Note: From August 2023 onwards, this MakerDisk microSD card is preloaded with JetPack 5.1.2 for Nvidia Jetson Orin Nano 8GB Dev Kit. Please DO NOT format the microSD card.
No eMMC is included on the Nvidia Jetson Orin Nano Module, this provides flexibility for the developer to choose the preferred storage size and type, for example, microSD card or NVMe SSD. Nvidia recommends booting from a microSD card with JetPack 5.1.2 OS. You can download the image and load it into a microSD card. However, the JetPack 5.1.2 image itself is >7GB, you will need high-speed Internet to download it, and 15 to 30 minutes (depending on USB port and microSD card adapter) or so just to load and verify the image into a microSD card. We have done the hard work for you. This is a MakerDisk 128GB, Class 10, U3, V30, UHS-1, A1 grade microSD card, preloaded JetPack 5.1.2, ready to boot up on the Jetson Orin Nano Dev board. Please DO NOT format it if you intend to use it with the board.
If you are using the 128GB microSD card with preloaded JetPack with NVIDIA Jetson Orin Nano Dev kit, please follow the Getting Started Guide (official from Nvidia), starting from "Setup and First Boot". Please DO NOT format this microSD Card, it is preloaded with JetPack 5.1.2.
Note: Once the microSD card with JetPack is bootup (1st boot), please proceed with the initial setup which includes: Review and accepting NVIDIA Jetson Software EULA, selecting system language, keyboard layout, and time zone, connecting to a wireless network (optional), create a username, password, and computer name, and login. Then you can shut it down properly. Please DO NOT power off without proper shutdown from the Desktop. It will corrupt the JetPack image in the microSD card.
It takes only ~71 seconds (1 minute & 11 seconds) to boot into the login screen. You will need to do some initial setup for the 1st boot.
Note: It is normal for the screen to go blank and the fan stops during the boot-up process.
The boot page looks like this:
You will see this configuration page once the Jetson Orin Nano boots up. You can now proceed with the initial setup which includes: Review and accepting NVIDIA Jetson Software EULA, selecting system language, keyboard layout, and time zone, connecting to a wireless network (optional), create a username, password, and computer name, and login.
And tadaaaa~
There you have it, the Jetson Orin Nano desktop!
Many NVIDIA Jetson Dev Kit users have a common doubt: What type of microSD card is best for the boards? Well, we have been asking the same question since day 1:) We recommend Class A1 because of the characteristic of Nvidia accessing the memory on the microSD card. The random read and write speed is critical. For details on Class A1, please refer here.
"But more and more, memory cards are being used to extend the memory of devices that run apps. Devices like smartphones and mobile gaming consoles. The apps that run on these devices interact with memory space differently. Rather than a stream of sequential data, they want to write a lot of small chunks of data wherever there's space available. That's known as random read/write (compared to sequential read/write that's important for video)." Nvidia Jetson falls into the operating system and will need to read/write data from/to the microSD card in random access.
The MakerDisk microSD card has also gone through a special lifespan test by Raspberry Pi Foundation. Here is the methodology:
"Each card under test is loaded with a custom image containing up-to-date Buster (Raspberry Pi OS) image, automated stress test scripts and a local website to be accessed using Google Puppeteer automation. The host Raspberry Pi 4 Model B is powered by a custom PSU allowing the 5V1 input power to be cut as required. Up to fifty of these RPis can be run in a self-contained soak/stress rig.
On power up the RPi boots the image and autoruns a python-based test script. It first loads the standard Raspberry Pi Diagnostics test and logs the output to both the microSD card under test and optionally a plugged-in USB memory stick. During this operation, the PSU status indicator is held on constantly. Once this test has completed a random power-on time is set (between 60 and 300 seconds). This number is also logged to a second file so both the number of reboots and total run time can be determined later on. The MicroSD card is now exercised both by Google Puppeteer accessing multiple web pages from the Card and also a separate script creating, copying, and deleting multiple random length files. The PSU status indicator flashes twice a second during this time. Failed MicroSD cards can be quickly noted by the absence of this indicator light showing the RPi has failed to successfully boot from the card.
The MicroSD card activity above continues as the power is cut. Power is held off for a second, the Pi reboots and the process starts again."
The sample MakerDisk microSD cards have gone through more than 4,000 times of random power interrupts and the speed tests show very good results. Superb!
