{"id":15935087,"url":"https://github.com/pinto0309/tinyyolo","last_synced_at":"2025-09-13T00:33:47.162Z","repository":{"id":97173280,"uuid":"127484726","full_name":"PINTO0309/TinyYolo","owner":"PINTO0309","description":"Challenge the marginal performance of YoloV2 + Neural Compute Stick + RaspberryPi　YoloV2+Neural Compute Stick(NCS)+Raspberry Piの限界性能に挑戦","archived":false,"fork":false,"pushed_at":"2018-07-10T04:05:09.000Z","size":96082,"stargazers_count":5,"open_issues_count":1,"forks_count":2,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-10-29T08:22:47.261Z","etag":null,"topics":["cpp","deeplearning","movidius","neural-compute-stick","opencv","opengl","python","raspberrypi","tinyyolo","yolov2"],"latest_commit_sha":null,"homepage":"https://qiita.com/PINTO","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/PINTO0309.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}},"created_at":"2018-03-31T00:21:56.000Z","updated_at":"2020-01-27T19:04:28.000Z","dependencies_parsed_at":"2023-03-30T07:39:24.860Z","dependency_job_id":null,"html_url":"https://github.com/PINTO0309/TinyYolo","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/PINTO0309/TinyYolo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PINTO0309%2FTinyYolo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PINTO0309%2FTinyYolo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PINTO0309%2FTinyYolo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PINTO0309%2FTinyYolo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PINTO0309","download_url":"https://codeload.github.com/PINTO0309/TinyYolo/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PINTO0309%2FTinyYolo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274902082,"owners_count":25371071,"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":"2025-09-12T02:00:09.324Z","response_time":60,"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":["cpp","deeplearning","movidius","neural-compute-stick","opencv","opengl","python","raspberrypi","tinyyolo","yolov2"],"created_at":"2024-10-07T03:22:44.418Z","updated_at":"2025-09-13T00:33:47.135Z","avatar_url":"https://github.com/PINTO0309.png","language":"Python","readme":"# [Japanese] TinyYolo\nYoloV2+Neural Compute Stick(NCS)+Raspberry Piの限界性能に挑戦　Challenge the marginal performance of YoloV2 + Neural Compute Stick + Raspberry Pi\n\nhttps://qiita.com/PINTO/items/db3ab44a3e2bcd87f2d8\n\n# 動作イメージ\nTinyYolo + Neural Compute Stick + RaspberryPi3\n\nYoutube: https://youtu.be/L4RvVLyo8Rc\n\n![Riders](https://github.com/PINTO0309/TinyYolo/blob/master/media/Riders.gif)  ![MultiStick](https://github.com/PINTO0309/MobileNet-SSD/blob/master/media/MultiStick.jpeg)\n# 環境\n・RaspberryPi 3 + Raspbian Stretch\n\n・NCSDK v1.12.00\n\n・Intel Movidius Neural Compute Stick　１本\n\n・OpenCV 3.4.1\n\n・OpenGL\n\n・numpy\n\n・UVC対応のUSB-Webカメラ\n\n\n# 環境構築\n1. SWAP領域の一時的な拡張\n```\n$ sudo nano /etc/dphys-swapfile\nCONF_SWAPSIZE=2048\n\n$ sudo /etc/init.d/dphys-swapfile restart swapon -s\n```\n2. パッケージのインストール\n```\n$ sudo apt-get update\n$ sudo apt-get upgrade\n$ sudo apt-get install python3-pip python3-numpy git cmake\n```\n3. NCSDKのインストール\n```\n$ cd ~\n$ git clone https://github.com/movidius/ncsdk.git\n$ cd ncsdk\n$ make install\n```\n4. OpenCVのインストール\n```\n$ wget https://github.com/PINTO0309/OpenCVonARMv7/blob/master/libopencv3_3.4.1-20180304.1_armhf.deb\n$ sudo apt install -y ./libopencv3_3.4.1-20180304.1_armhf.deb\n$ sudo ldconfig\n```\n5. OpenGLのインストール\n```\n$ sudo apt-get install python-opengl\n$ sudo -H pip3 install pyopengl\n$ sudo -H pip3 install pyopengl_accelerate\n$ sudo raspi-config\n```\n6. 