Deepstream 5.0 - how to view pipeline of example apps

• Hardware Platform ( GPU)
**• DeepStream Version 5.0
• TensorRT Version
**• NVIDIA GPU Driver Version (valid for GPU only) 450.36.06


I can invoke a command such as ../../bin/deepstream-app -c deepstream_app_config_yoloV3.txt and get satisfactory results, but I would like to invoke the same pipeline on the command line using gst-launch - is there an easy way to do this?

The reason I want to do this is because I want to use a custom source for the input to the pipeline - namely the pylon src for GigE support from here:


Hey, if you want to use custom source, you can base your gst-launch commandn on the following example:

gst-launch-1.0 v4l2src device=/dev/video0 io-mode=2 ! 'image/jpeg,width=1920,height=1080,framerate=30/1' ! jpegparse ! nvjpegdec ! video/x-raw ! nvvideoconvert ! 'video/x-raw(memory:NVMM),format=NV12' ! mux.sink_0 nvstreammux live-source=1 name=mux batch-size=1 width=1920 height=1080 ! nvinfer config-file-path=/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-test1/dstest1_pgie_config.txt batch-size=1 ! nvmultistreamtiler rows=1 columns=1 width=1920 height=1080 ! nvvideoconvert ! nvegltransform ! fpsdisplaysink video-sink=nveglglessink text-overlay=0 -v

The example is for jpeg v4l2 input source which you can replace with your own and you’ll have to update the decoder according to your stream as well but it gives a general view of how you can use nvinfer, nvstreammux, with eglglessink renderer.

When you file your own config file for deepstream-app, you already know what the pipeline is, which plugins are used. You can write ‘gst-launch-1.0’ command as a normal gstreamer pipeine. We don’t have tool to convert config file to pipeline because deepstream-app is not only to setup pipeline, but also to do some other things with deepstream apis.