# Quick Start Guide: NVIDIA Jetson with Ultralytics YOLOv8
This comprehensive guide provides a detailed walkthrough for deploying Ultralytics YOLOv8 on [NVIDIA Jetson](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/) devices. Additionally, it showcases performance benchmarks to demonstrate the capabilities of YOLOv8 on these small and powerful devices.
This guide has been tested with [Seeed Studio reComputer J4012](https://www.seeedstudio.com/reComputer-J4012-p-5586.html) which is based on NVIDIA Jetson Orin NX 16GB running the latest stable JetPack release of [JP5.1.3](https://developer.nvidia.com/embedded/jetpack-sdk-513). Using this guide for older Jetson devices such as the Jetson Nano (this only supports until JP4.6.4) may not be guaranteed to work. However this is expected to work on all Jetson Orin, Xavier NX, AGX Xavier devices running JP5.1.3.
NVIDIA Jetson is a series of embedded computing boards designed to bring accelerated AI (artificial intelligence) computing to edge devices. These compact and powerful devices are built around NVIDIA's GPU architecture and are capable of running complex AI algorithms and deep learning models directly on the device, without needing to rely on cloud computing resources. Jetson boards are often used in robotics, autonomous vehicles, industrial automation, and other applications where AI inference needs to be performed locally with low latency and high efficiency. Additionally, these boards are based on the ARM64 architecture and runs on lower power compared to traditional GPU computing devices.
[Jetson Orin](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/) is the latest iteration of the NVIDIA Jetson family based on NVIDIA Ampere architecture which brings drastically improved AI performance when compared to the previous generations. Below table compared few of the Jetson devices in the ecosystem.
| | Jetson AGX Orin 64GB | Jetson Orin NX 16GB | Jetson Orin Nano 8GB | Jetson AGX Xavier | Jetson Xavier NX | Jetson Nano |
For a more detailed comparison table, please visit the **Technical Specifications** section of [official NVIDIA Jetson page](https://developer.nvidia.com/embedded/jetson-modules).
## What is NVIDIA JetPack?
[NVIDIA JetPack SDK](https://developer.nvidia.com/embedded/jetpack) powering the Jetson modules is the most comprehensive solution and provides full development environment for building end-to-end accelerated AI applications and shortens time to market. JetPack includes Jetson Linux with bootloader, Linux kernel, Ubuntu desktop environment, and a complete set of libraries for acceleration of GPU computing, multimedia, graphics, and computer vision. It also includes samples, documentation, and developer tools for both host computer and developer kit, and supports higher level SDKs such as DeepStream for streaming video analytics, Isaac for robotics, and Riva for conversational AI.
## Flash JetPack to NVIDIA Jetson
The first step after getting your hands on an NVIDIA Jetson device is to flash NVIDIA JetPack to the device. There are several different way of flashing NVIDIA Jetson devices.
1. If you own an official NVIDIA Development Kit such as the Jetson Orin Nano Developer Kit, you can visit [this link](https://developer.nvidia.com/embedded/learn/get-started-jetson-orin-nano-devkit) to download an image and prepare an SD card with JetPack for booting the device.
2. If you own any other NVIDIA Development Kit, you can visit [this link](https://docs.nvidia.com/sdk-manager/install-with-sdkm-jetson/index.html) to flash JetPack to the device using [SDK Manager](https://developer.nvidia.com/sdk-manager).
3. If you own a Seeed Studio reComputer J4012 device, you can visit [this link](https://wiki.seeedstudio.com/reComputer_J4012_Flash_Jetpack) to flash JetPack to the included SSD.
4. If you own any other third party device powered by the NVIDIA Jetson module, it is recommended to follow command-line flashing by visiting [this link](https://docs.nvidia.com/jetson/archives/r35.5.0/DeveloperGuide/IN/QuickStart.html).
For methods 3 and 4 above, after flashing the system and booting the device, please enter "sudo apt update && sudo apt install nvidia-jetpack -y" on the device terminal to install all the remaining JetPack components needed.
