{"id":26693798,"url":"https://github.com/alwaysai/yolov4-object-detector","last_synced_at":"2025-08-30T12:42:51.893Z","repository":{"id":230254474,"uuid":"778904469","full_name":"alwaysai/yolov4-object-detector","owner":"alwaysai","description":"Yolov4 ONNX Object Detector","archived":false,"fork":false,"pushed_at":"2024-04-08T13:24:21.000Z","size":11,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-26T18:34:54.185Z","etag":null,"topics":["ai","alwaysai","chooch-ai","computer-vision","nvidia-gpu","object-detection","onnx-models","roboflow","vision","vision-ai","yolov4"],"latest_commit_sha":null,"homepage":"","language":"Python","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/alwaysai.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":"2024-03-28T16:31:38.000Z","updated_at":"2024-04-08T15:17:43.000Z","dependencies_parsed_at":"2025-03-26T18:43:47.716Z","dependency_job_id":null,"html_url":"https://github.com/alwaysai/yolov4-object-detector","commit_stats":null,"previous_names":["alwaysai/yolov4-object-detector"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alwaysai/yolov4-object-detector","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alwaysai%2Fyolov4-object-detector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alwaysai%2Fyolov4-object-detector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alwaysai%2Fyolov4-object-detector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alwaysai%2Fyolov4-object-detector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alwaysai","download_url":"https://codeload.github.com/alwaysai/yolov4-object-detector/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alwaysai%2Fyolov4-object-detector/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272852288,"owners_count":25004054,"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":"2025-08-30T02:00:09.474Z","response_time":77,"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":["ai","alwaysai","chooch-ai","computer-vision","nvidia-gpu","object-detection","onnx-models","roboflow","vision","vision-ai","yolov4"],"created_at":"2025-03-26T18:27:19.694Z","updated_at":"2025-08-30T12:42:51.864Z","avatar_url":"https://github.com/alwaysai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Yolov4 ONNX Object Detector\nThis repo contains a YOLOv4 ONNX reference application script that switches seamlessly between CPU and GPU inferencing. The script uses a YOLOv4 ONNX model created from the coco dataset and can be found in alwaysAI's model catalog. Script works with IP cameras.  To run simply add your ip camera's address as part of command line arguments when starting the application:\n```\naai app start -- --camera-url rtsp://acme:user@100.70.31.147/live\n```\nThis script uses either alwaysAI's ONNX runtime for CPU inferencing  ```engine=edgeiq.Engine.ONNX_RT``` or TENSORRT runtime ```engine=edgeiq.Engine.TENSOR_RT``` for GPU inferencing.  Adjust the script in ```app.py``` to met your inferencing needs.  The YOLOv4 architecture is computationally heavy so if your application requires realtime performance use the TENSORRT engine.\n\n### alwaysAI inference engine information\n\n## Requirements\n* [alwaysAI account](https://alwaysai.co/auth?register=true)\n* [alwaysAI Development Tools](https://alwaysai.co/docs/get_started/development_computer_setup.html)\n\n## Usage\nOnce the alwaysAI tools are installed on your development machine (or edge device if developing directly on it) you can install and run the app with the following CLI commands:\n\nTo perform initial configuration of the app:\n```\naai app configure\n```\nAdd model to the app:\n```\naai app models add alwaysai/yolov4-onnx\n```\nTo prepare the runtime environment and install app dependencies:\n```\naai app install\n```\n\nTo start the app (customize to your camera url):\n```\naai app start -- --camera-url rtsp://acme:user@100.70.31.147/live\n```\nTo change the computer vision model, the engine and accelerator, and add additional dependencies read [this guide](https://alwaysai.co/docs/application_development/configuration_and_packaging.html).\n\n### NIVIDA x86 GTX 1650 GPU Usage Information\nalwaysAI also supports inferencing on GeForce 1650 GPU's for x86 devices.  To perform initial configuration of the app:\n```\naai app configure --hardware x86-trt-23.02\n```\nSet ```ALWAYSAI_HW to x86-trt-23.02 in your Dockerfile```\nThen follow the Usage instructions starting with the ```aai add models``` command.\n\n## Support\n* [Documentation](https://alwaysai.co/docs/)\n* [Community Discord](https://discord.gg/alwaysai)\n* Email: support@alwaysai.co\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falwaysai%2Fyolov4-object-detector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falwaysai%2Fyolov4-object-detector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falwaysai%2Fyolov4-object-detector/lists"}