Packaging Custom Code for Jetson Devices in Production: A deploying package that maintains Optimal Performance and Security

Robotics & Edge Computing Jetson & Embedded Systems Jetson Orin NX
,
1

Hardware: Jetson Orin
Use Case: Multiple Model Integration (Detection, Segementation, Classification, etc.)

Hello,

I am studying and exploring the best ways to package the custom code for deployment on Jetson devices, particularly for use in production environments where performance is critical.

Context:
As newcomers to the Jetson platform, i am aiming to integrate custom code onto Jetson devices in a secure and efficient manner. I want to ensure that the code performance and securely packaged for production-line deployment.

If there are any recommended methods or best practices for creating packages for Jetson devices, please share your insights.

Thank you in Advance!

3

Hi,

Please check the below page for some info:

https://docs.nvidia.com/jetson/archives/r36.3/DeveloperGuide/SD/Security.html

Thanks.

4

Thank you for the response,
Currently started working on deploying code files, wanted to know is gstreamer pipeline or deepstream app is better or any other format w.r.t engine file.

5

Hi,

For performance, please try Deepstream SDK.
You might also be insterested in Jetson platform services :

https://docs.nvidia.com/jetson/jps/moj-overview.html

Thanks.

7

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