{"id":13576402,"url":"https://github.com/LeapLabTHU/Rank-DETR","last_synced_at":"2025-04-05T05:31:48.805Z","repository":{"id":200806919,"uuid":"703841896","full_name":"LeapLabTHU/Rank-DETR","owner":"LeapLabTHU","description":"[NeurIPS 2023] Rank-DETR for High Quality Object Detection","archived":false,"fork":false,"pushed_at":"2023-10-19T07:34:15.000Z","size":9308,"stargazers_count":87,"open_issues_count":1,"forks_count":6,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-05T12:33:38.025Z","etag":null,"topics":[],"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/LeapLabTHU.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":"2023-10-12T03:02:25.000Z","updated_at":"2024-10-29T10:49:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"080a5890-face-4bdb-bc93-be127ef5cba4","html_url":"https://github.com/LeapLabTHU/Rank-DETR","commit_stats":null,"previous_names":["leaplabthu/rank-detr"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LeapLabTHU%2FRank-DETR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LeapLabTHU%2FRank-DETR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LeapLabTHU%2FRank-DETR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LeapLabTHU%2FRank-DETR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LeapLabTHU","download_url":"https://codeload.github.com/LeapLabTHU/Rank-DETR/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247294453,"owners_count":20915335,"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":"2024-08-01T15:01:09.965Z","updated_at":"2025-04-05T05:31:43.787Z","avatar_url":"https://github.com/LeapLabTHU.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Rank-DETR for High Quality Object Detection (NeurIPS 2023)\n\nYifan Pu, Weicong Liang, Yiduo Hao, Yuhui Yuan, Yukang Yang, Chao Zhang, Han Hu, and Gao Huang\n\n[[`arXiv`](https://arxiv.org/abs/2310.08854)] [[`BibTeX`](#citing-rank-detr)]\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"projects/rank_detr/assets/rank_detr_overview.png\"/\u003e\n\u003c/div\u003e\u003cbr/\u003e\n\n\n## Table of Contents\n- [Installation](#installation)\n- [Pretrained Models](#pretrained-models)\n- [Run](#run)\n  - [Training](#training)\n  - [Evaluation](#evaluation)\n- [Citation](#citing-rank-detr)\n\n## Installation\nPlease refer to the [installation document](https://detrex.readthedocs.io/en/latest/tutorials/Installation.html) of detrex.\n\n## Pretrained Models\nHere we provide the Rank-DETR model pretrained weights based on detrex:\n\u003ctable\u003e\u003ctbody\u003e\n\u003c!-- START TABLE --\u003e\n\u003c!-- TABLE HEADER --\u003e\n\u003cth valign=\"bottom\"\u003eName\u003c/th\u003e\n\u003cth valign=\"bottom\"\u003eBackbone\u003c/th\u003e\n\u003cth valign=\"bottom\"\u003eQuery Num\u003c/th\u003e\n\u003cth valign=\"bottom\"\u003eEpochs\u003c/th\u003e\n\u003cth valign=\"bottom\"\u003eAP\u003c/th\u003e\n\u003cth valign=\"bottom\"\u003edownload\u003c/th\u003e\n\u003c!-- TABLE BODY --\u003e\n\u003c/tr\u003e\n \u003ctr\u003e\u003ctd align=\"left\"\u003e\u003ca href=\"configs/rank_detr_r50_two_stage_12ep.py\"\u003eRank-DETR\u003c/a\u003e\u003c/td\u003e\n\u003ctd align=\"center\"\u003eR50\u003c/td\u003e\n\u003ctd align=\"center\"\u003e300\u003c/td\u003e\n\u003ctd align=\"center\"\u003e12\u003c/td\u003e\n\u003ctd align=\"center\"\u003e50.2\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\u003ca href=\"https://cloud.tsinghua.edu.cn/f/4cc3dea3c2f64360894f/?dl=1\"\u003emodel\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/tr\u003e\n \u003ctr\u003e\u003ctd align=\"left\"\u003e\u003ca href=\"configs/rank_detr_r50_two_stage_12ep.py\"\u003eRank-DETR\u003c/a\u003e\u003c/td\u003e\n\u003ctd align=\"center\"\u003eR50\u003c/td\u003e\n\u003ctd align=\"center\"\u003e300\u003c/td\u003e\n\u003ctd align=\"center\"\u003e36\u003c/td\u003e\n\u003ctd