{"id":13415355,"url":"https://github.com/Megvii-BaseDetection/BorderDet","last_synced_at":"2025-03-14T22:33:20.074Z","repository":{"id":56011817,"uuid":"281337927","full_name":"Megvii-BaseDetection/BorderDet","owner":"Megvii-BaseDetection","description":"BorderDet: Border Feature for Dense Object Detection(ECCV2020 Oral)","archived":false,"fork":false,"pushed_at":"2021-03-25T12:57:04.000Z","size":894,"stargazers_count":430,"open_issues_count":6,"forks_count":63,"subscribers_count":19,"default_branch":"master","last_synced_at":"2024-07-31T21:53:43.055Z","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/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":"2020-07-21T08:17:08.000Z","updated_at":"2024-07-30T09:58:45.000Z","dependencies_parsed_at":"2022-08-15T11:20:45.205Z","dependency_job_id":null,"html_url":"https://github.com/Megvii-BaseDetection/BorderDet","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%2FBorderDet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Megvii-BaseDetection%2FBorderDet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Megvii-BaseDetection%2FBorderDet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Megvii-BaseDetection%2FBorderDet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Megvii-BaseDetection","download_url":"https://codeload.github.com/Megvii-BaseDetection/BorderDet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243658058,"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":[],"created_at":"2024-07-30T21:00:47.533Z","updated_at":"2025-03-14T22:33:20.069Z","avatar_url":"https://github.com/Megvii-BaseDetection.png","language":"Python","readme":"# BorderDet\n\nThis project provides an implementation for \"BorderDet: Border Feature for Dense Object Detection\" (*ECCV2020 Oral*) on PyTorch.\n\nFor the reason that experiments in the paper were conducted using internal framework, this project reimplements them on cvpods and reports detailed comparisons below.\n\n\u003ccenter\u003e\u003cimg src=\"./playground/detection/coco/borderdet/intro/borderdet.png\" width=\"700\" align=\"middle\"/\u003e\u003c/center\u003e\n\n## Requirements\n* [cvpods](https://github.com/Megvii-BaseDetection/cvpods)\n\n\n## Get Started\n\n* install cvpods locally (requires cuda to compile)\n```shell\n\npython3 -m pip install 'git+https://github.com/Megvii-BaseDetection/cvpods.git'\n# (add --user if you don't have permission)\n\n# Or, to install it from a local clone:\ngit clone https://github.com/Megvii-BaseDetection/cvpods.git\npython3 -m pip install -e cvpods\n\n# Or,\npip install -r requirements.txt\npython3 setup.py build develop\n```\n\n* prepare datasets\n```shell\ncd /path/to/cvpods\ncd datasets\nln -s /path/to/your/coco/dataset coco\n```\n\n* Train \u0026 Test\n```shell\ngit clone https://github.com/Megvii-BaseDetection/BorderDet.git\ncd BorderDet/playground/detection/coco/borderdet/borderdet.res50.fpn.coco.800size.1x  # for example\n```\n\n# Train\n```shell\npods_train --num-gpus 8\n```\n\n# Test\n```shell\npods_test --num-gpus 8 \\\n    MODEL.WEIGHTS /path/to/your/save_dir/ckpt.pth # optional\n    OUTPUT_DIR /path/to/your/save_dir # optional\n```\n\n# Multi node training\n## sudo apt install net-tools ifconfig\n```shell\npods_train --num-gpus 8 --num-machines N --machine-rank 0/1/.../N-1 --dist-url \"tcp://MASTER_IP:port\"\n```\n\n\n## Results on COCO\nFor your convenience, we provide the performance of the following trained models. All models are trained with 16 images in a mini-batch and frozen batch normalization. All model including X_101/DCN_X_101 will be released soon.\n\n| Model | Multi-scale training | Multi-scale testing | Testing time / im | AP (minival) | Link |\n|:--- |:--------------------:|:--------------------:|:-----------------:|:-------:|:---:|\n| [FCOS_R_50_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/fcos/fcos.res50.fpn.coco.800size.1x) | No | No | 54ms | 38.7 | [download](https://drive.google.com/file/d/1hcDobxvqolMwqj20BEAPikSMcz4NYZRx/view?usp=sharing)\n| [BD_R_50_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/borderdet/borderdet.res50.fpn.coco.800size.1x) | No | No | 60ms | 41.4 | [download](https://drive.google.com/file/d/1nhGA0TYtwGp_RMwPoZDAPbZ_TNL8-XCj/view?usp=sharing)\n| [BD_R_101_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/borderdet/borderdet.res101.fpn.coco.800size.2x) | Yes | No | 76ms | 45.0 | [download](https://drive.google.com/file/d/1LEbLZwP_9eKbpZXC52D5B_V85A4pr9eE/view?usp=sharing)\n| [BD_X_101_32x8d_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/borderdet/borderdet.x101.32x8d.fpn.coco.800size.2x) | Yes | No | 124ms | 45.6 | [download](https://drive.google.com/file/d/1Cd5xJCVdb1RPE1VAFAzCBXyLxcH315-f/view?usp=sharing)\n| [BD_X_101_64x4d_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/borderdet/borderdet.x101.64x4d.fpn.coco.800size.2x) | Yes | No | 123ms | 46.2 | [download](https://drive.google.com/file/d/15UH3PPQONv4nhHIDQGll0iHnuhmqwbAp/view?usp=sharing)\n| [BD_DCNV2_X_101_32x8d_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/borderdet/borderdet.dcnv2.x101.32x8d.fpn.coco.800size.2x) | Yes | No | 150ms | 47.9 | [download](https://drive.google.com/file/d/1xGnomS2rn2rayMrPxE_hpzbUQxMJ-eCN/view?usp=sharing)\n| [BD_DCNV2_X_101_64x4d_FPN_1x](https://github.com/Megvii-BaseDetection/BorderDet/blob/master/playground/detection/coco/borderdet/borderdet.dcnv2.x101.64x4d.fpn.coco.800size.2x) | Yes | No | 156ms | 47.5 | [download](https://drive.google.com/file/d/1R6a7CzwHu8iXSENZXNrWXVwaAaV-oB5_/view?usp=sharing)\n\n\n\n## Acknowledgement\ncvpods is developed based on Detectron2. For more details about official detectron2, please check [DETECTRON2](https://github.com/facebookresearch/detectron2/blob/master/README.md).\n\n\n## Contributing to the project\nAny pull requests or issues are welcome.","funding_links":[],"categories":["Frameworks"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMegvii-BaseDetection%2FBorderDet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMegvii-BaseDetection%2FBorderDet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMegvii-BaseDetection%2FBorderDet/lists"}