How to free gpu and memory usage in deepstream app

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson Orin Nano
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only) 5.1.2
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I am running a deepstream application and I am looking for anyway to free some GPU/CPU usage and memory.
I have tried to increase the interval and lower the source FPS, but haven’t changed anything.
Do you have any suggestion?

3

Is it our demo application? In theory you can reduce memory and gpu usage by doing the following.

  1. Reduce the number of your sources
  2. Reduce the resolution, bitrate, fps of your stream
  3. Set “interval” parameter to the nvinfer
  4. Set an appropriate batch-size(we recommend the same number of video sources)
  5. You can try to use trtexec to test the performance first
./trtexec --loadEngine=xxx.engine --fpxx  --batch=x
4

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.