At first, the fps value was very low and then became stable. What did you do at the beginning to cause the fps value to be very low?
What are your sources? Local video file, network streams such as http, rtsp, hls,… or videos from devices (such as CSI camara, USB camera,…)?
What kind of pipeline are you using? What is the configurations?
The sample program I used has not changed anything.
deepstream-app -c $Deepstream_Path/source30_1080p_dec_infer-resnet_tiled_display_int8.txt
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)
Please read the code of /opt/nvidia/deepstream/deepstream/sources/apps/common/src/deepstream_perf.c, “perf_measurement_callback” is triggered in a timer g_timeout_add(The Main Event Loop: GLib Reference Manual) when start the pipeline, so the initialization time of the pipeline is also calculated in the first frame. It will take a long time for initialization. If the timeout of the timer is too short, it is possible that the first time FPS calculation output 0 value.