Replace the problem of using gpu-id

I have implemented the rtsp stream example with reference to here:deepstream_python_apps/apps/deepstream-rtsp-in-rtsp-out at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub
When I replaced the gpu-id of pgie, I found that the gpu-id of the plugins like nvstreammux, tiler, nvvidconv, etc. must also be replaced. As shown below, why is this? How can I determine which plugin’s gpu-id needs to be replaced together?
屏幕截图 2022-07-28 153116

If you only replace the gpu-id of pgie, do not replace the gpu-id of other plugins. The output rtsp stream will be like this:

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.

Hi @2016674027 , Your diffrent GPUs may have diffrent memory processing. You can try to set the nvbuf-memory-type to Unified.

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• 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)

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