Reduce FPS to reduce computational complexity

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.2
• Issue Type( questions, new requirements, bugs) question
• Language Python

I would like to reduce the FPS before inference to fasten the overall process. In this stack overflow post, i saw this code to reduce FPS

def  create_videorate_filter():
     filter = Gst.ElementFactory.make('videorate', 'videorate')
     if not filter:
         sys.stderr.write(" Unable to create capsfilter \n")

     filter.set_property("max-rate", 5)

     return filter

In a multi stream pipeline I am not sure where to add this filter. I tried adding it after the streammux, but i am not getting any output

3

You can try to add that to each of your sources. We have a C/C++ demo to use this plugin “videorate”, you can refer to that:

opt\nvidia\deepstream\deepstream\sources\apps\sample_apps\deepstream-nmos\deepstream_nmos_app.c
4

is there any python code available ?

5

No. You can refer to how to use the videorate plugin and convert this snippet to Python.