Samples are simple applications that demonstrate how to use the DL Streamer. The samples are available in the
Samples separated into several categories
gvapythonelement and application provided python script for inference pre- or post-processing
Samples with C/C++ code provide
build_and_run.sh shell script to build application via cmake before execution.
Other samples (without C/C++ code) provide .sh script for constucting and executing gst-launch or Python command line.
DL Streamer samples use pre-trained models from OpenVINO™ Open Model Zoo
Before running samples, run script
download_models.sh once to download all models required for samples. The script located in
samples top folder.
First command-line parameter in DL Streamer samples specifies input video and supports
rtsp://) or other streaming source (ex URL starting with
If command-line parameter not specified, most samples by default stream video example from predefined HTTPS link, so require internet conection.
NOTE: Most samples set property
sync=falsein video sink element to disable real-time synchronization and run pipeline as fast as possible. Change to
sync=trueto run pipeline with real-time speed.