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)
Imagine a pipe composed of bellow plugins :
v4lsrc + nvinfer(pgie) + nvtracker + nvinfer(sgie) + nvdsosd
is there any difference if this pipe be in a gstreamer application or deep stream-app ? Is latency and fps different in two cases?
I mean using bellow pipe :
gst-launch-1.0 v4l2src ! nvinfer … ! nvtrackerwrapper … ! … ! nvdsosd
when I use this pipeline in jetson terminal the fps is much lower than deepstream-app. even tensorrt loading time is lower in deepstream-app. what is the reason?
Can you post your full gst-launch pipeline?
If your gst-launch pipeline has a bottleneck it might be dropping frames. Can you check using --gst-debug?
You can actually generate the Gst pipeline graph of your launch command vs your deepstream-app configuration and see whether the pipeline are same/similar at runtime. Just set the variable GST_DEBUG_DUMP_DOT_DIR=./ before your run command.
More details here
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