Upgrading to TensorRT 8.5.3.1 from TensorRT 8.4.1.5 on Jetson XAVIER NX (JetPack 5.02)

Autonomous Machines Jetson & Embedded Systems Jetson Xavier NX
1

Description

I have a follow up question to this thread.

I have Jetson Xavier with Jetpack 5.02.

I followed the nvidia/tensorrt git link so setup the docker container in my ubuntu system and created the required onnx and tensorrt file.
My tensorrt version in that docker container was 8.5.3.1 while it is 8.4.1.5 in the jetson.
Is there anyway to upgrade my tensorrt version?

Environment

TensorRT Version: 8.4.1.5:
Graphics: NVIDIA Tegra Xavier (nvgpu)/integrated:
Processor: ARMv8 Processor rev 0 (v8l) × 2:

Jetpack Information

Package: nvidia-jetpack
Version: 5.0.2-b231
Architecture: arm64
Maintainer: NVIDIA Corporation
Installed-Size: 194
Depends: nvidia-jetpack-runtime (= 5.0.2-b231), nvidia-jetpack-dev (= 5.0.2-b231)

Relevant Files

TensorRT github page: GitHub - NVIDIA/TensorRT: NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.

If something is unclear, kindly let me know.
Thank you in advance.

2

Hi,

This looks like a Jetson issue. Please refer to the below samples in case useful.

For any further assistance, we will move this post to to Jetson related forum.

Thanks!

4

I apologize. I have set the tags correctly this time and have also edited my question with few more details.
I would appreciate the help, thank you.

6

Hi,

Only TensorRT 8.5.2 is available for Jetson.
To do so, you can set up the XavierNX with JetPack 5.1:

Thanks.

1 Like
7

Thanks, I’ll give that a try.

8

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