Jetson Community Resources
Explore and learn from Jetson resources created our by our community. These have been created for Jetson developer kits. For more platform and design documentation, please visit our Support Resources page.
Create your own image for Jetson Nano board
Pythops
This article will guide you step by step to create a minimalist Ubuntu based image for your NVIDIA Jetson nano board that best suits your project.
jetson-nano-gpio-example
Jon Watte
GPIO addresses are physical memory addresses, and a regular process runs in a virtual memory address. You need to arrange for those physical addresses to show up as know virtual addresses in the address space of the process, OR you need to run in kernel space in some mode that uses physical addressing (not generally recommended or even always possible.) Using GPIO through sysfs (the /sys/class/gpio "files") is clearly simpler for a user-level program, but also incurs the system call overhead for each operation on each GPIO pin, so for code with very low latency requirements, that may not work out so well.
Getting Started with the NVIDIA Jetson Nano
DroneBot Workshop
Today we will look at the NVIDIA Jetson Nano Developer Kit, a low-cost platform for developing Artificial Intelligence (AI) applications. I’ll show you how to get started with the Jetson Nano.
Getting Started with Jetson Nano
Adrian Rosebrock, PyImageSearch
In this tutorial, you will learn how to get started with your NVIDIA Jetson Nano, including: First boot Installing system packages and prerequisites Configuring your Python development environment Installing Keras and TensorFlow on the Jetson Nano Changing the default camera Classification and object detection with the Jetson Nano
Deploy GPU-enabled Kubernetes Pod on NVIDIA Jetson Nano
Jerry Liang
NVIDIA Jetson Nano delivered GPU power in an amazingly small package. I finally got mine in the mailbox and couldn’t wait to add it to my Raspberry Pi K8s cluster to take up GPU workload. It turned out however, I had to jump through a couple of hoops to get it working. In this blog post, I will walk through the steps needed and hope it will help you to get it working.
Serial Console
Jim Benson, JetsonHacks
A Serial Console is a useful tool for embedded development, remote access, and those times when the development kit has issues that you need to observe.
Run on USB Drive
Jim Benson, JetsonHacks
Using a USB Drive as the root file system on a Jetson Nano Developer Kit provides many advantages, including faster disk access and more storage.
jetson-thermal-monitor
Tsutomu Furuse
Real-time plot of temperatures from NVIDIA Jetson on-module thermal sensors. This script is tested on NVIDIA Jetson Nano Developer Kit only.
Jetson Build Assistant Scripts
jtagxhub
After you download lots of files through JetPack-L4T-xxx-linux-x64-yyy.run
or sdkmanager
, you need to download toolchains, kernel source code, in addition to shortcuts for building code, flash images, etc. These scripts set up development environments and provide handy commands.
jetsonXavierGPIO
gaosiy
A straightforward C/C++ library to interface with NVIDIA Jetson AGX Xavier Development Kit GPIO pins.
Run Jetson Nano on USB Drive
Jim Benson, JetsonHacks
You can setup your Jetson Nano to run from a USB Drive in less than 10 minutes! This update video saves 45 minutes from our previous method.
jetson_xavier_canbus
An Nguyen
Tools and scripts to enable canbus on NVIDIA Jetson AGX Xavier.
jetson_clocks
Jordan Ford
jetson_clocks.hpp
is a single header C++ library for controlling the various power states of the NVidia Jetson Nano, Jetson TX1, Jetson TX2(i), and Jetson AGX Xavier.
Ubuntu Core for Jetson TX1/TX2/Nano/Xavier
Alfonso Sánchez-Beato
This repository contains scripts to create a tarball with all what is needed to flash Ubuntu Core 18 in a Jetson TX1/TX2/Nano/Xavier device.
jetson-nano-gpio-example
Jon Watte
GPIO addresses are physical memory addresses, and a regular process runs in a virtual memory address. You need to arrange for those physical addresses to show up as known virtual addresses in the address space of the process, OR run in kernel space in a mode that uses physical addressing (not generally recommended or even always possible). GPIO through sysfs
is clearly simpler for a user-level program, but also incurs the system call overhead for each operation on each GPIO pin.
jw-boot-logo-for-Jetson-Nano
Vladimir Sazonov
This is a modified jw-boot-logo for creation bmp.blob for JetsonNano. You must have lz4c installed for use this
torch2trt
torch2trt is a PyTorch to TensorRT converter which utilizes the TensorRT Python API. The converter is:
- Easy to use - Convert modules with a single function call torch2trt
- Easy to extend - Write your own layer converter in Python and register it with
@tensorrt_converter
TensorRT Pose Estimation
John Welsh, NVIDIA
This project features multi-instance pose estimation accelerated by NVIDIA TensorRT. It is ideal for applications where low latency is necessary. It includes
- Training scripts to train on any keypoint task data in MSCOCO format
- A collection of models that may be easily optimized with TensorRT using torch2trt
This project can be used easily for the task of human pose estimation, or extended for something new. If you run into any issues please let us know.
