{"id":24446296,"url":"https://github.com/kentaroy47/efficientdet.pytorch","last_synced_at":"2025-10-10T08:30:36.638Z","repository":{"id":104244226,"uuid":"223834146","full_name":"kentaroy47/efficientdet.pytorch","owner":"kentaroy47","description":":neckbeard:Unofficial implementation of EfficientDet","archived":false,"fork":false,"pushed_at":"2020-03-11T08:30:50.000Z","size":46515,"stargazers_count":63,"open_issues_count":7,"forks_count":16,"subscribers_count":7,"default_branch":"master","last_synced_at":"2025-04-03T18:09:02.971Z","etag":null,"topics":["apex","efficientdet","pytorch","retinanet","ssd"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/kentaroy47.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":"2019-11-25T00:57:28.000Z","updated_at":"2024-12-02T03:44:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"fbc0e2d9-b77b-4fb1-abfd-a922b58cd2da","html_url":"https://github.com/kentaroy47/efficientdet.pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kentaroy47/efficientdet.pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentaroy47%2Fefficientdet.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentaroy47%2Fefficientdet.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentaroy47%2Fefficientdet.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentaroy47%2Fefficientdet.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kentaroy47","download_url":"https://codeload.github.com/kentaroy47/efficientdet.pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentaroy47%2Fefficientdet.pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279003299,"owners_count":26083555,"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","status":"online","status_checked_at":"2025-10-10T02:00:06.843Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["apex","efficientdet","pytorch","retinanet","ssd"],"created_at":"2025-01-20T23:51:12.410Z","updated_at":"2025-10-10T08:30:36.017Z","avatar_url":"https://github.com/kentaroy47.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"Now training models..\n\n|*backbone*              |*resolution*|*VOCmAP*    |*COCOmAP*|*Inference[ms]*|*model*|\n|:------:                |:------------:|:----------:|:-------:|:-------------:|:-----:|\n|EfficientnetB0(wo/BiFPN)|512      |77.0       |TBD         |               |       |\n|EfficientnetB0(w/BiFPN) |512      |77.2       |TBD         |               |       |\n|EfficientnetB2(wo/BiFPN)|768      |TBD       |TBD         |               |       |\n|EfficientnetB2(w/BiFPN) |768      |TBD       |TBD         |               |       |\n|EfficientnetB4(wo/BiFPN)|1024      |TBD       |TBD         |               |       |\n|EfficientnetB4(w/BiFPN) |1024      |TBD       |TBD         |               |       |\n|EfficientnetB6(wo/BiFPN)|1408      |TBD       |TBD         |               |       |\n|EfficientnetB6(w/BiFPN) |1408      |TBD       |TBD         |               |       |\n\n# efficientdet.pytorch\nunofficial implementation of efficientdet\n\n- supported efficientnet backbone (B0 for now)\n- supported resnet backbone.\n- supports BiFPN.\n- supports VOC and COCO training.\n\n## requirements\n`pip install --upgrade efficientnet-pytorch`\n\n## PASCAL-VOC training\n- see `train_efficientdet.ipynb`\n- see `eval.ipynb` for evaluation\n\n## COCO training\n- see `train_efficientdet.ipynb` and configure MS-COCO dataset.\n\n## FP16 training\n- see `train_fp16_apex.ipynb`\n\n![configs](https://miro.medium.com/max/678/1*hGTQY4XHbAtPch7nLEp12g.png)\n\n![perf](https://miro.medium.com/max/1922/1*QVVzgKBg7P4nbKHcnO1uKQ.png)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkentaroy47%2Fefficientdet.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkentaroy47%2Fefficientdet.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkentaroy47%2Fefficientdet.pytorch/lists"}