Developer Guide

  • 2022.3
  • 10/25/2022
  • Public Content
Contents

OpenVINO™ Sample Application

This tutorial tells you how to:
  • Run inference engine object detection on a pretrained network using the SSD method.
  • Run the detection demo application for a CPU and GPU.
  • Use a model optimizer to convert a TensorFlow* neural network model.
  • After conversion, run the neural network with inference engine for a CPU and GPU.

Run the Sample Application

  1. Check if your installation has the eiforamr-openvino-sdk Docker* image.
    docker images |grep eiforamr-openvino-sdk #if you have it installed, the result is: eiforamr-openvino-sdk
    If the image is not installed, continuing with these steps
    triggers a build that takes longer than an hour
    (sometimes, a lot longer depending on the system resources and internet connection).
  2. If the image is not installed, Intel recommends installing the Robot Complete Kit with the Get Started Guide for Robots.
  3. Go to the
    AMR_containers
    folder:
    cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_<version>/AMR_containers
  4. Prepare the environment setup:
    source ./01_docker_sdk_env/docker_compose/common/docker_compose.source export CONTAINER_BASE_PATH=`pwd` export ROS_DOMAIN_ID=22
  5. Run inference engine object detection on a pre-trained network using the Single-Shot multibox Detection (SSD) method. Run the detection demo application for a CPU:
    CHOOSE_USER=root docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/openvino_CPU.tutorial.yml up
    Expected output: A video in a loop with cars being detected and labeled by the Neural Network using a CPU
  6. To close this, do one of the following:
    • Type
      Ctrl-c
      in the terminal where you did the up command.
    • Run this command in another terminal:
    CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/openvino_CPU.tutorial.yml down
  7. For an explanation of what happened, open the yml file. The file is well documented. To use your own files, place them in your home directory, and change the respective lines in the yml files to target them.
  8. Run the detection demo application for the GPU:
    CHOOSE_USER=root docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/openvino_GPU.tutorial.yml up
    Expected output: A video in a loop with cars being detected and labeled by the Neural Network using a GPU
  9. To close this, do one of the following:
    • Type
      Ctrl-c
      in the terminal where you did the up command.
    • Run this command in another terminal:
    CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/openvino_GPU.tutorial.yml down
  10. For an explanation of what happened, open the yml file. The file is well documented. To use your own files, place them in your home directory, and change the respective lines in the yml files to target them.
  11. For system with an Intel® Movidius™ Myriad™ X accelerator, run the detection demo application on the Intel® Movidius™ Myriad™ X accelerator:
    Only execute this command on systems with an Intel® Movidius™ Myriad™ X accelerator.
    Check your system:
    lsusb
    Look for
    Intel Movidius MyriadX
    in the output.
    CHOOSE_USER=root docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/openvino_MYRIAD.tutorial.yml up
    Expected output: A video in a loop with cars being detected and labeled by the Neural Network using the Intel® Movidius™ Myriad™ X accelerator.
    There is a known issue that if you choose to run the
    object_detection_demo
    using the
    –d MYRIAD
    option, a core dump error is thrown when the demo ends.
    If errors occur, remove the following file and try again:
    rm -rf /tmp/mvnc.mutex
  12. To close this, do one of the following:
    • Type
      Ctrl-c
      in the terminal where you did the up command.
    • Run this command in another terminal:
    CHOOSE_USER=eiforamr docker-compose -f 01_docker_sdk_env/docker_compose/05_tutorials/openvino_MYRIAD.tutorial.yml down
  13. For an explanation of what happened, open the yml file. The file is well documented. To use your own files, place them in your home directory, and change the respective lines in the yml files to target them.

Troubleshooting

If running the yml file gets stuck at downloading:
gedit 01_docker_sdk_env/docker_compose/05_tutorials/openvino_CPU.tutorial.yml # In the same way open any other yml you want to test behind a proxy.
Add the following lines after echo echo “
***
Set up the OpenVINO environment
***
”, replacing
http://<http_proxy>:port
with your actual environment http_proxy.
export http_proxy="http://<http_proxy>:port" export https_proxy="http://<https_proxy>:port"
For general robot issues, go to: Troubleshooting for Robot Tutorials.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.