Jetson AGX ORIN R36.4 unable to run imagenet inference example

[antoine.hamel]

Hi,

I’m trying to run imagenet example by following the Hello AI world example. The models seem to have been trained with caffe which is no longer supported by TensorRT > 10.3.

Since 36.4 is not yet available as a container I had to build from source.

I tried doing as suggested here but I get a segmentation fault when running the new suggested model :

Can't use any model with jetson-inference

I installed jetpack 6.1 on my jetson orin nano and trying to use jetson inference. I got this error: ./imagenet.py images/orange_0.jpg images/test/output_0.jpg imageNet -- loading classification network model from: -- prototxt networks/Googlenet/googlenet.prototxt -- model networks/Googlenet/bvlc_googlenet.caffemodel -- class_labels networks/ilsvrc12_synset_words.txt -- input_blob 'data' -- output_blob 'prob' -- batch_size …

I’m just trying to follow documentation but it seems outdated. Can anyone help?

[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!

[AastaLLL]

Hi,

JetPack 6.1 includes TensorRT 10.3 which removes the caffe parser support.
So imagenet with the caffe model cannot work.

Thanks.

[vishnuvermaverma5]

Hi @antoine.hamel,
I am also getting same error.
If you have resolved the error pls tell how to do that.

[antoine.hamel]

Hi @vishnuvermaverma5 I reflashed the jetson with 6.0 (r36.3) on which the examples run fine.

As @AastaLLL said Tensot RT 10.3 doesn’t support caffee models so the imagenet example doesn’t work with JetPack6.1.

[AastaLLL]

Hi, both

Yes, as TensorRT 10.3 drops Caffe model support.
To use jetson-inference with the default model, please try to set up the device with JetPack 6.0.

Thanks.