Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
L40
• DeepStream Version
DeepStream helm chart doc v0.1.9
https://catalog.ngc.nvidia.com/orgs/nvidia/helm-charts/video-analytics-demo?version=0.1.9
• 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)
I followed the documentation to deploy the chart on a 3-node Kubernetes cluster with an L40 GPU:
helm install dsdemo video-analytics-demo
–set “cameras.camera1=rtsp://172.24.114.122:8554/cam1”
–set resources.limits.“nvidia.com/gpu”=2
–set resources.limits.cpu=32
–set resources.limits.memory=64Gi
–set resources.requests.“nvidia.com/gpu”=2
–set resources.requests.cpu=16
–set resources.requests.memory=32Gi
I would like to ask DeepStream experts for advice or suggestions on how to resolve the issue where the demo video often lag and fuzzy. Any feedback would be greatly appreciated. Thank you.
Issue1: using mp4 files instead of rtsp://xxx:8554/cam1
–set “cameras.camera1=/mnt/taipei1.mp4”
(/mnt/ is mounted to the pod)
Issue2: how to improve rtsp://xxx:8554/cam1 steaming quality
I use mediamtx-ffmpeg to play the .mp4 file as the streaming source
rtspTransports: [“tcp”]
paths:
cam1:
source: publisher
runOnInit: >
ffmpeg
-re -stream_loop -1 -thread_queue_size 1024
-i /mnt/airport1.mp4
-c copy
-rtsp_transport tcp
-reset_timestamps 1
-avoid_negative_ts make_zero
-rtpflags latm
-f rtsp
rtsp://localhost:$RTSP_PORT/$MTX_PATH?pkt_size=1200
runOnInitRestart: yes
cam2:
…