reComputer J2022 (w/o power adapter) - Edge AI Computer with NVIDIA® Jetson™ Xavier NX 16GB

reComputer J2022 is a hand-size edge AI box built with Jetson Xavier NX 16GB module which delivers up to 21 TOPs AI performance, a rich set of IOs including USB 3.1 ports(4x), M.2 key E for WIFI, M.2 Key M for SSD, RTC, CAN, Raspberry Pi GPIO 40-pin, and so on, aluminum case, cooling fan, pre-installed JetPack System, as NVIDIA Jetson Xavier NX Dev Kit alternative, ready for your next AI application development and deployment. If you are looking for the version with power adapter, please check out reComputer J2022. Features Hand-size edge AI device: built with Jetson Xavier NX 16GB Production Module, delivering 384 NVIDIA CUDA® cores delivers up to 21 TOPs AI performance with a small form factor of 130mm x120mm x 50mm. NVIDIA Jetson Xavier NX Dev Kit alternative: the carrier board brings rich IOs including a Gigabit Ethernet port, 4 USB 3.1 ports, an HDMI port, and a DP port Pre-installed NVIDIA JetPack: support the entire Jetson software stack and various developer tools for building fast and robust AI application provided by Seeed Edge AI partners, helps develop innovative AI solution for manufacturing, logistics, retail, service, agriculture, smart city, healthcare, and life sciences, etc Expandable with the onboard interfaces and reComputer case, able to mount on the wall with mounting holes on the back. Description reComputer series for Jetson are compact edge computers built with NVIDIA advanced AI embedded systems: J10 (Nano 4GB) and J20 (Jetson Xavier NX 8GB and Jetson Xavier 16GB), where the reComputer J2022 is the Jetson Xavier NX 16GB module carried by reComputer J202 carrier board. With rich extension modules, industrial peripherals, and thermal management, reComputer for Jetson is ready to help you accelerate and scale the next-gen AI product by deploying popular DNN models and ML frameworks to the edge and inferencing with high performance, for tasks like real-time classification and object detection, pose estimation, semantic segmentation, and natural language processing (NLP). At Seeed Studio, you will find everything you want to work with the NVIDIA Jetson Platform – official NVIDIA Jetson Dev Kits, Seeed-designed carrier boards, edge devices, as well as accessories. Welcome to check out our free Edge AI partner program. We are looking forward to leveraging local and global resources to accelerate next-gen AI products together with you. Comparison among reComputer J20 series and Official Dev Kits Product NVIDIA Jetson Xavier NX Developer Kit reComputer J2012 reComputer J2021 reComputer J2022 Module Xavier NX (not the production version) Xavier NX 16GB (production version) Jetson Xavier NX 8 GB Jetson Xavier NX 16GB AI Perf 21 TOPS GPU 384-core NVIDIA Volta™ GPU CPU 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6 MB L2 + 4 MB L3 Memory 8 GB 128-bit LPDDR4x @ 51.2GB/s 16 GB 128-bit LPDDR4x @ 59.7GB/s 8 GB 128-bit LPDDR4x @ 59.7GB/s 16 GB 128-bit LPDDR4x 59.7GB/s Storage MicroSD (Card not included) 16 GB eMMC 5.1 Video encoder 2x 4K @ 30 | 6x 1080p @ 60 | 14x 1080p @ 30 (H.265/H.264) 2x 4K60 | 4x 4K30 | 10x 1080p60 | 22x 1080p30 (H.265) 2x 4K60 | 4x 4K30 | 10x 1080p60 | 20x 108p30 (H.264) Video decoder 2x 4K @ 60 | 4x 4K @ 30 | 12x 1080p @ 60 | 32x 1080p @ 30 (H.265) 2x 4K @ 30 | 6x 1080p @ 60 | 16x 1080p @ 30 (H.264) 2x 8K30 | 6x 4K60 | 12x 4K30 | 22x 1080p60 | 44x 1080p30 (H.265) 2x 4K60 | 6x 4K30 | 10x 1080p60 | 22x 1080p30 (H.264) Gigabit Ethernet 1*RJ45 Gigabit Ethernet Connector (10/100/1000) USB 4 * USB 3.1 Type A Connector; 1 * Micro-USB port for Device mode; 4 * USB 3.0 Type A Connector; 1 * Micro-USB port for Device mode; 4 * USB 3.1 Type A Connector； 1* USB Type-C (Device mode) CSI Camera Connect 2*CSI Camera (15 pos, 1mm pitch, MIPI CSI-2 ) Display 1*HDMI Type A; 1*DP FAN 1* FAN connector(5V PWM) M.2 KEY E 1*M.2 Key E(WiFi/BT included) 1*M.2 Key E M.2 KEY M 1*M.2 Key M RTC - 1*RTC Socket RTC 2-pin RTC socket Multifunctional port 1* 40-Pin header Power Requirements DC Jack 19V 4.74A (MAX 90W) 12V/5A(Barrel Jack 5.5/2.5mm) Mechanical 103 mm x 90.5 mm x 31 mm 130mm x120mm x 50mm Note If you use some GPIO libraries that cause floating voltage 1.2V~2V, GPIO issues on the carrier board could happen as the normal voltage should be 3V. This is a common situation on the carrier boards, for both the reComputer series and the official Nvidia Jetson developer kit. Thus, aftersales / warranty does not come into effect regarding this issue. For further information, refer to NVIDIA official document. Application For both beginners and experts, it is designed to help you to build your next-gen autonomous machine at the edge. Edge AI Applications reComputer J20 series, powered by Xavier NX, is ideal for building autonomous applications and complex AI tasks of image