{"id":18790535,"url":"https://github.com/ely-s/efficientdetjs","last_synced_at":"2025-04-13T14:14:03.830Z","repository":{"id":38536075,"uuid":"231663404","full_name":"Ely-S/EfficientDetJS","owner":"Ely-S","description":"Port of the EfficientDet neural network architecture to the web.","archived":false,"fork":false,"pushed_at":"2023-01-06T16:11:25.000Z","size":129175,"stargazers_count":4,"open_issues_count":26,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-13T14:13:11.415Z","etag":null,"topics":["ai","cv","tensorflow"],"latest_commit_sha":null,"homepage":"https://ondaka.github.io/EfficientDetJS/index.html","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ely-S.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-01-03T20:52:11.000Z","updated_at":"2024-11-18T13:56:04.000Z","dependencies_parsed_at":"2023-02-06T06:31:21.054Z","dependency_job_id":null,"html_url":"https://github.com/Ely-S/EfficientDetJS","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/Ely-S%2FEfficientDetJS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ely-S%2FEfficientDetJS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ely-S%2FEfficientDetJS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ely-S%2FEfficientDetJS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ely-S","download_url":"https://codeload.github.com/Ely-S/EfficientDetJS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248724629,"owners_count":21151561,"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":["ai","cv","tensorflow"],"created_at":"2024-11-07T21:12:38.949Z","updated_at":"2025-04-13T14:14:03.804Z","avatar_url":"https://github.com/Ely-S.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"### EfficientDetJs\n\nThis library lets you easily deploy a State-of-the-Art EfficientDet model to a tensorflow.js runtime. EfficientDet is a fast, very powerful neural architecture with an active open source [implementation](https://github.com/google/automl) making it a good base for new projects. This library allows you to use a pretrained or custom EfficientDet model without messing with tensorflow.js yourself.\n\n[See a live demo](https://ondaka.github.io/EfficientDetJS/example/dist/).\n\n## Getting Started\n\n    import EfficientDet from \"EfficientDetJS\"\n    \n    const model = new EfficientDet()\n\n    // load the model from tf hub\n    await model.load()\n\n    // get an array of object bounding boxes\n    // .predict accepts a a Tensor3D of an image.\n    const predictions = model.predict(image)\n\n    // draw boxes on canvas\n    model.draw(predictions, document.getElementById(\"mycanvas))\n\n### Pretrained checkpoint\n\nThe pretraiend checkpoint, efficientdet-d0 is trained on a 90 class COCO challange. It is hosted here on tensorflow hub\n\n### Custom checkpoints\n\nFor custom efficientdet models, refer to the Dockerfile for details on how to export your own model from EfficientDet\n\n###  Building the typescript\n\n    yarn build\n\n#### Building the model\n\nThere is a Dockerfile in hub/ that will build an image containing an EfficientDet model and convert it to the tensorflow.js format\n\n    cd hub\n    docker build -t efficientdet-model-d0 .\n    \n    # Or to build a different moodel size\n    # docker build --build-arg SIZE=d1 -t efficientdet-model-d0 .\n\n    # Copy exported model files into current directory\n    docker run -v (pwd):/out efficientdet-model-d0  cp -r /tmp/efficientdet-d0.js /out/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fely-s%2Fefficientdetjs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fely-s%2Fefficientdetjs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fely-s%2Fefficientdetjs/lists"}