DLI course exercise 5 Gstreamer pipeline getting frozen

[kamble.paresh]

Please provide complete information as applicable to your setup.

• GPU
• DeepStream Version - 3.0
• TensorRT Version - 5.0.2
• NVIDIA GPU Driver Version - 410
• Issue Type - questions
• How to reproduce the issue ?
Running exercise 5 from the notebook http://xxxxxxxxxxxxxxx.compute-1.amazonaws.com/xxxxxxx/notebooks/tasks/l-iv-04/task/DeepStream_Detailed.ipynb should reproduce the issue.
**• Requirement details **
I am doing the course ‘AI Workflows for Intelligent Video Analytics with DeepStream’ from NVIDIA DLI.
While on exercise 5, even after running the answer key, the pipeline is getting frozen and does not go ahead of

Setting pipeline to PAUSED ...
>>> Using TRT model serialized engine /dli/tasks/l-iv-04/task/DeepStream_Release/samples/configs/deepstream-app/../../models/Primary_Detector/resnet10.caffemodel_b30_int8.engine crypto flags(0)
Pipeline is PREROLLING ...
Redistribute latency...
Redistribute latency...

[yingliu]

Are you able to run other samples in this environment? I just run the exercise 5 in the end of the notebook and confirmed it works. Maybe you can stop your start and start it again.

[kamble.paresh]

Thank you for your respomse.
Yes, I am able to complete all other exercises in the environment except this one.
As per your suggestion, I restarted the notebook and directly jumped to exercise 5 after completing the SDK installation in 3.1.
However, it is still stuck like forever. It is more than 10min now. Even if I directly jump to exercise 5, the pipeline still stucks. :(

What could be the probable issue ?

[Amycao]

Please set nvstreammux batch size to 2, since you have 2 input.
Can you paste the pipeline here not as picture?

[kamble.paresh]

Wonderful! It worked.
The pipeline:

!gst-launch-1.0 nvstreammux name=mux batch-size=2 width=1280 height=720 ! nvinfer config-file-path=./DeepStream_Release/samples/configs/deepstream-app/config_infer_primary.txt ! nvstreamdemux name=demux \
filesrc location=./DeepStream_Release/samples/streams/1.264 ! h264parse ! nvdec_h264 ! queue ! mux.sink_0 \
filesrc location=./DeepStream_Release/samples/streams/2.264 ! decodebin ! queue ! mux.sink_1 \
demux.src_0 ! "video/x-raw(memory:NVMM), format=NV12" ! queue ! nvvidconv ! "video/x-raw(memory:NVMM), format=RGBA" ! nvosd font-size=15 ! nvvidconv ! "video/x-raw, format=RGBA" ! videoconvert ! "video/x-raw, format=NV12" ! x264enc ! qtmux ! filesink location=./out3.mp4 \
demux.src_1 ! "video/x-raw(memory:NVMM), format=NV12" ! queue ! nvvidconv ! "video/x-raw(memory:NVMM), format=RGBA" ! nvosd font-size=15 ! nvvidconv ! "video/x-raw, format=RGBA" ! videoconvert ! "video/x-raw, format=NV12" ! x264enc ! qtmux ! filesink location=./out4.mp4

Please edit the same in the answer key of the exercise 5.

Thank you so much!