ERROR: <create_multi_source_bin:1320>: Failed to create element 'src_bin_muxe

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

•Quadro RTX 5000 dual GPU
•DeepStream SDK 5.1
•TensorRT Version 7.2.1.6
•Driver Version: 460.91.03
•Bug
• CUDNN_MAJOR 7 and CUDNN_MAJOR 8
•CUDA 11.1
•Ubuntu 18.04
•python 3.6
•resnet10.caffemodel

I am running inference on default resnet10.caffemodel provided by deepstream 5.1 ,i was able to run inference on my jetson xaviers nx using the same model ,i installed deepstream 5.1 on my workstation while running infrence i am getting this error

deepstream-app -c /opt/nvidia/deepstream/deepstream-5.1/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt

** ERROR: <create_multi_source_bin:1320>: Failed to create element ‘src_bin_muxer’
** ERROR: <create_multi_source_bin:1411>: create_multi_source_bin failed
** ERROR: <create_pipeline:1294>: create_pipeline failed
** ERROR: main:636: Failed to create pipeline
Quitting
App run failed

3

I ran Deepstream using docker ,it worked

used this docker

docker pull nvcr.io/nvidia/deepstream:5.1-21.02-triton

and ran using

"xhost +"

run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e
DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-5.1
nvcr.io/nvidia/deepstream:5.1-21.02-triton


`deepstream-app -c /opt/nvidia/deepstream/deepstream-5.1/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt`
5

Glad to know you resolved the problem. Thanks for the update!

6

You are welcome