Deepstream 6.1: deepstream-app not working after install

rdh · August 13, 2022, 4:42pm

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU): GPU 3050 laptop
**• DeepStream Version: 6.1
• JetPack Version (valid for Jetson only)
**• TensorRT Version: 8.2.5.1
**• NVIDIA GPU Driver Version (valid for GPU only): 510.47.03
**• Issue Type( questions, new requirements, bugs): bug/install issues
**• How to reproduce the issue ? /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app$ sudo deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt
**• Requirement details:

I am attempting to run the sample applications to verify the installation of Deepstream 6.1 on a new laptop with a fresh install of Ubuntu 20.04, and I am getting errors when attempting to run the application. I attempted to follow the getting started instructions, and I seemed to get a successful install after running the 510.47 installer after telinit 3, installing prime-select, adding a nouveau blacklist and deleting xorg.conf.

The example app does not produce any video output and exits with errors.

Command and config file:
deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt

I would appreciate guidance on where to start troubleshooting. Output copied below:

0:00:02.405598255 2740 0x560b2a1bc240 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40

0:00:02.461789584 2740 0x560b2a1bc240 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine
0:00:02.465332125 2740 0x560b2a1bc240 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/config_infer_primary.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

p: Pause
r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.

** INFO: <bus_callback:194>: Pipeline ready

cuGraphicsGLRegisterBuffer failed with error(219) gst_eglglessink_cuda_init texture = 1
0:00:03.064526705 2740 0x560b28f166a0 WARN nvinfer gstnvinfer.cpp:2299:gst_nvinfer_output_loop:<primary_gie> error: Internal data stream error.
0:00:03.064549123 2740 0x560b28f166a0 WARN nvinfer gstnvinfer.cpp:2299:gst_nvinfer_output_loop:<primary_gie> error: streaming stopped, reason not-negotiated (-4)
ERROR from primary_gie: Internal data stream error.
Debug info: gstnvinfer.cpp(2299): gst_nvinfer_output_loop (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
streaming stopped, reason not-negotiated (-4)
Quitting
ERROR from sink_bin_queue: Internal data stream error.
Debug info: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstQueue:sink_bin_queue:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux19: Internal data stream error.
Debug info: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin19/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin19/GstQTDemux:qtdemux19:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue19: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin19/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin19/GstMultiQueue:multiqueue19:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux28: Internal data stream error.
Debug info: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin29/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin29/GstQTDemux:qtdemux28:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux13: Internal data stream error.
Debug info: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin1/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin1/GstQTDemux:qtdemux13:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux4: Internal data stream error.
Debug info: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin0/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin0/GstQTDemux:qtdemux4:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux3: Internal data stream error.
Debug info: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin7/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin7/GstQTDemux:qtdemux3:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue3: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin7/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin7/GstMultiQueue:multiqueue3:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux24: Internal data stream error.
Debug info: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin23/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin23/GstQTDemux:qtdemux24:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue24: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin23/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin23/GstMultiQueue:multiqueue24:
streaming stopped, reason not-negotiated (-4)

yingliu · August 14, 2022, 9:19am

Did you follow the installation guide here? Quickstart Guide — DeepStream 6.1.1 Release documentation
Alternately you can run deepstream in docker, the relevant documents can be found on below links:
Docker Containers — DeepStream 6.1.1 Release documentation
DeepStream | NVIDIA NGC

rdh · August 14, 2022, 1:19pm

I did attempt to follow the Quickstart Guide. There appeared to be some missing steps:
*several related to X11 and nouveau for the 510.47 graphics driver installation to work with the ubuntu GUI (prime-select, nouveua blacklist configuration and removing xorg.conf after driver installation)
*libglvnd seems to need to be installed - which I did
*/usr/local/python is not installed or linked, but seems to be required. I linked it to python3

Regarding docker containers, the docker containers appear to require a data center graphics card, and the computer I am attempting to install on is a laptop with RTX 3050. Are there docker containers that support the laptop version of the RTX3050?

yingliu · August 14, 2022, 1:35pm

We test and maintain DeepStream on NVIDIA® T4, NVIDIA® Ampere for dGPU mentioned in the quick start guide, but it’s still working on RTX, you can google some guide on it. Please be sure nvidia-docker is installed.

rdh · August 15, 2022, 12:26am

I tried running it with docker and got a very similar result.

I followed the instructions at Install Docker Engine on Ubuntu | Docker Documentation to install the 19.03.15 version of docker engine, then continued with the NVIDIA Container Toolkit from Installation Guide — NVIDIA Cloud Native Technologies documentation.

The cuda container check seemed to work (results at the end). I ran the nvcr.io/nvidia/deepstream:6.1-devel container and the deepstream-app sample gave very similar results.

in the host OS:
xhost+
sudo docker run --gpus all -it --rm --net=host --privileged -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-6.1 nvcr.io/nvidia/deepstream:6.1-samples

in the container
cd /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app
deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt

The result is the a black window briefly pops up and the following.