Deploying Deep Learning
Dustin Franklin, NVIDIA
Guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson. This repo uses NVIDIA TensorRT for efficiently deploying neural networks onto the embedded Jetson platform, improving performance and power efficiency using graph optimizations, kernel fusion, and FP16/INT8 precision.
TensorRT Python Sample for Object Detection
Aasta Lin, NVIDIA
Python sample for referencing object detection model with TensorRT. Performance includes memcpy and inference.
DeepSpeech for Jetson Nano
Dominik (domcross)
Wheels for tensorflow and DeepSpeech compiled for NVidia Jetson Nano (arm64) tensorflow 1.14.1 with Cuda 10.0 and GPU 5.3 support
Jetson-TX2-Install-Caffe
wheslyx
Installing Caffe v1 official release from BVLC in embedded device NVIDIA Jetson TX2 8GB with JetPack L4T 4.2 as updated as August 2019 release.
How to deploy ONNX models on NVIDIA Jetson Nano using DeepStream
Bharath Raj
Deploying complex deep learning models onto small embedded devices is challenging. Even with toptimized hardware optimized for deep learning such as the Jetson Nano and inference optimization tools such as TensorRT, bottlenecks can still [appear] in the I/O pipeline. [...] Wouldn’t it be great to have a tool that can take care of all bottlenecks in an end-to-end fashion?
Jetson Nano: Vision Recognition Neural Network Demo
Christopher Barnatt, ExplainingComputers.com
Jetson Nano performing vision recognition on a live video stream using a deep neural network (DNN). This video is based on the "Hello AI World" demo provided by NVIDIA for their Jetson boards, and employs a Raspberry Pi V2 camera.
Apriltag_pose_ros
yuannuaa
This is a ROS wrapper for publishing Apriltag with Jetson Nano and RPI camera through CSI. It is truly easy to use.
Jetbot ROS2 Package
Richard Osterloh
Using this package, set your JetBot to use ROS2 Dashing, grant user access to the i2c bus and enable teleop.
ORB_SLAM2_CUDA
Thien Nguyen
Modified version of ORB-SLAM2 with GPU enhancement and several ROS topics for NVIDIA Jetson. Currently only supports Monocular camera. Run in real time.
darknet_det
Maoxu Li
Darknet YOLO, ROS, gstreamer/gscam, CSI camera, Jetson TX2/Nano, Raspberry PI.
Jetson Nano + Raspberry Pi Camera
Jim Benson, JetsonHacks
Since the introduction of the first Jetson in 2014, one of the most requested features has been Raspberry Pi camera support. The Jetson Nano has built in support, no finagling required. This guide shows you how.
NVIDIA Deepstream + Azure IoT Edge on a NVIDIA Jetson Nano
Azure Samples
Perform real-time video analytics, running deep neural networks with NVIDIA Deepstream on a Jetson Nano device connected to Azure via Azure IoT Edge. DeepStream SDK is a must-have tool whenever you have complex video analytics requirements; whether it's real-time or with cascading AI models. IoT Edge gives you the possibility to run this pipeline next to your cameras, thus lowering your bandwitch costs and enabling scenarios with poor internet connectivity or privacy concerns.
Getting Started with ZED stereo camera on Jetson Nano
StereoLabs
How can a robot be autonomous without perceiving the world? The ZED and ZED Mini 3D depth cameras are the ideal companions for a Jetson Nano and ROS-powered robot.
CircuitPython Libraries on Linux and the NVIDIA Jetson Nano
M. LeBlanc-Williams, Adafruit
Make hardware and interface with sensors super easy using CircuitPython. CircuitPython adds the Circuit part to the Python part. Letting you program in Python and talk to Circuitry like sensors, motors, and LEDs!
Jetson Nano + Intel Wifi and Bluetooth
Jim Benson, JetsonHacks
The NVIDIA Jetson Nano Developer Kit does not include a wifi module. Fortunately there is a connector to easily add one! The connector is M.2 Key E, located underneath the Jetson Nano Module.
You Too Can Have a Sub-$200 .11ax Client (Using Jetson Nano)
John Kilpatrick
"I know that some of us right now have 802.11ax-capable APs. But having APs with no clients isn’t fun, and for testing (and fun) having a real AX client or two is awesome. If you get two of them you have a chance of seeing OFDMA over the air. […] when I saw how the Jetson Nano has an M.2 slot it got me thinking. The 8265 works well with it but we wondered about getting the AX200 to work. Turns out it was pretty easy."
Use More Power!
Jim Benson, JetsonHacks
You need to get all the power out of your Jetson Nano Developer Kit.
Use More Memory!
Jim Benson, JetsonHacks
The NVIDIA Jetson Nano Developer Kit has 4 GB of main memory. This may not enough memory for running many of the large deep learning models, or compiling very large programs. Let’s fix that! We are going to install a swapfile.
Automount Drive
Jim Benson, JetsonHacks
There are times when you need to have your external drives mounted when the Jetson Nano boots. Let’s go over it!
Jetson Nano Kinect2 Python
Joev Valdivia
These are the steps I took to get the Kinect2 to run on Jetson Nano. These steps will let you run the Kinect2 in C++ and Python.