Jetson AGX Orin Usage

[haitham.yaghi99]

Hi,

I started using the Jetson AGX Orin recently for a project that involves Deep Learning and Reinforcement Learning. However, I want to make sure if the Jetson AGX Orin is made for training the models, or is it made for deploying trained models?

Which approach is the most efficient:
1- Training and deploying the model on the Orin ?
2- Training the model on a different computer and deploying it on the Orin?

Thanks

[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!

[haitham.yaghi99]

Thanks for your reply, but that doesn’t clear my doubt.

I would like to know what is the main use of the Orin, is it supposed to be used for training or inference?

[kayccc]

Most customers use AGX Orin as edge computing for inference, of course it can be used for training but the RAM might be a concern than some other host machine.
There are many AI projects sharing at Latest Jetson & Embedded Systems/Jetson Projects topics - NVIDIA Developer Forums for your reference.

[jameskuo]

Maybe you can try TAO Toolkit, and deploy to Jetson.

Ref Link Here