Running PeopleNet on x86 with Jetson Inference Container

lars.gerber · August 23, 2024, 11:14am

Hey, I have a project where I want to run Automatic labeling of people on images. I Have it running on my Jetson device. I am using the pre trained PeopleNet. Now I want to also have it running on my normal linux PC with a 1080ti. I did build the docker container but it can not load PeopleNet.
jetson.inference – detectNet loading build-in network ‘peoplenet’
jetson.inference – detectNet invalid built-in network was requested (‘peoplenet’)
Traceback (most recent call last):
File “Automatic_Labeling.py”, line 85, in
results = detect_people_in_image(image)
File “Automatic_Labeling.py”, line 50, in detect_people_in_image
net = detectNet(“peoplenet”, threshold=0.01)
Exception: jetson.inference – detectNet invalid built-in network was requested

I also tried to load PeopleNet (deployable_quantized_onnx_v2.6.2) myself and then transform it with trtexec to a .engine file but there I only had empty boundinboxes and no detections.
Can you support me in this topic? You can also tell me if there is a better option to do this project.

AastaLLL · August 26, 2024, 4:18am

Hi,

Could you checkout the x86 branch and try it again?

Thanks.

lars.gerber · September 19, 2024, 2:42pm

Hi,
so as explained I am using my own container. I build it with the base image from Dusty for amd64. (with dustynv/jetson-inference:22.06)
I need this because I need to install some company related stuff. When I understand it correctly it should download peoplenet by itself when I call it, or do I miss understand something? I also don’t understand why I should clone the git site.

Sorry for the late awnser I was on vaccation.

AastaLLL · September 26, 2024, 6:42am

Hi

Models are downloaded by CMakePreBuild.sh script.
If it doesn’t download automatically, would you mind running it manually?

github.com

dusty-nv/jetson-inference/blob/master/docs/building-repo-2.md#configuring-with-cmake

<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
<p align="right"><sup><a href="aux-docker.md">Back</a> | <a href="imagenet-console-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
<br/>
<sup>System Setup</sup></p>   

# Building the Project from Source

Once your Jetson has has been [flashed with JetPack](jetpack-setup-2.md) or setup with the latest [SD card image](https://developer.nvidia.com/embedded/learn/get-started-jetson-nano-devkit#write), you should be able to either run the pre-built [Docker container](aux-docker.md), or compile jetson-inference from source.  Either option is also able to install PyTorch for you.

## Quick Reference

If you aren't using the [Docker container](aux-docker.md), here's a condensed form of the commands to build/install the project directly on your Jetson:

``` bash
sudo apt-get update
sudo apt-get install git cmake libpython3-dev python3-numpy
git clone --recursive --depth=1 https://github.com/dusty-nv/jetson-inference
cd jetson-inference
mkdir build
cd build

This file has been truncated. show original

Thanks.

system · October 23, 2024, 5:07am

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

Topic		Replies	Views
Jetson orin nano peoplenet inference Jetson Orin Nano jetson-inference	2	38	August 14, 2024
Jetson-inference detectnet.py --model=peoplenet , no engine file Jetson Xavier NX jetson-inference	11	597	February 13, 2024
Use jetson-inference TensorRT to infer from custom models like PeopleNet Jetson Nano tensorrt , jetson-inference	8	824	October 18, 2021
Cannot load custom trained or pre-trained models from x86 jetson-inference docker container Jetson Nano jetson-inference , docker , platform-x86_64	8	50	August 12, 2024
Run peoplenet on python virtual environment without jetson TAO Toolkit tensorrt	29	1151	January 20, 2024
How to run purpose built model Peoplenet on Jetson Nano in my own application? TAO Toolkit tensorrt	11	3683	September 7, 2021
sudo make install Jetson TX2	1	489	August 20, 2019
Unable to build jetson-inference code in Jetson Nano B01 board Jetson Nano jetson-inference	2	385	January 18, 2023
Update the docs for deepstream_tao_apps DeepStream SDK nvbugs , python , documentation , inference-server-triton , tao , deepstream	4	56	November 18, 2024
Deploy PeopleNet into existing Python Application Jetson Xavier NX	2	654	October 18, 2021

Running PeopleNet on x86 with Jetson Inference Container

Related topics