ERROR from src_bin_muxer: Output width not set

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) NVIDIA RTX A3000 Ubuntu 20.04
• DeepStream Version 6.2

/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app$ deepstream-app -c config_tracker_NvDeepSORT.yml
** ERROR: main:716: Failed to set pipeline to PAUSED
Quitting
ERROR from src_bin_muxer: Output width not set
Debug info: gstnvstreammux.c(2910): gst_nvstreammux_change_state (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer
App run failed

2

This is the config file for tracker. You can refer to the config file starting with souce*.

4

You can try command below for test local file as input

deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml

You can got more information from here

Thanks

5

I am getting this error after running above command
0:01:14.670972658 22751 0x5571d992e610 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<secondary_gie_0> [UID 4]: Load new model:/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/config_infer_secondary_vehicletypes.txt sucessfully
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-6.2/lib/libnvds_nvmultiobjecttracker.so
gstnvtracker: Failed to open low-level lib at /opt/nvidia/deepstream/deepstream-6.2/lib/libnvds_nvmultiobjecttracker.so
dlopen error: libcufft.so.10: cannot open shared object file: No such file or directory
gstnvtracker: Failed to initilaize low level lib.
** ERROR: main:716: Failed to set pipeline to PAUSED
Quitting
nvstreammux: Successfully handled EOS for source_id=0
nvstreammux: Successfully handled EOS for source_id=1
nvstreammux: Successfully handled EOS for source_id=2
nvstreammux: Successfully handled EOS for source_id=3
App run failed

6

Looks like there is a problem with your gpu driver.
Please reference this document to install dependencies

I strongly recommend you to use docker.
Here is the installation manual

Thanks

7

I will say by example:
deepstream-app -c source4_1080p_dec_preprocess_infer-resnet_preprocess_sgie_tiled_display_int8.txt
This works perfectly on my local machine setup but not on docker.
Similarly I was trying to run this
deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml
I am unable to run it either on my local machine setup or in Docker.

8

Did you run “xhost + ” before launching the docker?
This is required as mentioned in DeepStream | NVIDIA NGC

Can you provide log after export GST_DEBUG=3 ?

9

after doing xhost+
I ran docker
then deepstream-app -c source4_1080p_dec_preprocess_infer-resnet_preprocess_sgie_tiled_display_int8.txt
Getting error
** ERROR: main:733: Could not open X Display

10

How you ran docker ? can you provide the command line

Recommended:

docker run --gpus all -it --rm --net=host --privileged -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-6.2 nvcr.io/nvidia/deepstream:6.2-devel

what do you see from “echo $DISPLAY ”?
If there is no content
export DISPLAY=:0 or 1 // xrandr to check display environment exported or not.

If still not working, Please provide log after export GST_DEBUG=3.

11

I was running docker like this
docker run -it --gpus all nvcr.io/nvidia/deepstream:6.2-samples
so got error after running DeepStream sample inference

Then I ran docker like this
docker run --gpus all -it --rm --net=host --privileged -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-6.2 nvcr.io/nvidia/deepstream:6.2-samples
Then I ran these following sample inferences and they are running fine
deepstream-app -c source4_1080p_dec_preprocess_infer-resnet_preprocess_sgie_tiled_display_int8.txt

deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml

However this deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml is not running on my local setup