{"id":21802458,"url":"https://github.com/qengineering/rock-5-image","last_synced_at":"2025-10-26T22:47:15.463Z","repository":{"id":237277749,"uuid":"624339542","full_name":"Qengineering/Rock-5-image","owner":"Qengineering","description":"Rock Pi 5 image with OpenCV, deep learning frameworks and NPU drivers","archived":false,"fork":false,"pushed_at":"2024-04-30T16:16:38.000Z","size":14,"stargazers_count":6,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-13T18:55:12.024Z","etag":null,"topics":["debian11","ncnn","npu","opencv","rknpu2","rock-pi-5","tnn"],"latest_commit_sha":null,"homepage":"https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Qengineering.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":"2023-04-06T08:51:36.000Z","updated_at":"2025-01-30T06:14:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"7c8a4265-ea48-422c-822e-5cd84a379c31","html_url":"https://github.com/Qengineering/Rock-5-image","commit_stats":null,"previous_names":["qengineering/rock-5-image"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Qengineering/Rock-5-image","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qengineering%2FRock-5-image","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qengineering%2FRock-5-image/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qengineering%2FRock-5-image/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qengineering%2FRock-5-image/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Qengineering","download_url":"https://codeload.github.com/Qengineering/Rock-5-image/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qengineering%2FRock-5-image/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281185449,"owners_count":26457747,"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":"2025-10-26T02:00:06.575Z","response_time":61,"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":["debian11","ncnn","npu","opencv","rknpu2","rock-pi-5","tnn"],"created_at":"2024-11-27T11:28:48.693Z","updated_at":"2025-10-26T22:47:15.447Z","avatar_url":"https://github.com/Qengineering.png","language":null,"funding_links":["https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick\u0026hosted_button_id=CPZTM5BB3FCYL"],"categories":[],"sub_categories":[],"readme":"# Rock 5 image\n![output image]( https://qengineering.eu/github/SDcard32GB_RockPi5_Large.webp)\u003cbr/\u003e\n## A Rock 5 image with OpenCV, ncnn, TNN and NPU\n[![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)\u003cbr/\u003e\u003cbr/\u003e\n\n------------\n\n## Installation.\n\n- Get a 32 GB (minimal) SD card holding the image. \n- Download the `RockPi5.img.xz` image (2.8 GByte) from our [Sync](https://ln5.sync.com/dl/b9c189080/csvcycve-qn6f2zt8-49z54nm6-m9gvzbf3) site. \n- Flash the image on the SD card with the [Imager](https://www.raspberrypi.org/software/) or [balenaEtcher](https://www.balena.io/etcher/).\n- Insert the SD card in your Rock 5 and enjoy.\n- Username: ***rock***\n- no password \n\n------------\n\n## Model performance benchmark(FPS)\n\nAll models, with C++ examples, can be found on the SD image.\u003cbr\u003e\n\n| demo             | model_name                   | inputs_shape            | dtype | Rock 5        |\n| ---------------- | ---------------------------- | ----------------------- | ----- | ------------- |\n| yolov5           | yolov5s_relu                 | [1, 3, 640, 640]        | INT8  | 50.0          |\n|                  | yolov5n                      | [1, 3, 640, 640]        | INT8  | 58.8          |\n|                  | yolov5s                      | [1, 3, 640, 640]        | INT8  | 37.7          |\n|                  | yolov5m                      | [1, 3, 640, 640]        | INT8  | 16.2          |\n| yolov6           | yolov6n                      | [1, 3, 640, 640]        | INT8  | 63.0          |\n|                  | yolov6s                      | [1, 3, 640, 640]        | INT8  | 29.5          |\n|                  | yolov6m                      | [1, 3, 640, 640]        | INT8  | 15.4          |\n| yolov7           | yolov7-tiny                  | [1, 3, 640, 640]        | INT8  | 53.4          |\n|                  | yolov7                       | [1, 3, 640, 640]        | INT8  | 9.4           |\n| yolov8           | yolov8n                      | [1, 3, 640, 640]        | INT8  | 53.1          |\n|                  | yolov8s                      | [1, 3, 640, 640]        | INT8  | 28.5          |\n|                  | yolov8m                      | [1, 3, 640, 640]        | INT8  | 12.1          |\n| yolox            | yolox_s                      | [1, 3, 640, 640]        | INT8  | 30.0          |\n|                  | yolox_m                      | [1, 3, 640, 640]        | INT8  | 12.9          |\n| ppyoloe          | ppyoloe_s                    | [1, 3, 640, 640]        | INT8  | 28.8          |\n|                  | ppyoloe_m                    | [1, 3, 640, 640]        | INT8  | 13.1          |\n| yolov5_seg       | yolov5n-seg                  | [1, 3, 640, 640]        | INT8  | 9.4           |\n|                  | yolov5s-seg                  | [1, 3, 640, 640]        | INT8  | 7.8           |\n|                  | yolov5m-seg                  | [1, 3, 640, 640]        | INT8  | 6.1           |\n| yolov8_seg       | yolov8n-seg                  | [1, 3, 640, 640]        | INT8  | 8.9           |\n|                  | yolov8s-seg                  | [1, 3, 640, 640]        | INT8  | 7.3           |\n|                  | yolov8m-seg                  | [1, 3, 640, 640]        | INT8  | 4.5           |\n| ppseg\t           | ppseg_lite_1024x512          |\t[1, 3, 512, 512]\t      | INT8\t| 27.5          |\n| RetinaFace       | RetinaFace_mobile320         | [1, 3, 320, 320]        | INT8  | 243.6         |\n|                  | RetinaFace_resnet50_320      | [1, 3, 320, 320]        | INT8  | 43.4          |\n| PPOCR-Det        | ppocrv4_det                  | [1, 3, 480, 480]        | INT8  | 31.5          |\n| PPOCR-Rec        | ppocrv4_rec                  | [1, 3, 48, 320]         | FP16  | 35.7          |\n\n* Due to the pixel-wise filling and drawing, segmentation models are relatively slow\n\n------------\n\n## Tips.\n\n* If you need extra space delete the opencv and the opencv_contrib folder from the SD card. They are no longer needed since all libraries are stored in the /usr/ directory.\n* Use a tool like [GParted](https://gparted.org/) `sudo apt-get install gparted` to expand the image to larger SD cards. We recommend a minimum of 64 GB. Deep learning requires a lot of space.\u003cbr/\u003e\n* An example of YoloV5 running on the NPU (25 FPS) is included.\n\n------------\n\n## Pre-installed frameworks.\n\n- [OpenCV](https://qengineering.eu/deep-learning-with-opencv-on-raspberry-pi-4.html) 4.9.0\n- [ncnn](https://qengineering.eu/install-ncnn-on-raspberry-pi-4.html) 20240410\n- NPU [rknpu2](https://github.com/airockchip/rknn-toolkit2/tree/master/rknpu2) 1.5.2\n- NPU [model zoo](https://github.com/airockchip/rknn_model_zoo) 2.0.0\n- NPU [model zoo models](https://github.com/Qengineering/rknn_model_zoo) 2.0.0\n- [TeamViewer aarch64](https://www.teamviewer.com/en/download/linux/) 15.24.5\n\n------------\n\n### Thanks.\nA more than special thanks to [***Stuart Naylor***](https://forum.radxa.com/u/stuartiannaylor/summary), who, ever so kindly, provided us the Rock Pi 5 for free.\n\n------------\n\n![output image]( https://qengineering.eu/github/RockPi5.webp )\u003cbr/\u003e\u003cbr/\u003e\n\n------------\n\n[![paypal](https://qengineering.eu/images/TipJarSmall4.png)](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick\u0026hosted_button_id=CPZTM5BB3FCYL) \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqengineering%2Frock-5-image","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqengineering%2Frock-5-image","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqengineering%2Frock-5-image/lists"}