(gst-plugin-scanner:14): GStreamer-WARNING **: 23:59:38.060: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_ucx.so’: libucs.so.0: cannot open shared object file: No such file or directory

(gst-plugin-scanner:14): GStreamer-WARNING **: 23:59:38.070: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_udp.so’: librivermax.so.0: cannot open shared object file: No such file or directory

(gst-plugin-scanner:14): GStreamer-WARNING **: 23:59:38.102: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferserver.so’: libtritonserver.so: cannot open shared object file: No such file or directory
WARNING: …/nvdsinfer/nvdsinfer_model_builder.cpp:1482 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine open error
0:00:02.547788450 13 0x556f26675630 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed
0:00:02.561766342 13 0x556f26675630 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed, try rebuild
0:00:02.561785260 13 0x556f26675630 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
0:01:01.436544222 13 0x556f26675630 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1946> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine successfully
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40

0:01:01.458046640 13 0x556f26675630 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/config_infer_primary.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

p: Pause
r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.

**PERF: FPS 0 (Avg) FPS 1 (Avg) FPS 2 (Avg) FPS 3 (Avg) FPS 4 (Avg) FPS 5 (Avg) FPS 6 (Avg) FPS 7 (Avg) FPS 8 (Avg) FPS 9 (Avg) FPS 10 (Avg) FPS 11 (Avg) FPS 12 (Avg) FPS 13 (Avg) FPS 14 (Avg) FPS 15 (Avg) FPS 16 (Avg) FPS 17 (Avg) FPS 18 (Avg) FPS 19 (Avg) FPS 20 (Avg) FPS 21 (Avg) FPS 22 (Avg) FPS 23 (Avg) FPS 24 (Avg) FPS 25 (Avg) FPS 26 (Avg) FPS 27 (Avg) FPS 28 (Avg) FPS 29 (Avg)
**PERF: 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00)
** INFO: <bus_callback:194>: Pipeline ready

cuGraphicsGLRegisterBuffer failed with error(219) gst_eglglessink_cuda_init texture = 1
0:01:02.130533255 13 0x556f253b16a0 WARN nvinfer gstnvinfer.cpp:2299:gst_nvinfer_output_loop:<primary_gie> error: Internal data stream error.
0:01:02.130550397 13 0x556f253b16a0 WARN nvinfer gstnvinfer.cpp:2299:gst_nvinfer_output_loop:<primary_gie> error: streaming stopped, reason not-negotiated (-4)
ERROR from primary_gie: Internal data stream error.
Debug info: gstnvinfer.cpp(2299): gst_nvinfer_output_loop (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
streaming stopped, reason not-negotiated (-4)
Quitting
ERROR from sink_bin_queue: Internal data stream error.
Debug info: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstQueue:sink_bin_queue:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux20: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin24/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin24/GstQTDemux:qtdemux20:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue20: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin24/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin24/GstMultiQueue:multiqueue20:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux21: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin20/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin20/GstQTDemux:qtdemux21:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue22: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin20/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin20/GstMultiQueue:multiqueue22:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux4: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin6/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin6/GstQTDemux:qtdemux4:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue3: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin6/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin6/GstMultiQueue:multiqueue3:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux22: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin23/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin23/GstQTDemux:qtdemux22:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue21: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin23/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin23/GstMultiQueue:multiqueue21:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux1: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin7/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin7/GstQTDemux:qtdemux1:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux10: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin9/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin9/GstQTDemux:qtdemux10:
streaming stopped, reason not-negotiated (-4)
ERROR from multiqueue8: Internal data stream error.
Debug info: gstmultiqueue.c(2357): gst_multi_queue_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin9/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin9/GstMultiQueue:multiqueue8:
streaming stopped, reason not-negotiated (-4)
ERROR from qtdemux28: Internal data stream error.
Debug info: qtdemux.c(6605): gst_qtdemux_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin25/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin25/GstQTDemux:qtdemux28:
streaming stopped, reason not-negotiated (-4)
App run failed

±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1267 G 4MiB |
| 0 N/A N/A 2094 G 4MiB |
±----------------------------------------------------------------------------+

Amycao · August 16, 2022, 1:50am

Please follow this to trouble shoot error: cuGraphicsGLRegisterBuffer failed with error(219) gst_eglglessink_cuda_init texture = 1

DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums

rdh · August 17, 2022, 2:40am

I was successful - thanks for the assistance. There was a lot in the referenced post, so I will try to detail what seemed to work.

I tried running nvidia-xconfig and verifying the the nvidia driver was selected. This gave me a black screen rather than an X11 gui, so I deleted the xorg.conf again to get the X11 gui working again.

I tried installing the mesa drivers to no effect on the “bare” or docker app run success. I still had the same errors after installation of these drivers.
sudo apt-get install mesa-common-dev libgl1-mesa-dev libglu1-mesa-dev

I tried to run prime-select and found it was not installed. So I installed it ran it and updated the ramfs:
sudo apt install nvidia-prime
prime-select nvidia
sudo update-initramfs -u
shutdown -r now

After the reboot the deepstream-app worked in both the “bare” installation and the docker.

rdh · August 17, 2022, 2:52am

I am reluctant to mark this as solved. It works for me now, but the root cause and the solution are not obvious to me.

rdh · September 5, 2022, 11:34pm

I am reasonably sure the the problem in the original post was due to not using prime-select. In a fresh install, although with different versions, I never installed the mesa libraries and resolved the problem with prime-select.

I ended up using the 515.65.01 driver through the Ubuntu packages and Docker version 19.03.15 and tested the deepstream-app in the NVIDIA provided docker containers.

system · September 19, 2022, 11:35pm

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.