• Hardware Platform (Jetson / GPU) NVIDIA A2
• DeepStream Version 6.3
• TensorRT Version 8.4.0
• NVIDIA GPU Driver Version (valid for GPU only) 535.129.03
I am using python deepstream SDK with nvinferserver, and I face an issue while running rtsp on my pipeline.
If I run 30+ camera, when some of them go off (rtsp stream stops), the whole pipeline hang.
which sample are you referring to? what is the while media pipeline? please refer to this topic.
I wrote my own pipeline based on deepstream_test_3.
My pipeline originally is pgie → tracker → sgie → sgie. I suspected that the sgies models might have issue or something so, I excluded them to have pgie (peoplenet) and tracker (accuracy one -which has reid-) and I still have the same issue.
There is no update from you for a period, assuming this is not an issue any more. Hence we are closing this topic. If need further support, please open a new one. Thanks.
please refer to this topic. you can modify batched-push-timeout to improve. please refer to this FAQ to improve.
duplicate with Reconnection Issue
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.