Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 7.1
• JetPack Version (valid for Jetson only) None
• TensorRT Version 10.6
• NVIDIA GPU Driver Version (valid for GPU only) 560.35.05
• Issue Type( questions, new requirements, bugs) Questions
• 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)
I am trying to grab frames from 16ch rtsp streams and forward multiple detectors with nvidia refrence app deepstream_parallel_inference_app.
If input streams are video files w/o any detector, fps is around 60 and gpu usage ‘dec’ is high.
# source_file.csv
enable,type,uri,num-sources,gpu-id,cudadec-memtype
1,3,file:///workspace/vidoes/m28s1.mp4,1,0,0
1,3,file:///workspace/vidoes/m28s1.mp4,1,0,0
1,3,file:///workspace/vidoes/m28s1.mp4,1,0,0
...
However, when input streams are RTSP, FPS drops to 5~6.
# source_rtsp.csv
enable,type,uri,num-sources,gpu-id,cudadec-memtype
1,4,rtsp://RTSP_URI,1,0,0
1,4,rtsp://RTSP_URI,1,0,0
1,4,rtsp://RTSP_URI,1,0,0
...
Here are my problems,
- Decoding frame rate too small like 5 or 6 per second.
- Deepstream has 2 second delay compare to vlc player with same uri.
- in some point, blurring/ pixelation in some area while frame in vlc player is clean.
What config or option should I check…?
I would greatly appreciate your assistance.
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)