Gst-nvdsanalytics sample pipeline does not work

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I am trying to run the sample pipeline but its not working
The following pipelines demonstrate plugin’s usage.

•For dGPU:

gst-launch-1.0 filesrc location=streams/sample_1080p.mp4 ! qtdemux ! h264parse ! nvv4l2decoder ! m.sink_0 nvstreammux name=m width=1920 height=1080 batch-size=1 live-source=1 ! nvinfer config-file-path= config_infer_primary.txt ! nvtracker ll-lib-file = /opt/nvidia/deepstream/deepstream/lib/libnvds_nvdcf.so ll-config-file= tracker_config.yml tracker-width=640 tracker-height=384 ! nvdsanalytics config-file= config_nvdsanalytics.txt ! nvmultistreamtiler ! nvvideoconvert ! nvdsosd ! nveglglessink

root@mike:/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-nvdsanalytics-test# ll
total 372
drwxr-xrwx 1 root root 4096 May 8 08:10 ./
drwxr-xrwx 1 root root 4096 May 8 07:06 …/
-rw-r–rw- 1 root root 2143 Apr 27 13:33 Makefile
-rw-r–rw- 1 root root 3758 Apr 27 13:33 README
-rw-r–rw- 1 root root 1659 Apr 27 13:33 config_nvdsanalytics.txt
-rwxr-xr-x 1 root root 104304 May 8 07:14 deepstream-nvdsanalytics-test*
-rw-r–rw- 1 root root 17813 Apr 27 13:33 deepstream_nvdsanalytics_test.cpp
-rw-r–r-- 1 root root 217832 May 8 07:14 deepstream_nvdsanalytics_test.o
-rw-r–rw- 1 root root 3295 Apr 27 13:33 nvdsanalytics_pgie_config.txt
-rw-r–r-- 1 root root 0 May 8 08:20 nvof.mp4
-rw-r–rw- 1 root root 3233 Apr 27 13:33 tracker_config.yml
root@mike:/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-nvdsanalytics-test# gst-launch-1.0 filesrc location=/opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p.mp4 ! qtdemux ! h264parse ! nvv4l2decoder ! m.sink_0 nvstreammux name=m width=1920 height=1080 batch-size=1 live-source=1 ! nvinfer config-file-path= config_infer_primary.txt ! nvtracker ll-lib-file = /opt/nvidia/deepstream/deepstream/lib/libnvds_nvdcf.so ll-config-file= tracker_config.yml tracker-width=640 tracker-height=384 ! nvdsanalytics config-file=config_nvdsanalytics.txt ! nvmultistreamtiler ! nvvideoconvert ! nvdsosd ! nveglglessink
Failed to load config file: No such file or directory
**** ERROR: <gst_nvinfer_parse_config_file:1158>: failed**
Setting pipeline to PAUSED …
No protocol specified
No protocol specified
No protocol specified
No protocol specified
No protocol specified
ERROR: Pipeline doesn’t want to pause.
Got context from element ‘eglglessink0’: gst.egl.EGLDisplay=context, display=(GstEGLDisplay)NULL;
Setting pipeline to NULL …
Freeing pipeline …

can you please shed more information on the plugin. Do you have an example where its output can be written to a RTSP Stream.

3

Can deepstream-nvdsanalytics-test run well?

4

Yes I can. Thanks.

I am trying to combine test4 and nvdsanalytics and also trying to display using RTSP. Do you have any samples. I keep getting pipeline could not be made.

5

Hi
about plugin, you can refer to documentation,

about how the output written to rtsp stream, you can use deepstream-app, in config group sink, we have type 4: Encode + RTSP streaming, refer to this,
https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html#page/DeepStream_Development_Guide/deepstream_app_config.3.2.html#wwpID0ENHA
about error you met, Failed to load config file: No such file or directory
**** ERROR: <gst_nvinfer_parse_config_file:1158>: failed**
please check the config file path.

7

Hi,

A similar error occurred:

deepstream-app -c …/…/…/…/samples/configs/deepstream-app-trtis/source1_primary_detector.txt

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***

Failed to load config file: Key file contains line ?infer_config {? which is not a key-value pair, group, or comment
** ERROR: <gst_nvinfer_parse_config_file:1158>: failed
0:00:00.434796374 9027 0x55a2d5dd2a00 WARN nvinfer gstnvinfer.cpp:747:gst_nvinfer_start:<primary_gie> error: Configuration file parsing failed
0:00:00.434816632 9027 0x55a2d5dd2a00 WARN nvinfer gstnvinfer.cpp:747:gst_nvinfer_start:<primary_gie> error: Config file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app-trtis/config_infer_primary_detector_ssd_inception_v2_coco_2018_01_28.txt
** ERROR: main:651: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Configuration file parsing failed
Debug info: gstnvinfer.cpp(747): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
Config file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app-trtis/config_infer_primary_detector_ssd_inception_v2_coco_2018_01_28.txt
App run failed

This is due to the mismatch in the file format that is expected.

This is strange. I was able to run these apps on the NVIDIA Docker images. But, when I built these on the local machine, the above error occurs. Any input will be appreciated.

8

config in your local server and config within docker is same?

9

Hi,

The problem seems to be due to using “deepstream-app-trtis” config file for ‘standard’ (non Trtiton Inference Server) environment. Using a ‘standard’ “deepstream-app” config file solved the problem.

This is a very basic question:
The performance on a Ubuntu 18.04, with dGPU (RTX2080) is poor. %CPU is very high 50-70% where as %GPU is low 5%-7% as compared to running under the docker container on the same machine.

I couldn’t get any reference to do the setup (environmental variables, enabling CUDA etc on the NVIDIA Quick Start pages (of 5.0). I re-used some of the items from the docker container (5.0-x-3-devel) but that didn’t help.
Any suggestions or pointers on how to utilize the GPU on a Ubuntu system?

nvidia-smi provides this output for running it outside the container:

±----------------------------------------------------------------------------+
| NVIDIA-SMI 440.64.00 Driver Version: 440.64.00 CUDA Version: 10.2 |
|-------------------------------±---------------------±---------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce RTX 208… On | 00000000:09:00.0 Off | N/A |
| 52% 71C P2 120W / 250W | 2770MiB / 11018MiB | 12% Default |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 2220 G /usr/lib/xorg/Xorg 18MiB |
| 0 2358 G /usr/bin/sddm-greeter 33MiB |
| 0 6458 C ./deepstream-app 2576MiB |
±----------------------------------------------------------------------------+

Thanks in advance!

12

Hi deepak,

Please open a new topic for your issue. Thanks