{"data":{"slug":"bmw-innovationlab-bmw-yolov4-inference-api-gpu","name":"BMW-YOLOv4-Inference-API-GPU","tagline":"nocode object detection inference API using Yolov3 and Yolov4 Darknet framework","github_url":"https://github.com/BMW-InnovationLab/BMW-YOLOv4-Inference-API-GPU","owner":"BMW-InnovationLab","repo":"BMW-YOLOv4-Inference-API-GPU","owner_avatar_url":"https://avatars.githubusercontent.com/u/58600135?v=4","primary_language":"Python","stars":274,"forks":68,"topics":["alexeyab-darknet","api","bounding-boxes","computer-vision","deep-learning","deeplearning","detection-inference-api","docker","dockerfile","gpu","inference","inference-gui","inference-server","neural-network","no-code","rest-api","yolo","yolo-gui","yolov3","yolov4"],"archived":false,"github_pushed_at":"2022-06-28T13:28:08+00:00","maintenance_label":"Dormant","stars_delta_30d":-2,"url":"https://www.graphcanon.com/tools/bmw-innovationlab-bmw-yolov4-inference-api-gpu","markdown_url":"https://www.graphcanon.com/tools/bmw-innovationlab-bmw-yolov4-inference-api-gpu.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bmw-innovationlab-bmw-yolov4-inference-api-gpu","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bmw-innovationlab-bmw-yolov4-inference-api-gpu","description":"This is a repository for an nocode object detection inference API using the Yolov3 and Yolov4 Darknet framework.","homepage_url":null,"license":"BSD-3-Clause","open_issues":0,"watchers":16,"ai_summary":"Supplies an nocode object detection service with support for both YOLOv3 and YOLOv4, built on the Darknet framework. Optimized for deployment via Docker containers, allowing inference execution on GPU.","readme_excerpt":"### Install prerequisites\n\nUse the following command to install docker on Ubuntu:\n\n```sh\nchmod +x install_prerequisites.sh && source install_prerequisites.sh\n```\n\nInstall NVIDIA Drivers (410.x or higher) and NVIDIA Docker for GPU by following the [official docs](https://github.com/nvidia/nvidia-docker/wiki/Installation-(version-2.0))\n\n---\n\n## Build The Docker Image\n\nIn order to build the project run the following command from the project's root directory:\n\n```sh\nsudo docker build -t yolov4_inference_api_gpu -f ./docker/dockerfile .\n```\n\n---\n\n## Run The Docker Container\n\nAs mentioned before, this container can be deployed using either **docker** or **docker swarm**.\n\nIf you wish to deploy this API using **docker**, please issue the following run command.\n\nIf you wish to deploy this API using **docker swarm**, please refer to following link [docker swarm documentation](./README-docker_swarm.md). After deploying the API with docker swarm, please consider returning to this documentation for further information about the API endpoints as well as the model structure sections.\n\nTo run the API, go the to the API's directory and run the following:\n\n#### Using Linux based docker:\n\n```sh\nsudo NV_GPU=0 nvidia-docker run -itv $(pwd)/models:/models -v $(pwd)/models_hash:/models_hash -p <docker_host_port>:1234 yolov4_inference_api_gpu\n```\nThe <docker_host_port> can be any unique port of your choice.\n\nThe API file will be run automatically, and the service will listen to http requests on the chosen port.\n\nNV_GPU defines on which GPU you want the API to run. If you want the API to run on multiple GPUs just enter multiple numbers seperated by a comma: (NV_GPU=0,1 for example)","github_created_at":"2019-12-11T17:42:18+00:00","created_at":"2026-07-15T11:19:46.727798+00:00","updated_at":"2026-09-20T05:20:16.902507+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"darknet","name":"darknet"},{"slug":"docker-container","name":"docker-container"},{"slug":"gpu-support","name":"gpu-support"},{"slug":"inference-api","name":"inference-api"},{"slug":"no-code","name":"no-code"},{"slug":"object-detection","name":"object-detection"},{"slug":"yolo-v3-and-yolo-v4","name":"yolo-v3-and-yolo-v4"}],"trust":{"provenance":{"is_fork":false,"github_id":227425343,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:20:14.159Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1544,"last_release_at":"2019-12-11T18:27:01Z","stars_delta_30d":-2,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:19:48.874Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:20:15.176Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T05:20:15.176Z"},"license_spdx":{"value":"BSD-3-Clause","source":"github.license","observed_at":"2026-09-20T05:20:15.176Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to deploy a no-code object detection API leveraging both YOLOv3 and YOLOv4 frameworks, and require high-performance inference with GPU support through Docker containerization.","If your project requires the flexibility of deploying on either Docker or Docker Swarm, this tool is optimized for such scenarios."],"when_not_to_use":["Avoid using BMW-YOLOv4-Inference-API-GPU if you need to perform inference without a GPU setup since it specifically leverages NVIDIA GPU drivers and does not provide native support for other hardware.","Do not use this tool when needing multi-platform deployment out of the box, as the no-code interface and documentation focus primarily on Linux systems with Docker."],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:49:44.531Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"BMW-YOLOv4-Inference-API-GPU offers no-code object detection services with support for YOLOv3 and YOLOv4 on the Darknet framework, optimized for deployment via Docker containers and GPU execution."}]}}