Please provide complete information as applicable to your setup.
• Hardware Platform (DGPU) • DeepStream Version 6.2 • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) - 535 • Issue Type( questions, new requirements, bugs) - Gstreamer NV Plugins • 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 am able to run the Deepstream sample applications thro “./deepstream-test1-app dstest1_config.yml”.
But when I try to run thro’ Gstreamer pipeline (gst-launch-1.0 uridecodebin3 uri=“rtspt://170.93.143.139/rtplive/4e00a5cd00050075004d823633235daa” ! queue ! nvstreammux0.sink_0 nvstreammux name=nvstreammux0 batch-size=1 batched-push-timeout=40000 width=1280 height=720 live-source=TRUE ! queue ! nvvideoconvert ! queue ! nvinfer config-file-path=“/opt/nvidia/deepstream/deepstream-4.0/samples/configs/deepstream-app/config_infer_primary.txt” model-engine-file=“/opt/nvidia/deepstream/deepstream-4.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_int8.engine” ! queue ! nvdsosd process-mode=HW_MODE ! queue ! nvoverlaysink sync=false).
It throws error "WARNING: erroneous pipeline: no element “nvstreammux”
I tried to inspect the element gst-inspect-1.0 nvstreammux and got the message as “No such element or plugin ‘nvstreammux’”. Infact none of the NV plugins are found thro Gstreamer incl nvarguscamerasrc and other nv plugins.
Do we need to install anything specific for NV plugins?
1.Is libnvdsgst_multistream.so and libnvdsgst_infer.so exsits at /opt/nvidia/deepstream/deepstream/lib/gst-plugins ?
Yes. Both the files are present.
2.what is the output of deepstream-app --version-all ?
deepstream-app version 6.2.0
DeepStreamSDK 6.2.0
CUDA Driver Version: 12.2
CUDA Runtime Version: 12.2
TensorRT Version: 8.5
cuDNN Version: 8.7
libNVWarp360 Version: 2.0.1d3
3.Is the following command line run normally ?
It returns "WARNING: erroneous pipeline: no element “nvstreammux”
As mentioned earlier, I am able to run Deep stream sample applications like deepstream-test1-app, deepstream-test2-app, ‘deepstream-app’… and able to see the video with detected objects (like car, people…). But I am unable to run thro Gstreamer pipeline.
I am now trying with Docker NGC container as per steps given Deep stream documentation
I am facing couple of issue
“xhost +” returns “Invalid MIT-MAGIC-COOKIE-1 keyxhost: unable to open display ":0”
Without the above step, I tried running docker as below
“sudo docker run -it --rm --net=host --gpus all -e DISPLAY=$DISPLAY --device /dev/snd -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream:6.3-samples”
However, When I am executing
“./deepstream-test1-app dstest1_config.yml”, it is not progressing (and it hangs) beyond the below message
"
Added elements to bin
Using file: dstest1_config.yml
No protocol specified
No protocol specified
No protocol specified
No protocol specified
Running…