Execute the below command to pull the Docker container and run on Jetson. This is based on [l4t-pytorch](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/l4t-pytorch) docker image which contains PyTorch and Torchvision in a Python3 environment.
Here we will install ultralyics package on the Jetson with optional dependencies so that we can export the PyTorch models to other different formats. We will mainly focus on [NVIDIA TensorRT exports](../integrations/tensorrt.md) because TensoRT will make sure we can get the maximum performance out of the Jetson devices.
The above ultralytics installation will install Torch and Torchvision. However, these 2 packages installed via pip are not compatible to run on Jetson platform which is based on ARM64 architecture. Therefore, we need to manually install pre-built PyTorch pip wheel and compile/ install Torchvision from source.
Visit the [PyTorch for Jetson page](https://forums.developer.nvidia.com/t/pytorch-for-jetson/72048) to access all different versions of PyTorch for different JetPack versions. For a more detailed list on the PyTorch, Torchvision compatibility, visit the [PyTorch and Torchvision compatibility page](https://github.com/pytorch/vision).
#### Install `onnxruntime-gpu`
The [onnxruntime-gpu](https://pypi.org/project/onnxruntime-gpu/) package hosted in PyPI does not have `aarch64` binaries for the Jetson. So we need to manually install this package. This package is needed for some of the exports.
All different `onnxruntime-gpu` packages corresponsing to different JetPack and Python versions are listed [here](https://elinux.org/Jetson_Zoo#ONNX_Runtime). However, here we will download and install `onnxruntime-gpu 1.17.0` with `Python3.8` support for the JetPack we are using for this guide.
Out of all the model export formats supported by Ultralytics, TensorRT delivers the best inference performance when working with NVIDIA Jetson devices and our recommendation is to use TensorRT with Jetson. We also have a detailed document on TensorRT [here](../integrations/tensorrt.md).
YOLOv8 benchmarks were run by the Ultralytics team on 10 different model formats measuring speed and accuracy: PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, TF SavedModel, TF Graphdef, TF Lite, PaddlePaddle, NCNN. Benchmarks were run on Seeed Studio reComputer J4012 powered by Jetson Orin NX 16GB device at FP32 precision with default input image size of 640.
### Comparison Chart
Eventhough all model exports are working with NVIDIA Jetson, we have only included **PyTorch, TorchScript, TensorRT** for the comparison chart below because, they make use of the GPU on the Jetson and are guaranteed to produce the best results. All the other exports only utilize the CPU and the performance is not as good as the above three. You can find benchmarks for all exports in the section after this chart.
The below table represents the benchmark results for five different models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x) across ten different formats (PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, TF SavedModel, TF Graphdef, TF Lite, PaddlePaddle, NCNN), giving us the status, size, mAP50-95(B) metric, and inference time for each combination.
!!! Performance
=== "YOLOv8n"
| Format | Status | Size on disk (MB) | mAP50-95(B) | Inference time (ms/im) |
Visit [this link](https://www.seeedstudio.com/blog/2023/03/30/yolov8-performance-benchmarks-on-nvidia-jetson-devices) to explore more benchmarking efforts by Seeed Studio running on different versions of NVIDIA Jetson hardware.
## Reproduce Our Results
To reproduce the above Ultralytics benchmarks on all export [formats](../modes/export.md) run this code:
Note that benchmarking results might vary based on the exact hardware and software configuration of a system, as well as the current workload of the system at the time the benchmarks are run. For the most reliable results use a dataset with a large number of images, i.e. `data='coco8.yaml' (4 val images), or `data='coco.yaml'` (5000 val images).
We can use jetson stats application to monitor the temperatures of the system components and check other system details such as view CPU, GPU, RAM utilization, change power modes, set to max clocks, check JetPack information
Congratulations on successfully setting up YOLOv8 on your NVIDIA Jetson! For further learning and support, visit more guide at [Ultralytics YOLOv8 Docs](../index.md)!
