I can share it to you personally.
So what does that mean, it worked fine on deepstream6.1.1, but deepstream6.4 doesn’t work?
There are too many modules involved in your project, please run the following pipeline first to narrowdown the scope.
gst-launch-1.0 uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 ! \
smuxer.sink_0 nvstreammux name=smuxer batch-size=1 batched-push-timeout=4000000 ! \
nvinfer config-file-path=models/assets/face/face.txt ! \
nvvideoconvert ! nvdsosd ! faksink
What is your host system, ubuntu, WSL or VM?
It’s a ubuntu VM running on a Type 1 hypervisor!
From your log, there’s nothing wrong when DeepStream gst-launch-1.0 running.
Because many corresponding modules such as Ubuntu are upgraded, you need to check your own code step by step to find out which module caused the crash yourself.
I have fixed the configuration issue.
But now the Parallel application is not working, only one streammux is called, the other parallel streammux are not being called.
I feel it has to do with the metamux.
Only the first two cameras from the 1st streammux is being called, the second streammux is not being called at all.
Glad to hear that. Could you open a new topic for the new issue? It will make it easier for others to refer to it.
I have opened multiple topics for my second issue, but not proper reply, nor solution.
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
You can refer to our C/C++ demo deepstream_parallel_inference_app. Then compare your python code flow and the pipeline diagram to see where the differences are.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.