openvino-docker

Intel® OpenVINO™ Toolkit environment

This Dockerfile will provide you with a base environment to run your inference models with OpenVINO™.

Building the Docker Image

The firt thing you need is to download the OpenVINO(tm) toolkit.

Or use wget to get the package directly (Latest version is 2020 1 by the time writing this guide)

wget http://registrationcenter-download.intel.com/akdlm/irc_nas/16345/l_openvino_toolkit_p_2020.1.023.tgz

tar -xf l_openvino_toolkit*

docker build -t openvino .

You can directly run a container based on this image or use this image across other images.

To run a container based on this image:

docker run -ti openvino /bin/bash

You can use this Docker image as a base image and use it in multiple Dockerfiles. An example of how to do this has been provided:

Move to sample-app directory and build the image

cd sample-app
docker build -t sample-app .

Additionally, for running a sample application that displays an image, you need to share the host display to be accessed from guest Docker container.

The X server on the host should be enabled for remote connections:

xhost +

The following flags needs to be added to the docker run command:

To run the sample-app image with the display enabled:

docker run --net=host --env="DISPLAY" --volume="$HOME/.Xauthority:/root/.Xauthority:rw" -ti sample-app /bin/bash

Finally disable the remote connections to the X server

xhost -

Once inside the container, go to the Inference Engine demo directory:

cd /opt/intel/openvino/deployment_tools/demo

Run the Image Classification demo:

./demo_squeezenet_download_convert_run.sh

Run the inference pipeline demo:

./demo_security_barrier_camera.sh