「7.Advanced Options」-「A7 GL Driver」-「G2 GL (Fake KMS)」の順に選択し、Raspberry Pi のOpenGL Driver を有効化\n\n7. 再起動\n```\n$ sudo reboot\n```\n8. リソース一式のダウンロード\n```\n$ cd ~\n$ git clone https://github.com/PINTO0309/TinyYolo.git\n```\n9. USB-WEBカメラ(UVC対応) と Neural Compute Stick をRaspberryPiのUSBポートへ接続(Neural Compute Stickをマルチで使用する場合は電圧が不足するためセルフパワーUSB-Hub必須)\n\n10. RaspberryPiとディスプレイをHDMIケーブルで接続\n\n11. MultiStick.pyの実行\n```\n$ cd TinyYolo\n$ python3 ./detectionExample/MultiStick.py\n```\n12. SWAP領域の縮小\n```\n$ sudo nano /etc/dphys-swapfile\nCONF_SWAPSIZE=100\n\n$ sudo /etc/init.d/dphys-swapfile restart swapon -s\n```\n\n　\n　\n \n# [English] TinyYolo\nChallenge the marginal performance of YoloV2 + Neural Compute Stick + Raspberry Pi\n\nhttps://qiita.com/PINTO/items/db3ab44a3e2bcd87f2d8\n\n# Image of motion\nTinyYolo + Neural Compute Stick + RaspberryPi3\n\nYoutube: https://youtu.be/L4RvVLyo8Rc\n\n![Riders](https://github.com/PINTO0309/TinyYolo/blob/master/media/Riders.gif)  ![MultiStick](https://github.com/PINTO0309/MobileNet-SSD/blob/master/media/MultiStick.jpeg)\n# Environment\n・RaspberryPi 3 + Raspbian Stretch\n\n・NCSDK v1.12.00\n\n・Intel Movidius Neural Compute Stick　１本\n\n・OpenCV 3.4.1\n\n・OpenGL\n\n・numpy\n\n・(UVC)USB-Web Camera\n\n\n# Building environment\n1. Temporary extension of SWAP area\n```\n$ sudo nano /etc/dphys-swapfile\nCONF_SWAPSIZE=2048\n\n$ sudo /etc/init.d/dphys-swapfile restart swapon -s\n```\n2. Installing packages\n```\n$ sudo apt-get update\n$ sudo apt-get upgrade\n$ sudo apt-get install python3-pip python3-numpy git cmake\n```\n3. Installing NCSDK\n```\n$ cd ~\n$ git clone https://github.com/movidius/ncsdk.git\n$ cd ncsdk\n$ make install\n```\n4. Installation of OpenCV\n```\n$ wget https://github.com/PINTO0309/OpenCVonARMv7/blob/master/libopencv3_3.4.1-20180304.1_armhf.deb\n$ sudo apt install -y ./libopencv3_3.4.1-20180304.1_armhf.deb\n$ sudo ldconfig\n```\n5. Installing OpenGL\n```\n$ sudo apt-get install python-opengl\n$ sudo -H pip3 install pyopengl\n$ sudo -H pip3 install pyopengl_accelerate\n$ sudo raspi-config\n```\n6. 「7.Advanced Options」-「A7 GL Driver」-「G2 GL (Fake KMS)」 and Activate Raspberry Pi's OpenGL Driver\n\n7. Reboot\n```\n$ sudo reboot\n```\n8. Download complete set of resources\n```\n$ cd ~\n$ git clone https://github.com/PINTO0309/TinyYolo.git\n```\n9. Connect USB-WEB camera (UVC compatible) and Neural Compute Stick to RaspberryPi's USB port (self power USB-Hub required due to insufficient voltage when using Neural Compute Stick in multiple)\n\n10. Connect RaspberryPi and display with HDMI cable\n\n11. Running MultiStick.py\n```\n$ cd TinyYolo\n$ python3 ./detectionExample/MultiStick.py\n```\n12. Reducing the SWAP area\n```\n$ sudo nano /etc/dphys-swapfile\nCONF_SWAPSIZE=100\n\n$ sudo /etc/init.d/dphys-swapfile restart swapon -s\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpinto0309%2Ftinyyolo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpinto0309%2Ftinyyolo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpinto0309%2Ftinyyolo/lists"}