跳到主要內容

Intel’s Movidius Neural Compute Stick Supports Raspberry Pi 3 Board

Intel’s Movidius Neural Compute Stick Supports Raspberry Pi 3 Board

August 2nd, 2017Leave a commentGo to comments
Orange Pi Development Boards
Last month, Intel introduced Movidius Neural Computer Stick to accelerate applications such as object recognition, and do so offline, i.e. without the cloud, and at low power. While there was not that much information available at the time, the minimal requirements for the host machine were that it had to be a x86_64 computer running Ubuntu 16.04, and come with at least 1GB RAM, and 4GB storage.
So I understood the stick would only work attached with 64-bit Intel or AMD processors, and ARM development boards would not be an option. But today, I’ve found that Movidius had uploaded a new video showing a Python based object recognition demo with the Neural Compute Stick connected to the the Raspberry Pi 3 board. You just need to add a USB camera, copy ncapi directory from the SDK installed on your Ubuntu 16.04 development machine to the Debian Jessie installed on RPi 3 board, install the relevant .deb packages from that directory, and as well as some required packages (e.g. Gstreamer), and run one of the demos such as stream_infer as explained in the video.
Since all computing is supposed to happen in the stick, I’d assume this should work on other ARM development board with Debian and Gstreamer support. I understand you’ll need an Ubuntu PC to compile neural networks using the toolkit, but you can run inferencing on lower end ARM hardware.
Related posts:
  1. Intel’s Movidius Neural Compute Stick Brings Low Power Deep Learning & Artificial Intelligence Offline
  2. Intel Compute Stick HDMI TV Dongle Runs Windows or Ubuntu for as Low as $89
  3. Intel Compute Stick is up for Pre-order for $110 and Up (USA Only)
  4. Android, Chromium OS, and Ubuntu on Intel Atom x5 Compute Stick. What Works, What Doesn’t.
  5. Intel Showcases Core m Compute Stick Prototype with RealSense Camera at IDF 2016 Shenzhen
Categories:Broadcom BCMxxxx, Debian, Hardware, LinuxTags:arm, artificial intelligence, development board, intel, movidius, raspberry pi
  1. halherta
    August 2nd, 2017 at 11:43 | #1
    Reply | Quote
    I love the raspberry pi 3 but it is not meant for serious machine learning especially when combined with computer vision. The Movidius is quite inferior as well. Combining 2 inferior products giving us a slightly less inferior result is not the best way to go. If you have a decent rig with an i3/i5/i7. Just add a gtx1060 to it. That setup will be leagues better than RPI 3 plus movidius.
    As for the movidius, there’s a running joke where people are betting on how long it will take for Intel to kill it as they did with their iot stuff. Most estimates are between 6 to 24 months.
    • Anton Fosselius
      August 2nd, 2017 at 12:50 | #2
      Reply | Quote
      @halherta
      You have obviously missed the point of the product. You cant strap something like that on a system with power/heat/size/weight restrictions.
