Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) t4 • DeepStream Version 7.0 • JetPack Version (valid for Jetson only) • TensorRT Version deepstream 7.0 installation docs • NVIDIA GPU Driver Version (valid for GPU only) 535 • 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)
hi i try to see latency of all element in deepstream and do what exacly exist in deepstream sdk frequently asked and see that latency in framelatency
to too high how can i fix this ? (the first picture is incorrect it most of the time more that 2000ms)
From the graph you attached, the pipeline is working with two live streams.
Have you tested the latency with local video file sources?
What are the FPS of the two live sources? What are the two live sources? RTSP, HTTP, RTMP, V4L2src,…? The video format and resolution?
Since you have only two input streams, it is better to set “batch-size=2” with the nvstreammux.
What is the performance data of the “yolov4_resnet18_epoch_100.onnx_b1_gpu0_fp16.engine” with trtexec? Can you try batch size 2 engine for you have two input streams.
1- It works well in more than 3 video
2- rtsp 1920x1080 avi(maybe)
3- i did but the impact was too low
4-i didn"t use trtexec but i will send to you tomorrow but with deepstream measurment for 1 video it was 11ms
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
