How to run on jetson Xavier a custom project developed on GPU server

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

• Hardware Platform (Jetson / GPU)
nvidia GPU 2060 super
• DeepStream Version
5.0.1
• JetPack Version (valid for Jetson only)
• TensorRT Version
7.0.0
• NVIDIA GPU Driver Version (valid for GPU only)
460.39
• Issue Type( questions, new requirements, bugs)
question
• 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)
follow the steps I describe
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hello everyone.
I have been developing a deepstream application on a GPU server and now it is time to deploy it on Jetson.
Thing is there is no devel docker for jetson and there are some things I had to install on the development server, like https://github.com/NVIDIA-AI-IOT/deepstream_tlt_apps.

So, is there any docker image where all those tools and pluggins are already working or any tool for compiling libraryes and pluggins?
Can I cross-compile my projetc, pluggins, and libs on the server and then just copy them to the jetson?

Thank you.

3

no such docker provided, user need to do incrementally installation.

Jetson Linux API Reference: Setting Up Cross-Platform Support | NVIDIA Docs is a reference guide for compiling Jetson Multimedia Low Level SDK.
But, for cross-compiling DeepStream, in theory, yes, you can, but you will need to solve some link issues for that.

Thanks!