Install Guide RHEL#

For Red Hat Enterprise Linux 8, Intel® Deep Learning Streamer (Intel® DL Streamer) Pipeline Framework can be built from the source code provided in this repository as Docker image.

Compile Intel® DL Streamer Pipeline Framework as Docker image#

To be able to create Intel® DL Streamer Pipeline Framework Docker image, activated RHEL Docker image is required.

Step 1: Install Docker CE (if not installed)#

Refer to Docker installation documentation

Step 2: Clone the repository#

Clone this repository into folder ~/intel/dlstreamer:

mkdir -p ~/intel
git clone ~/intel/dlstreamer
cd ~/intel/dlstreamer

Step 3: Build Docker image#

Run the following command to build Docker image:

cd ~/intel/dlstreamer/docker/source/rhel8
# Provide a name and a tag of activated RHEL Docker image as a first argument.
# If you want to build an image with a specific tag then provide it
# as a second argument (by default latest).
./ <image name> [tag]

The build process may take significant time and should finally create Docker image dlstreamer:<tag> (by default latest). Obtained Docker image can be validated with command:

docker images | grep dlstreamer

This command will return a line with image dlstreamer:<tag> description. If the image is absent in the output, please repeat all the steps above.

Step 4: Run Docker image#

Some Pipeline Framework samples use display to render results. In order to allow connection from Docker container to host X server run the following commands.

xhost local:root
setfacl -m user:1000:r ~/.Xauthority

Then, run container:

docker run -it --privileged --net=host \
-v ~/.Xauthority:/home/dlstreamer/.Xauthority \
-v /tmp/.X11-unix:/tmp/.X11-unix \
-e http_proxy=$http_proxy \
-e https_proxy=$https_proxy \
-v ~/intel/dlstreamer/models:/home/intel/dlstreamer/models \
-v ~/intel/dlstreamer/video:/home/video-examples:ro \
-e VIDEO_EXAMPLES_DIR=/home/video-examples \


If your host OS is Ubuntu 20 add --group-add=$(stat -c "%g" /dev/dri/render*) argument for docker run in order to setup access to GPU from container.
Refer to this guide for more details.

Here is the additional information and the meaning of some options in the Docker run command:

  • Option --privileged is required for Docker container to access the host system’s GPU.

  • Option --net=host provides host network access to container. It is needed for correct interaction with X server.

  • Files ~/.Xauthority and /tmp/.X11-unix mapped to the container are needed to ensure smooth authentication with X server.

  • -v instances are needed to map host system directories inside Docker container.

  • -e instances set Docker container environment variables. The samples need some of them set in order to operate correctly. Proxy variables are needed if the host is behind a firewall.

  • Volume provided for models folder will be used to download and store the models. Environment variable MODELS_PATH in the Docker container is responsible for it.

  • Entrypoint of the Docker is by default /opt/intel/dlstreamer/samples.

Inside Docker image you can find Pipeline Framework samples at the entrypoint. Before using the samples, run the script (located in samples folder) to download the models required for samples.


If you want to use video from web camera as an input in sample you should mount the device with this command (add this command when running the container):

-v /dev/video0:/dev/video0

Now you can run the sample with video from web camera:

./ /dev/video0


You can run Docker image using utility script located in docker folder:

cd ~/intel/dlstreamer/docker/source/rhel8  # essential
export DATA_PATH=~/intel/dlstreamer  # essential
sudo ./ --video-examples-path=$DATA_PATH/video --models-path=$DATA_PATH/models --image-name=dlstreamer:<tag>

Next Steps#

* Other names and brands may be claimed as the property of others.