Enquiry About Using PyTorch on Jetson for GPU Inference

Autonomous Machines Jetson & Embedded Systems Jetson AGX Xavier
1

Hello,
I am reaching out to inquire about the possibility of performing inferences on Jetson hardware using a PyTorch model, but without employing a DeepStream pipeline, while being able to take advantage of the GPU cores.

Thank you in advance for your support!

3

Hi,

It’s possible.

On Jetson, we recommended to use TensorRT for inference.
We have several examples that deploy a PyTorch model with TensorRT in the below link:

Thanks.

1 Like
5

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