Sample deepstream-app crashes in Deepstream 5.0

Hi, I’m having problems when I run the sample deepstream-app in Deepstream 5.0. I am using the docker container with the tag deepstream:5.0-dp-20.04-devel on a remote server with this setup:

deepstream-app version 5.0.0
DeepStreamSDK 5.0.0
CUDA Driver Version: 10.2
CUDA Runtime Version: 10.2
TensorRT Version: 7.0
cuDNN Version: 7.6
libNVWarp360 Version: 2.0.1d3

These are the errors:

root@6652db923a9d:/pkl2/deepstream-5.0/sources/apps/sample_apps/deepstream-app# ./deepstream-app -c …/…/…/…/samples/configs/deepstream-app/config_infer_primary.txt
** ERROR: main:651: Failed to set pipeline to PAUSED
Quitting
ERROR from src_bin_muxer: Output width not set
Debug info: gstnvstreammux.c(2125): gst_nvstreammux_change_state (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer
App run failed

root@6652db923a9d:/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-app# ./deepstream-app -c …/…/…/…/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt
** ERROR: main:651: Failed to set pipeline to PAUSED
Quitting
App run failed

I have not changed source30_1080p_dec_infer-resnet_tiled_display_int8.txt but I have added the following onto the end of config_infer_primary.txt for a file output

[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file:///opt/nvidia/deepstream/deepstrewm-5.0/samples/streams/sample_1080p_h264.mp4
num-sources=1
#drop-frame-interval=2
gpu-id=0
cudadec-memtype=0

[sink0]
enable=0
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming 5=Overlay
type=2
sync=0
display-id=0
offset-x=0
offset-y=0
width=0
height=0
overlay-id=1
source-id=0

[sink2]
enable=1
type=3
#1=mp4 2=mkv
container=1
#1=h264 2=h265 3=mpeg4
codec=3
sync=1
bitrate=2000000
output-file=out.mp4
source-id=0

[tests]
file-loop=0

Seems you didn’t set the width under streammux group, could you double check?

[streammux]
width=1920
height=1080

Is this correct? When I add this into config_infer_primary.txt I get the error

Could not find group property
** ERROR: <gst_nvinfer_parse_config_file:1158>: failed

Can you refer https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html#page/DeepStream_Development_Guide/deepstream_app_config.3.2.html# firstly?

Thanks, I also added in batch-size now I’m getting a segmentation fault error.

2020-06-17 08:12:43.585557: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.2 Runtime commands: h: Print this help q: Quit p: Pause r: Resume ** INFO: <bus_callback:181>: Pipeline ready ** INFO: <bus_callback:167>: Pipeline running Segmentation fault (core dumped)

Have you solved your issues, obviously it’s a setup issue, could you following the link I shared on last comment?

I haven’t solved it yet. I am now just trying to run with the sample config files without any edits. I am running on GeForce Titan X which has a CUDA compute capability of 5.2 - do you think this could be the problem?

You’d better follow the DS setup doc to resetup your env.

Sorry, just to check do you mean this https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html? I am using the triton docker container

Exactly, BTW, are you planning to use nvinferserver since u’r using triton docker

I will eventually be using triton, just trying to get any of the sample apps running at the moment. Pulled and run the container again and the issue is now Bus Error (core dumped)

Turns out my server wasn’t CUDA compute compatible with Deepstream 5.0. The GeForce Titan X is 5.2 but Deepstream requires at least 6.0