Himax AIoT Platform Board with NB-IoT(TensorFlow Lite for Microcontrollers)

It is a modified version of the TensorFlow Lite for Microcontrollers for use with Himax-AIoT-NB-G3 Boards. Each example in the package has been tested in Ubuntu 20.04 LTS environment.

Following examples are included :

• person detection INT8 example

Table of contents

• Prerequisites
• Deploy to Himax-AIoT-NB-G3

Prerequisites

• Make Tool version

  A make tool is required for deploying Tensorflow Lite Micro applications, See Check make tool version section for proper environment.

• Development Toolkit

  Install the toolkits listed below:

  • GNU Development Toolkit

    See ARC GNU Tool Chain section for more detail, current released GNU version is GNU Toolchain for ARC Processors, 2020.09. After download and extract toolkit to local space, please remember to add it to environment PATH. For example:

    export PATH=[location of your ARC_GNU_ROOT]/bin:$PATH
    

• curl command

  Installing curl for Ubuntu Linux.

  sudo apt update
  sudo apt upgrade
  sudo apt install curl
  

• Serial Terminal Emulation Application

  There are 2 main purposes for Himax-AIoT-NB-G3 Debug UART port, print application output and burn application to flash by using xmodem send application binary.

Deploy to Himax-AIoT-NB-G3

Default building toolchain in makefile is Metaware Development toolkit, if you are trying to build example with GNU toolkit. please change the ARC_TOOLCHAIN define in Makefile like this

ARC_TOOLCHAIN ?= gnu

Before Build person detection INT8 example and flash image, you need to Himax-AIoT-NB-G3-SDK-Azure-RTOS-main\himax_aiot_nb_g3-master\tools\image_gen_cstm directory

chmod 777 *

Build person detection INT8 example and flash image. The resulted flash image will be named output.img and saved under Himax-AIoT-NB-G3-SDK-Azure-RTOS-main\himax_aiot_nb_g3-master\tools\image_gen_cstm\outputby default.

make clean && make && make flash 

After flash image generated, please download the flash image file to Himax-AIoT-NB-G3 EVB by UART, details are described here