This MakerDisk microSD card comes pre-loaded with JetPack 5.1.2 for Jetson Orin Nano Dev Kit, so it can boot up on the Jetson Orin Nano Dev kit right out of the box. Please DO NOT format it. If you want to load other Operating Systems, we would recommend getting the Raspberry Pi Imager or BalenaEtcher and choosing the preferred Operating System into the microSD card.
Note: If you need a USB microSD card reader/writer, get it from here.
JetPack 5.1.2 is the latest production release by Nvidia and supports all Jetson Orin modules.
Key features in Jetpack 5.1.2:
- Jetson Linux:
- NVIDIA Jetson Linux 35.4.1 provides the Linux Kernel 5.10, UEFI-based bootloader, Ubuntu 20.04-based root file system, NVIDIA drivers, necessary firmware, toolchain, and more.
- JetPack 5.1.2 includes Jetson Linux 35.4.1 which adds the following highlights: (Please refer to release notes for additional details)
- Adds support for Jetson AGX Orin Industrial module
- Bootloader
- Camera:
- Enhanced error resiliency for improved stability in Argus
- Support for multiple camera synchronization (sample argus_syncstereo added)
- Deskew calibration support for high data rate sensors (> 1.5 Gbps)
- Support for alternating exposures in Argus (sample argus_userAlternatingAutoexposure added)
- Multimedia:
- Security:
- Over the Air Updates:
- TensorRT:
- TensorRT is a high-performance deep learning inference runtime for image classification, segmentation, and object detection neural networks. TensorRT is built on CUDA, NVIDIA’s parallel programming model, and enables you to optimize inference for all deep learning frameworks. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications.
- JetPack 5.1.2 includes TensorRT 8.5.2
- DLA:
- NVIDIA DLA hardware is a fixed-function accelerator engine targeted for deep learning operations. It's designed to do full hardware acceleration of convolutional neural network, supporting various layers such as convolution, deconvolution, fully connected, activation, pooling, batch normalization, and others
- DLA software consists of the DLA compiler and the DLA runtime stack. The offline compiler translates the neural network graph into a DLA loadable binary and can be invoked using NVIDIA TensorRT. The runtime stack consists of the DLA firmware, kernel mode driver, and user mode driver.
- Jetpack 5.1.2 includes DLA 3.12.1
- cuDNN:
- CUDA Deep Neural Network library provides high-performance primitives for deep learning frameworks. It provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers.
- JetPack 5.1.2 includes cuDNN 8.6.0
- CUDA:
- CUDA Toolkit provides a comprehensive development environment for C and C++ developers building GPU-accelerated applications. The toolkit includes a compiler for NVIDIA GPUs, math libraries, and tools for debugging and optimizing the performance of your applications.
- JetPack 5.1.2 includes CUDA 11.4.19
- Starting with JetPack 5.0.2, upgrade to the latest and greatest CUDA releases from CUDA 11.8 onwards without the need to update Jetson Linux other JetPack components. Refer to the instructions in the CUDA documentation on how to get the latest CUDA on JetPack.
- Multimedia API:
- The Jetson Multimedia API package provides low level APIs for flexible application development.
- Camera application API: libargus offers a low-level frame-synchronous API for camera applications, with per-frame camera parameter control, multiple (including synchronized) camera support, and EGL stream outputs. RAW output CSI cameras needing ISP can be used with either libargus or GStreamer plugin. In either case, the V4L2 media-controller sensor driver API is used.
- Sensor driver API: V4L2 API enables video decode, encode, format conversion and scaling functionality. V4L2 for encoding opens up many features like bit rate control, quality presets, low latency encode, temporal tradeoffs, motion vector maps, and more.
- JetPack 5.1.2 Camera highlights include:
- Enhanced error resiliency for improved stability in Argus
- Support for multiple camera synchronization (sample argus_syncstereo added).
- Deskew calibration support for high data rate sensors (> 1.5 Gbps)
- Support for alternating exposures in Argus (sample argus_userAlternatingAutoexposure added)
- Computer Vision:
- VPI (Vision Programing Interface) is a software library that provides Computer Vision / Image Processing algorithms implemented on multiple hardware accelerators found on Jetson such as PVA (Programmable Vision Accelerator), GPU, NVDEC(NVIDIA Decoder), NVENC (NVIDIA Encoder), VIC (Video Image Compositor) and so on.
- OpenCV is an open-source library for computer vision, image processing and machine learning.
- JetPack 5.1.2 includes VPI 2.3 with following highlights:
- New Brute Force Matcher algorithm supported on CPU and GPU backends
- New Transform Estimator algorithm supported on CPU backend
- JetPack 5.1.2 includes OpenCV 4.5.4
- Graphics:
- JetPack 5.1.2 includes the following graphics libraries:
- Vulkan® 1.3 (including the Roadmap 2022 Profile).