      Of cause a bycycle generator is inferior to a wind turbine, but thats ok, because they forfill different needs.
  2. cnxsoft
    August 2nd, 2017 at 11:51 | #3
    Reply | Quote
    @halherta 
    That’s supposed to run on batteries, so you could install it on drones and robots.
  3. tkaiser
    August 2nd, 2017 at 12:47 | #4
    Reply | Quote
    @cnxsoft: I would think once the work with the SDK is finished the final application can run on anything equipped with an USB port to connect the Movidius stick. And after taking the 3 minutes to look through https://youtu.be/4xud1T9DaFY it looks obvious to me why a beefy x64 host is needed for the initial steps (CPU, IO and even good Internet connection needed). Watching the Movidius integration in the Phantom 4 drone from DJI was also quite interesting 🙂
  4. Patrick Poirier
    August 3rd, 2017 at 19:39 | #5
    Reply | Quote
    I installed the SDK on the new MelE celeron based miniPC and it works fine.
    Copied the graphfiles and the debs into my RPI 2b and the launch the python stream example using my C920 camera.
    It can recognize basic stuff at a prety good speed (estimate 10-15 fps) just like running caffe on a I5 type Laptop.
    My use case is QuadCopter object tracking and Pose commands, so this little stick is really an interesting add-on to an onboard low power (Watt & Whetstone) Companion Computer
  5. cnxsoft
    August 9th, 2017 at 11:15 | #6
    Reply | Quote
    Movidius Neural Compute Stick with RPi3 is about 3 times faster than the GPU on the Raspberry Pi when using the 12-cores of the stick for object recognition. YouTube Video: https://www.youtube.com/watch?v=v9_539oYufA
    Description:
    Comparison of deep learning inference acceleration by Movidius’ Neural Compute Stick (MvNCS) and by Idein’s software which uses Raspberry Pi’s GPU (VideoCore IV) without any extra computing resources.
    Movidius’ demo runs GoogLeNet with 16-bit floating point precision.Average inference time is 108ms.
    We used MvNC SDK 1.07.07 and their official demo script without any changes. (ncapi/py_examples/stream_infer/stream_infer.py)
    It seems something is wrong with the inference results.
    We recompiled graph file with -s12 option to use 12 SHAVE vector processor simultaneously.
    Idein’s demo also runs GoogLeNet with 32-bit floating point precision. Average inference time is 320ms.
  6. crashoverride
    August 9th, 2017 at 11:25 | #7
    Reply | Quote
    @cnxsoft 
    That all!?!?!?! Only 3X faster than an obsolete embedded GPU from 6 years ago!?!? Moore’s Law is dead at Intel!
  7. tkaiser
    August 9th, 2017 at 13:24 | #8
    Reply | Quote
    @crashoverride 
    Are you realizing that the video you use for your Intel bashing is provided by ‘Idein Inc’ comparing Idein’s own commercial deep learning solution with unoptimized demo code from a competitor (even mentioning ‘It seems something is wrong with the inference results’)? The competitor is a fabless semiconductor company called ‘Movidius Ltd’ (recently bought by Intel)…

