{"id":13415352,"url":"https://github.com/Megvii-BaseDetection/AutoAssign","last_synced_at":"2025-03-14T22:33:21.064Z","repository":{"id":59431035,"uuid":"317792072","full_name":"Megvii-BaseDetection/AutoAssign","owner":"Megvii-BaseDetection","description":"Pytorch implementation of \"AutoAssign: Differentiable Label Assignment for Dense Object Detection\"","archived":false,"fork":false,"pushed_at":"2020-12-07T12:15:00.000Z","size":350,"stargazers_count":140,"open_issues_count":2,"forks_count":18,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-07-31T21:53:43.062Z","etag":null,"topics":["coco-dataset","computer-vision","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/Megvii-BaseDetection.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":"2020-12-02T08:08:03.000Z","updated_at":"2024-07-12T09:02:28.000Z","dependencies_parsed_at":"2022-09-17T01:20:46.491Z","dependency_job_id":null,"html_url":"https://github.com/Megvii-BaseDetection/AutoAssign","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-BaseDetection%2FAutoAssign","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Megvii-BaseDetection%2FAutoAssign/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Megvii-BaseDetection%2FAutoAssign/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Megvii-BaseDetection%2FAutoAssign/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Megvii-BaseDetection","download_url":"https://codeload.github.com/Megvii-BaseDetection/AutoAssign/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243658059,"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-dataset","computer-vision","object-detection"],"created_at":"2024-07-30T21:00:47.490Z","updated_at":"2025-03-14T22:33:21.059Z","avatar_url":"https://github.com/Megvii-BaseDetection.png","language":"Python","funding_links":[],"categories":["Frameworks"],"sub_categories":[],"readme":"# AutoAssign: Differentiable Label Assignment for Dense Object Detection \n\n# ![pipeline](./pipeline.png)\n\nThis is a PyTorch implementation of the [AutoAssign paper](https://arxiv.org/abs/2007.03496):\n\n```\n@article{zhu2020autoassign,\n  title={AutoAssign: Differentiable Label Assignment for Dense Object Detection},\n  author={Zhu, Benjin and Wang, Jianfeng and Jiang, Zhengkai and Zong, Fuhang and Liu, Songtao and Li, Zeming and Sun, Jian},\n  journal={arXiv preprint arXiv:2007.03496},\n  year={2020}\n}\n```\n\n\n\n## Get Started\n\n1. install [cvpods](https://github.com/Megvii-BaseDetection/cvpods) following the instructions\n\n```shell\n# Install cvpods\ngit clone https://github.com/Megvii-BaseDetection/cvpods\ncd cvpods \n## build cvpods (requires GPU)\npip install -r requirements.txt\npython setup.py build develop\n## preprare data path\nmkdir datasets\nln -s /path/to/your/coco/dataset datasets/coco\n```\n\n2. run the project\n\n```shell\ncd auto_assign.res50.fpn.coco.800size.1x\n\n# train\npods_train --num-gpus 8\n\n# test\npods_test --num-gpus 8\n# test with provided weights\npods_test --num-gpus 8 MODEL.WEIGHTS /path/to/your/model.pth\n```\n\n\n\n## Results\n\n| Model | Multi-scale training | Multi-scale testing | Testing time / im | AP (minival) | Link |\n|:--- |:--------------------:|:--------------------:|:-----------------:|:-------:|:---:|\n| [AutoAssign_Res50_FPN_1x](https://github.com/poodarchu/AutoAssign/blob/master/auto_assign.res50.fpn.coco.800size.1x/config.py) | No | No | 53ms | 40.5 | [download](https://drive.google.com/file/d/11mV53SJUIpCdWj-Wbfi_fdmDz96ekb-Z/view?usp=sharing)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMegvii-BaseDetection%2FAutoAssign","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMegvii-BaseDetection%2FAutoAssign","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMegvii-BaseDetection%2FAutoAssign/lists"}