota/one-stage-anchor-free-oriented-object-1?p=dafne-a-one-stage-anchor-free-deep-model-for)\u003c/br\u003e\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dafne-a-one-stage-anchor-free-deep-model-for/one-stage-anchor-free-oriented-object-2)](https://paperswithcode.com/sota/one-stage-anchor-free-oriented-object-2?p=dafne-a-one-stage-anchor-free-deep-model-for)\u003c/br\u003e\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dafne-a-one-stage-anchor-free-deep-model-for/one-stage-anchor-free-oriented-object-3)](https://paperswithcode.com/sota/one-stage-anchor-free-oriented-object-3?p=dafne-a-one-stage-anchor-free-deep-model-for)\n\n## Datasets\n\n- UCAS-AOD: https://hyper.ai/datasets/5419\n- DOTA 1.0/1.5: https://captain-whu.github.io/DOTA/index.html\n  - Note: See [./tools/prepare_dota/](./tools/prepare_dota/) for instructions on how to prepare the DOTA datasets.\n- HRSC2016: https://www.kaggle.com/guofeng/hrsc2016\n\n## Docker Setup\n\nUse the `Dockerfile` to build the necessary docker image:\n\n``` bash\ndocker build -t dafne .\n```\n\n## Training\n\nCheck out `./configs/pre-trained/` for different pre-defined configurations for the DOTA 1.0, DOTA 1.5, UCAS-AOD, and HRSC2016 datasets. Use these paths as argument for the `--config-file` option below.\n\n\n### With Docker\n\nUse the `./tools/run.py` helper to start running experiments\n\n``` bash\n./tools/run.py --gpus 0,1,2,3 --config-file ./configs/dota-1.0/1024.yaml\n```\n\n### Without Docker\n\n``` bash\nNVIDIA_VISIBLE_DEVICES=0,1,2,3 ./tools/plain_train_net.py --num-gpus 4 --config-file ./configs/dota-1.0/1024.yaml\n```\n\n## Pre-Trained Weights\n\n| Dataset  | mAP (%) | Config                                                          | Weights                                                                                                    |\n|----------|---------|-----------------------------------------------------------------|------------------------------------------------------------------------------------------------------------|\n| UCAS-AOD | 89.65   | [ucas_aod_r101_ms](./configs/pre-trained/ucas_aod_r101_ms.yaml) | [ucas-aod-r101-ms.pth](https://drive.google.com/file/d/1snC7IU-ud-d6L_AxbDx_HG8QBINP2_RO/view?usp=sharing) |\n| HRSC2016 | 89.76   | [hrsc_r50_ms](./configs/pre-trained/hrsc_r50_ms.yaml)           | [hrsc-r50-ms.pth](https://drive.google.com/file/d/10i3pHxiHgjJGzJoZK-HtNdsAyfGD5Ydj/view?usp=sharing)      |\n| DOTA 1.0 | 76.95   | [dota-1.0_r101_ms](./configs/pre-trained/dota-1.0_r101_ms.yaml) | [dota-1.0-r101-ms.pth](https://drive.google.com/file/d/1-lgSLhKQSZBogI2YD0r64wjJV6k2xL4E/view?usp=sharing) |\n| DOTA 1.5 | 71.99   | [dota-1.5_r101_ms](./configs/pre-trained/dota-1.5_r101_ms.yaml) | [dota-1.5-r101-ms.pth](https://drive.google.com/file/d/1MQbTngieoWh-DcJL-z55RnI3PUNeSvBv/view?usp=sharing) |\n\n\n### Pre-Trained Weights Usage with Docker\n\n``` bash\n./tools/run.py --gpus 0 --config-file \u003cCONFIG_PATH\u003e --opts \"MODEL.WEIGHTS \u003cWEIGHTS_PATH\u003e\"\n```\n\n### Pre-Trained Weights Usage without Docker\n\n``` bash\nNVIDIA_VISIBLE_DEVICES=0 ./tools/plain_train_net.py --num-gpus 1 --config-file \u003cCONFIG_PATH\u003e MODEL.WEIGHTS \u003cWEIGHTS_PATH\u003e\n```\n\n## Cite\n\n``` bibtex\n@misc{lang2021dafne,\n      title={DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection}, \n      author={Steven Lang and Fabrizio Ventola and Kristian Kersting},\n      year={2021},\n      eprint={2109.06148},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n\n## Acknowledgments\n\n- Thanks to [AdelaiDet](https://github.com/aim-uofa/AdelaiDet) for providing the initial FCOS implementation\n- Thanks to [Detectron2](https://github.com/facebookresearch/detectron2) for providing a general object detection framework\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbraun-steven%2FDAFNe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbraun-steven%2FDAFNe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbraun-steven%2FDAFNe/lists"}