留言

張貼留言

這個網誌中的熱門文章

opencv4nodejs Asynchronous OpenCV 3.x Binding for node.js   122     2715     414   0   0 Author Contributors Repository https://github.com/justadudewhohacks/opencv4nodejs Wiki Page https://github.com/justadudewhohacks/opencv4nodejs/wiki Last Commit Mar. 8, 2019 Created Aug. 20, 2017 opencv4nodejs           By its nature, JavaScript lacks the performance to implement Computer Vision tasks efficiently. Therefore this package brings the performance of the native OpenCV library to your Node.js application. This project targets OpenCV 3 and provides an asynchronous as well as an synchronous API. The ultimate goal of this project is to provide a comprehensive collection of Node.js bindings to the API of OpenCV and the OpenCV-contrib modules. An overview of available bindings can be found in the  API Documentation . Furthermore, contribution is highly appreciated....
張貼留言
閱讀完整內容

2017通訊大賽「聯發科技物聯網開發競賽」決賽團隊29強出爐！作品都在11月24日頒獎典禮進行展示

2017通訊大賽「聯發科技物聯網開發競賽」決賽團隊29強出爐！作品都在11月24日頒獎典禮進行展示 LIS   發表於 2017年11月16日 10:31   收藏此文 2017通訊大賽「聯發科技物聯網開發競賽」決賽於11月4日在台北文創大樓舉行，共有29個隊伍進入決賽，角逐最後的大獎，並於11月24日進行頒獎，現場會有全部進入決賽團隊的展示攤位，總計約為100個，各種創意作品琳琅滿目，非常值得一看，這次錯過就要等一年。 「聯發科技物聯網開發競賽」決賽持續一整天，每個團隊都有15分鐘面對評審團做簡報與展示，並接受評審們的詢問。在所有團隊完成簡報與展示後，主辦單位便統計所有評審的分數，並由評審們進行審慎的討論，決定冠亞季軍及其他各獎項得主，結果將於11月24日的「2017通訊大賽頒獎典禮暨成果展」現場公佈並頒獎。 在「2017通訊大賽頒獎典禮暨成果展」現場，所有入圍決賽的團隊會設置攤位，總計約為100個，展示他們辛苦研發並實作的作品，無論是想觀摩別人的成品、了解物聯網應用有那些新的創意、尋找投資標的、尋找人才、尋求合作機會或是單純有興趣，都很適合花點時間到現場看看。 頒獎典禮暨成果展資訊如下： 日期：2017年11月24日(星期五) 地點：中油大樓國光廳(台北市信義區松仁路3號) 我要報名參加「2017通訊大賽頒獎典禮暨成果展」>>> 在參加「2017通訊大賽頒獎典禮暨成果展」之前，可以先在本文觀看各團隊的作品介紹。 決賽29強團隊如下： 長者安全救星 可隨意描繪或書寫之電子筆記系統 微觀天下 體適能訓練管理裝置 肌少症之行走速率檢測系統 Sugar Robot 賽亞人的飛機維修輔助器 iTemp你的溫度個人化管家 語音行動冰箱 MR模擬飛行 智慧防盜自行車 跨平台X-Y視覺馬達控制 Ironmet 菸消雲散 無人小艇 (Mini-USV) 救OK-緊急救援小幫手 穿戴式長照輔助系統 應用於教育之模組機器人教具 這味兒很台味 Aquarium Hub 發展遲緩兒童之擴增實境學習系統 蚊房四寶 車輛相控陣列聲納環境偵測系統 戶外團隊運動管理裝置 懷舊治療數位桌曆 SeeM智能眼罩 觸...
張貼留言
閱讀完整內容
自製直播音源線 Bird Liang   October 6, 2016   in  View Bird Liang, Chief Engineer (梁子凌 / 技術長兼工程輔導長) 負責 AppWorks 技術策略與佈署，同時主導工程輔導。人生的第一份正職工作是創業，之後在外商圈電子業中闖蕩多年，經歷過 NXP、Sony、Newport Imagining、Crossmatch 等企業，從事無線通訊、影像系統、手機、面板、半導體、生物辨識等不同領域產品開發。熱愛學習新事物，協助團隊解決技術問題。放棄了幾近退休般的生活加入 AppWorks，為的是幫助更多在創業路上的人，並重新體驗創業的熱情。台大農機系、台科大電子所畢業，熱愛賞鳥、演奏管風琴，亦是不折不扣的熱血 Maker。 隨著 Facebook 開放一般帳號直播，現在我們只要拿起手機，隨時隨地都可以開始直播。回想幾年前 AppWorks 剛開始進行 Demo Day 直播時，還要將 HDMI 訊號接進 PC 中、再編碼打進 YouTube 的複雜度，實不可同日而語。 但用手機或平板直播最大的問題往往不是影像而是聲音。iPhone 或 iPad 上的攝影機，感度和解析度早已不輸數年前的專業攝影機，只要現場光不太差，大概都可以拍出令人滿意的畫面。但直播的聲音一直是個大問題，手機上的麥克風跟人耳所聽到的聲音其實有很大的差距，在比較大的場子裡，光是仰賴內建麥克風的收音多半無法有令人滿意的效果。 在大型的活動中，現場通常會有 PA 系統，最理想的方式還是想辦法將 PA 的訊號餵進 iPad 或 iPhone 中，保證聲音乾淨又清楚，絕對不會有其它有的沒的現場音。 iPhone 的耳機孔雖然可以插帶有麥克風的耳機 (如 Apple 原廠的 EarPods)，但它的訊號位準是電容式麥克風的位準。PA 控台的輸出幾乎都是 line level 的，兩者的訊號電壓相差百倍以上，我們得做個小東西來解決這個差距。 Line 與 Mic 在 mixer 上，我們常會看到輸入可以在兩種規格中切換: line level 和 mic level。Mic level 顧名思義就是從麥克風來的訊號，這個訊號的規格是從不需供電的傳統動圈麥克風來的。因為不需...
張貼留言
閱讀完整內容