- Vulkan® SC 1.0
- Vulkan SC is a low-level, deterministic, robust API that is based on Vulkan 1.2. This API enables state-of-the-art GPU-accelerated graphics and computation that can be deployed in safety-critical systems and that are certified to meet industry functional safety standards. Refer to https://www.khronos.org/vulkansc/ for more information.
- Vulkan SC can also be invaluable for real-time non safety-critical embedded applications. Vulkan SC increases determinism and reduces application size by shifting preparation of the run-time application environment either offline or into application setup, as much as possible. This includes an offline compilation of graphics pipelines that define how the GPU processes data, together with static memory allocation, that together enable detailed GPU control that can be rigorously specified and tested.
- Vulkan SC 1.0 is evolved from Vulkan 1.2 and includes: the removal of runtime functionality that is not needed in safety-critical markets, an updated design to provide predictable execution times and results, and clarifications to remove potential ambiguity in its operation. For more details see https://www.khronos.org/blog/vulkan-sc-overview
- Note: Jetson support for Vulkan SC is NOT safety certified.
- OpenWF™ Display 1.0
- OpenWF Display is a Khronos API for low overhead interaction with the native display driver on Jetson and allows interaction with Vulkan SC to display images.
- Note: Jetson support for OpenWF Display is NOT safety certified.
- Nsight Developer Tools:
- CUDA Toolkit provides a comprehensive development environment for C and C++ developers building high-performance GPU-accelerated applications with CUDA libraries. The toolkit includes Nsight Visual Studio Code Edition, Nsight Eclipse Plugins, debugging and profiling tools including Nsight Compute, and a toolchain for cross-compiling applications
- NVIDIA Nsight Systems is a low overhead system-wide profiling tool, providing the insights developers need to analyze and optimize software performance.
- NVIDIA Nsight Graphics is a standalone application for debugging and profiling graphics applications.
- NVIDIA Nsight Deep Learning Designer is an integrated development environment that helps developers efficiently design and develop deep neural networks for in-app inference.
- Nsight System, Nsight Graphics, and Nsight Compute are all supported on Jetson Orin modules to assist development for autonomous machines.
- JetPack 5.1.2 includes NVIDIA Nsight Systems v2022.5
- JetPack 5.1.2 includes NVIDIA Nsight Graphics 2022.6
- JetPack 5.1.2 includes NVIDIA Nsight Deep Learning Designer 2022.2
- Supported SDKs and Tools:
- NVIDIA DeepStream SDK is a complete analytics toolkit for AI-based multi-sensor processing and video and audio understanding.
- DeepStream 6.2 release supports JetPack 5.1.2
- NVIDIA Triton™ Inference Server simplifies the deployment of AI models at scale. Triton Inference Server is open source and supports the deployment of trained AI models from NVIDIA TensorRT, TensorFlow and ONNX Runtime on Jetson. On Jetson, Triton Inference Server is provided as a shared library for direct integration with C API.
- PowerEstimator is a webapp that simplifies the creation of custom power mode profiles and estimates Jetson module power consumption.
- JetPack 5.1.2 adds supports for Jetson Orin NX and Jetson Orin Nano in PowerEstimator.
- NVIDIA Isaac™ ROS is a collection of hardware-accelerated packages that make it easier for ROS developers to build high-performance solutions on NVIDIA hardware including NVIDIA Jetson.
- Isaac ROS DP3.1 release supports JetPack 5.1.2
- Cloud Native:
- Jetson brings Cloud-Native to the edge and enables technologies like containers and container orchestration. NVIDIA JetPack includes NVIDIA Container Runtime with Docker integration, enbaling GPU accelerated containerized applications on Jetson platform.
- NVIDIA hosts several container images for Jetson on NVIDIA NGC. Some are suitable for software development with samples and documentation and others are suitable for production software deployment, containing only runtime components.
- Find more information and a list of all container images at the Cloud-Native on Jetson page.
- Security:
- NVIDIA Jetson modules include various security features includes Hardware Root of Trust, Secure Boot, Hardware Cryptographic Acceleration, Trusted Execution Environment, Disk and Memory Encryption, Physical Attack Protection and more.
- Learn about the security features by jumping to the security section of the Jetson Linux Developer guide.
- Jetpack 5.1.2 Security highlights include:
International
Singapore
Malaysia
Thailand
Vietnam