align=\"center\"\u003e51.2\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\u003ca href=\"https://cloud.tsinghua.edu.cn/f/761f8e9e5bc74d2fa4ce/?dl=1\"\u003emodel\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/tr\u003e\n \u003ctr\u003e\u003ctd align=\"left\"\u003e\u003ca href=\"configs/rank_detr_r50_two_stage_12ep.py\"\u003eRank-DETR\u003c/a\u003e\u003c/td\u003e\n\u003ctd align=\"center\"\u003eSwin Tiny\u003c/td\u003e\n\u003ctd align=\"center\"\u003e300\u003c/td\u003e\n\u003ctd align=\"center\"\u003e12\u003c/td\u003e\n\u003ctd align=\"center\"\u003e52.7\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\u003ca href=\"https://cloud.tsinghua.edu.cn/f/b32aae34fce449aa9aca/?dl=1\"\u003emodel\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/tr\u003e\n \u003ctr\u003e\u003ctd align=\"left\"\u003e\u003ca href=\"configs/rank_detr_r50_two_stage_12ep.py\"\u003eRank-DETR\u003c/a\u003e\u003c/td\u003e\n\u003ctd align=\"center\"\u003eSwin Tiny\u003c/td\u003e\n\u003ctd align=\"center\"\u003e300\u003c/td\u003e\n\u003ctd align=\"center\"\u003e36\u003c/td\u003e\n\u003ctd align=\"center\"\u003e54.7 \u003c/td\u003e\n\u003ctd align=\"center\"\u003e\u003ca href=\"https://cloud.tsinghua.edu.cn/f/649dc9b265a641f5be5c/?dl=1\"\u003emodel\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/tr\u003e\n \u003ctr\u003e\u003ctd align=\"left\"\u003e\u003ca href=\"configs/rank_detr_r50_two_stage_12ep.py\"\u003eRank-DETR\u003c/a\u003e\u003c/td\u003e\n\u003ctd align=\"center\"\u003eSwin Large\u003c/td\u003e\n\u003ctd align=\"center\"\u003e300\u003c/td\u003e\n\u003ctd align=\"center\"\u003e12\u003c/td\u003e\n\u003ctd align=\"center\"\u003e57.3\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\u003ca href=\"https://cloud.tsinghua.edu.cn/f/b03f2e1a148045e78619/?dl=1\"\u003emodel\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/tr\u003e\n \u003ctr\u003e\u003ctd align=\"left\"\u003e\u003ca href=\"configs/rank_detr_r50_two_stage_12ep.py\"\u003eRank-DETR\u003c/a\u003e\u003c/td\u003e\n\u003ctd align=\"center\"\u003eSwin Large\u003c/td\u003e\n\u003ctd align=\"center\"\u003e300\u003c/td\u003e\n\u003ctd align=\"center\"\u003e36\u003c/td\u003e\n\u003ctd align=\"center\"\u003e58.2\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\u003ca href=\"https://cloud.tsinghua.edu.cn/f/34912e493fb644dd8bf4/?dl=1\"\u003emodel\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\u003c/table\u003e\n\n\n\n## Run\n### Training\n\nAll configs can be trained with:\n\n```bash\ncd detrex\npython projects/rank_detr/train_net.py --config-file projects/rank_detr/configs/path/to/config.py --num-gpus 8\n```\n\n* By default, we use 8 GPUs with total batch size as 16 for training.\n* To train/eval a model with the swin transformer backbone, you need to download the backbone from the [offical repo](https://github.com/microsoft/Swin-Transformer#main-results-on-imagenet-with-pretrained-models) frist and specify argument `train.init_checkpoint` like [our configs](./configs/rank_detr_swin_tiny_two_stage_12ep.py).\n\n### Evaluation\nModel evaluation can be done as follows:\n```bash\ncd detrex\npython projects/rank_detr/train_net.py --config-file projects/rank_detr/configs/path/to/config.py  --eval-only train.init_checkpoint=/path/to/model_checkpoint\n```\n\n\n\n\n## Citing Rank-DETR\nIf you find Rank-DETR useful in your research, please consider citing:\n\n```bibtex\n@inproceedings{pu2023rank,\n  title={Rank-DETR for High Quality Object Detection},\n  author={Pu, Yifan and Liang, Weicong and Hao, Yiduo and Yuan, Yuhui and Yang, Yukang and Zhang, Chao and Hu, Han and Huang, Gao},\n  booktitle={NeurIPS},\n  year={2023}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLeapLabTHU%2FRank-DETR","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FLeapLabTHU%2FRank-DETR","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLeapLabTHU%2FRank-DETR/lists"}