Modify device tree and add new camera config

[congthuong2512]

Hello everyone,

I work with GMSL cameras - STURDeCAM31 - 3MP on Orin AGX board - MIC-733-AO.

The thing is that I am not clear on the way to use cameras although I read all the documents for several days.

Here are my concerns:

• How to write the device tree and the source file for my camera? The camera sensor is ISX301, it is supported by Nvidia. I check it from here: Jetson Partner Supported Cameras | NVIDIA Developer. However, I don’t know how to get the device tree as well as the camera source files.

• What are the steps to compile and load the device tree to Orin AGX? I have a built jetpack for Orin AGX board - MIC-733-AO from Advantech (the company sold the board to us). However, I cannot find the example camera device tree .dtsi in that jetpack. On the other hand, I downloaded the source file of jetpack in Nvidia and saw the device tree file in a folder like this: </kernel_src/hardware/nvidia/platform/t23x/concord/kernel-dts/cvb/tegra234-p3737-0000-camera-ar0234-a00.dtsi>. So do I need to build the jetpack from source file and flash to my AGX Orin?

I am currently using Jetpack 35.2.1 with Orin AGX.

I appreciate any help and support, please help me!

Thank you very much!

[carolyuu]

Hi,
Here are some suggestions for the common issues:

1. Performance

Please run the below command before benchmarking deep learning use case:

$ sudo nvpmodel -m 0
$ sudo jetson_clocks

2. Installation

Installation guide of deep learning frameworks on Jetson:

• TensorFlow: Installing TensorFlow for Jetson Platform - NVIDIA Docs
• PyTorch: Installing PyTorch for Jetson Platform - NVIDIA Docs
  We also have containers that have frameworks preinstalled:
  Data Science, Machine Learning, AI, HPC Containers | NVIDIA NGC

3. Tutorial

Startup deep learning tutorial:

• Jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson
• TensorRT sample: Jetson/L4T/TRT Customized Example - eLinux.org

4. Report issue

If these suggestions don’t help and you want to report an issue to us, please attach the model, command/step, and the customized app (if any) with us to reproduce locally.

Thanks!

[congthuong2512]

Thank you for your quick responses!

I can use deep learning models as well as TensorRT properly. However, I have concerns with using GMSL cameras.

[nagesh_accord]

@congthuong2512

What are the steps to compile and load the device tree to Orin AGX?

https://docs.nvidia.com/jetson/archives/r35.2.1/DeveloperGuide/text/SD/Kernel/KernelCustomization.html

https://docs.nvidia.com/jetson/archives/r35.2.1/DeveloperGuide/text/SD/CameraDevelopment/CameraSoftwareDevelopmentSolution.html

check if these links helps…