Memory consumption on DeepStream 3.0 pipeline

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi,
We are developing a DS 3.0 application with multiple input sources.
In the pipeline we use the plugin streammux, source * and “ds-example”.
Why is the memory consumption for one DS source is about 0.5 GB of GPU RAM?

Is it possible to monitor/tune memory allocations for DeepStream applications?

configfile.txt (1.71 KB)

2

It includes decoder video memory, streammux conversion memory, and the memory ds-example needs.