{"id":24989812,"url":"https://github.com/clementsan/object_detection_ecs","last_synced_at":"2026-04-18T00:32:02.300Z","repository":{"id":266913886,"uuid":"899742540","full_name":"clementsan/object_detection_ecs","owner":"clementsan","description":"Object detection using AWS ECS endpoint","archived":false,"fork":false,"pushed_at":"2025-01-10T23:59:02.000Z","size":209,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-23T18:38:15.767Z","etag":null,"topics":["ai","aws","aws-ecs","computer-vision","deep-learning","gradio","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/clementsan.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-12-06T23:07:20.000Z","updated_at":"2025-01-10T23:59:05.000Z","dependencies_parsed_at":"2024-12-07T00:31:14.785Z","dependency_job_id":"b8551cc6-705c-4410-b7b5-faad94cdf5fc","html_url":"https://github.com/clementsan/object_detection_ecs","commit_stats":null,"previous_names":["clementsan/object_detection_ecs"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/clementsan/object_detection_ecs","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fobject_detection_ecs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fobject_detection_ecs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fobject_detection_ecs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fobject_detection_ecs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/clementsan","download_url":"https://codeload.github.com/clementsan/object_detection_ecs/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clementsan%2Fobject_detection_ecs/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31951284,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T17:29:20.459Z","status":"ssl_error","status_checked_at":"2026-04-17T17:28:47.801Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["ai","aws","aws-ecs","computer-vision","deep-learning","gradio","object-detection"],"created_at":"2025-02-04T13:03:34.784Z","updated_at":"2026-04-18T00:32:02.272Z","avatar_url":"https://github.com/clementsan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"---\ntitle: Object Detection ECS\nemoji: 🌖\ncolorFrom: purple\ncolorTo: green\nsdk: gradio\nsdk_version: 5.5.0\napp_file: app.py\npinned: false\nshort_description: Object detection ECS\n---\n\n# Object detection via ECS endpoints\n\n[![](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![Docker Pulls](https://img.shields.io/docker/pulls/cvachet/object-detection-ecs)](https://hub.docker.com/repository/docker/cvachet/object-detection-ecs)\n\n![example workflow](https://github.com/clementsan/object_detection_ecs/actions/workflows/publish_docker_image.yml/badge.svg)\n![example workflow](https://github.com/clementsan/object_detection_ecs/actions/workflows/sync_HFSpace.yml/badge.svg)\n\n**Aim: AI-driven object detection task**\n - Front-end: user interface via Gradio library\n - Back-end: use of AWS ECS endpoints to run Machine Learning models\n\n----\n**Table of contents:**\n- [Front-end user interface](#1-front-end-user-interface)\n  - [Environment variables](#11-environment-variables)\n  - [Local execution](#12-local-execution)\n- [Back-end Machine Learning models](#2-back-end-machine-learning-models)\n  - [Information on ML models](#21-information-on-ml-models)\n  - [Deployment on AWS ECS](#22-information-on-aws-ecs-deployment)\n- [Deployment on Hugging Face](#3-deployment-on-hugging-face)\n- [Deployment on Docker Hub](#4-deployment-on-docker-hub)\n----\n\n## 1. Front-end user interface\n\n### 1.1. Environment variables\n\nThis web app uses two environment variables, corresponding to the endpoints for the deployed machine learning models\n(cf. [Section 2 - Back-end ML models](#2-back-end-ml-models))\n\nEnvironment variables:\n - AWS_DETR_URL: endpoint for DETR model\n - AWS_YOLOS_URL: endpoint for YOLOS model\n\n### 1.2. Local execution\nUse of Gradio library for web interface\n\nCommand line:\n\u003e python3 app.py\n\n**Note:** The Gradio app should now be accessible at http://localhost:7860\n\n\n\n## 2. Back-end machine learning models\n\nMachine Learning (ML) models are available on Docker Hub and have been deployed to AWS ECS (Elastic Container Service)\n\n### 2.1. Information on ML models\n**Github repos:**\n - DETR API: https://github.com/clementsan/object_detection_detr_api\n - YOLOS API: https://github.com/clementsan/object_detection_yolos_api\n\n**Docker hub containers:**\n - DETR API: https://hub.docker.com/r/cvachet/object-detection-detr-api\n - YOLOS API: https://hub.docker.com/r/cvachet/object-detection-yolos-api\n\n### 2.2 Information on AWS ECS deployment\n\nECS: Elastic Container Service\n\n\u003cdetails\u003e\n\nSteps after docker images are available on Docker Hub\n\n### Step 1. Create a new ECS task definition\n   - Task name (e.g. ObjectDetectionDETRTask)\n   - Infrastructure requirement: \n     - Launch type: ```AWS Fargate```\n     - Architecture: ```Linux/X86_64```\n     - Task size: ```0.5 CPU, 3GB memory```\n   - Container:\n     - Container name:  (e.g. ```object-detection-detr```)\n     - Image uri: point to Docker image URI (e.g. ```cvachet/object-detection-detr-api```)\n     - Port mapping: assess port number (e.g. ```port 8000, TCP protocol```)\n     \n\n### Step 2. Create a new ECS cluster\n   - Cluster name (e.g. ```ObjectDetectionCluster```)\n\n\n### Step 3. Add a new service to the cluster\n - Compute configuration\n   - Use capacity provider strategy (e.g. using Fargate or Fargate_spot)\n - Deployment configuration\n   - Application Type: Service\n   - Task Family: Select task definition family from prior instance (e.g. ```ObjectDetectionDETRTask```)\n   - Assign a Service Name: (e.g. ```object-detection-detr-api```)\n\n\n### Step 4. Update security group for new service\n - Go to Cluster -\u003e service -\u003e task -\u003e configuration and networking\n - Click on ```Security Group```\n - Adjust rules for inbound traffic (e.g. traffic only from my_ip)\n\n\u003c/details\u003e\n\n\n### 3. Deployment on Hugging Face\n\nThis web application has been deployed on Hugging Face. \n\nHF Space URL: https://huggingface.co/spaces/cvachet/object_detection_ecs\n\n\n### 4. Deployment on Docker Hub\n\nThis web application has been deployed on Docker Hub. \n\nURL: https://hub.docker.com/r/cvachet/object-detection-ecs\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclementsan%2Fobject_detection_ecs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fclementsan%2Fobject_detection_ecs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclementsan%2Fobject_detection_ecs/lists"}