zoukankan      html  css  js  c++  java
  • Intel® Neural Compute Stick 2

    Technical Specifications

    A Plug and Play Development Kit for AI Inferencing

    • Build and scale with exceptional performance per watt per dollar on the Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU)
    • Start developing quickly on Windows® 10 or Ubuntu*
    • Develop on common frameworks and out-of-the-box sample applications
    • Operate without cloud compute dependence
    • Prototype with low-cost edge devices such as Raspberry Pi* 3 and other ARM* host devices

    https://software.intel.com/en-us/neural-compute-stick

    Hardware

    • Processor: Intel Movidius Myriad X Vision Processing Unit (VPU)
    • Supported frameworks: TensorFlow*, Caffe*, Apache MXNet*, Open Neural Network Exchange (ONNX*), PyTorch*, and PaddlePaddle* via an ONNX conversion
    • Connectivity: USB 3.0 Type-A
    • Dimensions: 2.85 in. x 1.06 in. x 0.55 in. (72.5 mm x 27 mm x 14 mm)
    • Operating temperature: 0° C to 40° C

    Software

    • Intel Distribution of OpenVINO toolkit
    • Supported operating systems:
      • Ubuntu 16.04.3 LTS (64 bit)
      • CentOS* 7.4 (64 bit)
      • Windows 10 (64 bit)
      • Raspbian (target only)
      • Other (via the open source distribution of OpenVINO™ toolkit)

    Product Brief

    Datasheet

    Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU)

    The latest generation of Intel® VPUs includes 16 powerful processing cores (called SHAVE cores) and a dedicated deep neural network hardware accelerator for high-performance vision and AI inference applications—all at low power.

    schematic drawing of the Intel Movidius Myriad X V P U
     
  • 相关阅读:
    题解45 跳跃游戏 II
    《重构》第八章阅读总结
    Scala学习笔记一
    Java初学随笔
    染色算法总结
    BingMap
    Google Earth API 替换方案
    本周安排
    OleDb 内存泄露问题
    css3 布局
  • 原文地址:https://www.cnblogs.com/cloudrivers/p/11604573.html
Copyright © 2011-2022 走看看