Request for information regarding Deepstream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Actually I just want the tutorials to run the samples of the deepstream

I am using:
Jeston Orin Nano with Jetpack 6.x
with Deepstream 7.1

2

Hi,

NVIDIA DeepStream SDK Documentation

Sample Apps

Running DeepStream Samples

For DeepStream 7.x, the samples are located in:

/opt/nvidia/deepstream/deepstream-7.0/samples/

To run a sample app like deepstream-test1, just do:

deepstream-test1-app /opt/nvidia/deepstream/deepstream-7.0/samples/configs/deepstream-app/source1_usb_dec_infer_resnet_int8.txt

Each sample (test1, test2, etc.) demonstrates a different pipeline feature. Their configs are under:

/opt/nvidia/deepstream/deepstream-7.0/samples/configs/deepstream-app/
4

Take test1 as an example， Other samples are similar, and there is a README in the corresponding directory.

cd /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test1/

make CUDA_VER=12.6

./deepstream-test1-app /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
5

Actually While building the test scripts I am getting errors while executing with the sample videos

6

Please refer to README/ to check the Jetpack version. If you have other questions, please provide detailed logs for forum support.

7

jetson@jetson-desktop:/opt/nvidia/deepstream/deepstream-7.1/sources/apps/sample_apps/deepstream-opencv-test$ ./deepstream-opencv-test -t inferserver file:///opt/nvidia/deepstream/deepstream-7.1/samples/streams/video1.mp4
Using nvinferserver as the inference plugin
One element could not be created. Exiting.

This are the logs and I am trying to run the Deepstream-OpenCV-test sample

8

nvinfer is recommended.

If you need to use nvinferserver, please install triton first and build the engine file.

/opt/nvidia/deepstream/deepstream/samples/triton_backend_setup.sh

/opt/nvidia/deepstream/deepstream/samples/prepare_ds_triton_model_repo.sh

In addition, because triton depends on boost, but the boost download link is no longer valid, please refer to the FAQ below to modify the triton installation script

9

Can you give me the details of entire process or some source to refer for the process?

10

Please refer to this documentation locate at
/opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app-triton/README

Use docker image is another option.

docker run -it --rm --network=host --runtime nvidia  -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-7.1 -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream-l4t:7.1-triton-multiarch

For those unfamiliar with DeepStream, start with nvinfer. Deploying nvinferserver is more complex.

11

jetson@jetson-desktop:/opt/nvidia/deepstream/deepstream-7.1/samples$ sudo patch triton_backend_setup.sh < setup.patch
patching file triton_backend_setup.sh
Hunk #1 FAILED at 31.
1 out of 1 hunk FAILED – saving rejects to file triton_backend_setup.sh.rej

This is the error I am facing during patching the triton_backend_setup.sh script file with the new setup patch

12

Alternatively, you can open triton_backend_setup.sh with vim or vscode and edit it as shown below:

-wget -O ${TRITON_DOWNLOADS}/boost.tar.gz https://boostorg.jfrog.io/artifactory/main/release/1.80.0/source/boost_1_80_0.tar.gz
+wget -O ${TRITON_DOWNLOADS}/boost.tar.gz https://archives.boost.io/release/1.80.0/source/boost_1_80_0.tar.gz
13

Even after changing the backend script.sh I am getting the same error
jetson@jetson-desktop:~$ cd /opt/nvidia/deepstream/deepstream-7.1/samples/
jetson@jetson-desktop:/opt/nvidia/deepstream/deepstream-7.1/samples$ vim triton_backend_setup.sh
jetson@jetson-desktop:/opt/nvidia/deepstream/deepstream-7.1/samples$ sudo patch triton_backend_setup.sh < setup.patch
[sudo] password for jetson:
patching file triton_backend_setup.sh
Hunk #1 FAILED at 31.
1 out of 1 hunk FAILED – saving rejects to file triton_backend_setup.sh.rej