NVIDIA just announced now Jetson® AGX Orin™ 32GB module is available. The NVIDIA Jetson® AGX Orin™ 32GB module delivers up to 200 TOPS of AI performance with power configurable between 15W and 40W, more than 6X the performance of Jetson AGX Xavier in the same compact form-factor for robotics and other autonomous machine use cases.
JetPack 5.0.2 will be also available next week August 10, 2022. This will be a production release adding support for Jetson AGX Orin 32 GB. NVIDIA JetPack SDK is the most comprehensive solution for building end-to-end accelerated AI applications. Now AI enterprises will be more ready and move faster for their product to market.
In this article, we compared Jetson AGX Orin with AGX Xavier and Orin NX with Xavier NX with specs table. Through the Jetson module roadmap, we can expect Orin NX module 16GB in September. As NVIDIA’s ecosystem partner, Seeed is also working on reComputer-design with Orin NX and also reServer-design with AGX Orin. Please let us know your thoughts and expectations anytime at our discord edge ai channel!
- Jetson AGX Orin 64GB in October, $1599 over 1K units
- Jetson Orin NX 16GB in September, $599 over 1K units.
- Jetson Orin NX 8GB in December, $399 over 1K units
The most frequently asked question: can I use the developer kit for production usage?
Answer: NO. Jetson development kits are not recommended for production use. Development kits come with a non-production specification Jetson module attached to a reference carrier board are mainly for developing and testing software in a pre-production environment, as well as PoC development. Jetson modules are suitable for deployment in a production environment throughout their operating lifetime. Each Jetson module ships with no software pre-installed; you attach it to a carrier board designed or procured for your end product and flash it with the software image you’ve developed. Jetson modules are designed for deployment in a production environment throughout their operating lifetime.
Seeed reComputer and reServer series are built with NVIDIA Jetson production modules attached to carrier boards, which included necessary protocols for both AI product development and also mass production usage. Seeed delivers the hardware that meets your mass production needs and requirement. Seeed’s reComputer also comes with certifications of CE, FCC, RoHS, and adding KC, UKCA, Reach.
Seeed edge AI partners also offer comprehensive software support like AI software, developer tools, model optimization, device management, operating systems (Yocto & Realtime OS), and many more! Seeed will be the hardware partner, working with AI enterprises to deliver robust solutions together tailored to different needs. Join us today and contact [email protected] for more info!
- Edge Impulse: the leading development platform for machine learning on edge devices, free for developers and trusted by enterprises. Try it now for building models in minutes.
- AlwaysAI: a complete developer platform for Computer Vision applications on IoT devices. Get started today with our tutorial, and quickly deploy CV applications at the edge.
- ultralytics YOLOv5 : YOLO is an abbreviation for the term ‘You Only Look Once’. It is an algorithm that detects and recognizes various objects in an image in real-time. YOLOv5 is the latest version of YOLO which performs much better than the previous iterations of YOLO and it is now based on the PyTorch framework.
- Roboflow: annotate images super fast, right within your browser. Easily train a working computer vision model.
- Deci: empowers deep learning developers to accelerate inference on edge or cloud, reach production faster, and maximize hardware potential. Check out How to Deploy and Boost Inference on NVIDIA Jetson.
- Nimbus: log on to Nimbus, simply drag and drop to configure your robot application in the cloud.
- Allxon: Enable Efficient Remote Hardware Management Services for NVIDIA Jetson Platform. Enjoy an exclusive 90-day free trial to unlock all functions with code H4U-NMW-CPK. Read our partnership story here.
Built with Jetson Nano 4GB/ Xavier NX 8GB/16GB
- Edge AI box fit into anywhere
- Embedded Jetson Nano/NX Module
- Pre-installed Jetpack for easy deployment
- Nearly same form factor with Jetson Developer Kits, with rich set of I/Os
- Stackable and expandable
reServer Jetson: inference center for the edge
- Portable Edge AI center with up to 275 TOPS AI performance
- Chill 24/7 with Vapor Chamber heatsink (AGX Orin only),
40% more effective thermal performance
- Rapid network access and hybrid connectivity
2.5Gbes, 4G, 5G, LoRa, BLE, and WiFi (modules not included）
- Built-in storage for multiple concurrent AI applications
- Support Triton Inference Server and Pre-installed Jetpack
- Rich IOs ready for AIoT
USB 3.2 Type-A port, USB 2.0 Type-A port, HDMI port, and DP port