recognition, object detection, pose estimation, semantic segmentation, video processing, and many more. Traffic management license plate detection car detection pedestrian detection Industry 4.0: helmet detection, hard hat detection, and custom PPE detection visual anomaly detection using NVIDIA Deepstream IoT Retail: sentiment analysis(webinar: learn your customer with AI by Zenus smart camera), retail store items detection Robotics: under-ice sensing ROV warehouse towing robot Edge AI into the Wild: Wildfire detection Agriculture: weeding machines, Tractors, Livestock detection Healthcare: medical imaging analysis Find in the Jetson Community Resources page tools and tutorials the community has created to power your development experience, and check out the Community Projects page to inspire your next project! AI Beginners learning center If you would like to get critical AI skills and dive into deep learning. NVIDIA’s Deep Learning Institute (DLI) will be a good choice, which delivers practical, hands-on training and certification in AI at the edge for developers, educators, students, and lifelong learners. You can even earn certificates to demonstrate your understanding of Jetson and AI when you complete these free, open-source courses. Please also check out Seeed wiki guide including getting started with Jetson Nano and also building different projects. Developers Tools Pre-installed Jetpack for fast development and edge AI integration Jetson software stack begins with NVIDIA JetPack™ SDK which provides a full development environment and includes CUDA-X accelerated libraries and other NVIDIA technologies to kickstart your development. JetPack includes the Jetson Linux Driver package which provides the Linux kernel, bootloader, NVIDIA drivers, flashing utilities, sample filesystem, and toolchains for the Jetson platform. It also includes security features, over-the-air update capabilities, and much more. Computer Vision and embedded machine learning Edge AI no code Vision tool, Seeed latest open-source project for deploying AI application within 3 nodes. NVIDIA DeepStream SDK delivers a complete streaming analytics toolkit for AI-based multi-sensor processing and video and image understanding on Jetson. NVIDIA TAO tool kit, built on TensorFlow and PyTorch, is a low-code version of the NVIDIA TAO framework that accelerates the model training alwaysAI: build, train, and deploy computer vision applications directly at the edge of reComputer. Get free access to 100+ pre-trained Computer Vision Models and train custom AI models in the cloud in a few clicks via enterprise subscription. Check out our wiki guide to get started with alwaysAI. Edge Impulse: the easiest embedded machine learning pipeline for deploying audio, classification, and object detection applications at the edge with zero dependencies on the cloud. Roboflow provides tools to convert raw images into a custom-trained computer vision model of object detection and classification and deploy the model for use in applications. See the full documentation for deploying to NVIDIA Jetson with Roboflow. YOLOv5 by Ultralytics: use transfer learning to realize few-shot object detection with YOLOv5 which needs only a very few training samples. See our step-by-step wiki tutorials Deci: optimize your models on NVIDIA Jetson Nano. Check the webinar at Deci of Automatically Benchmark and Optimize Runtime Performance on NVIDIA Jetson Nano and Xavier NX Devices Speech AI NVIDIA® Riva is a GPU-accelerated SDK for building Speech AI applications that are customized for your use case and deliver real-time performance. Remote Fleet Management Enable secure OTA and remote device management with Allxon. Unlock 90 days free trial with code H4U-NMW-CPK. Robot and ROS Development NVIDIA Isaac ROS GEMs are hardware-accelerated packages that make it easier for ROS developers to build high-performance solutions on NVIDIA hardware. Learn more about NVIDIA Developer Tools Cogniteam Nimbus is a cloud-based solution that allows developers to manage autonomous robots more effectively. Nimbus platform supports NVIDIA® Jetson™ and ISAAC SDK and GEMs out-of-the-box. Check out our webinar on connecting your ROS Project to the Cloud with Nimbus. Compare NVIDIA Jetson Nano and Jetson Xavier NX With Jetson Nano, developers can use highly accurate pre-trained models from TAO Toolkit and deploy with DeepStream. Jetson Nano can achieve 11 FPS for PeopleNet- ResNet34 of People Detection, 19 FPS for DashCamNet-ResNet18 of Vehicle Detection, and 101 FPS for FaceDetect-IR-ResNet18 for Face Detection. Jetson Xavier NX can achieve 172 FPS for PeopleNet- ResNet34 for People Detection, 274 FPS for DashCamNet-ResNet18 of Vehicle Detection, and 1126 FPS for FaceDetect-IR-ResNet18 for Face Detection. Benchmark details can be found on NVIDIA®’s DeepStream SDK website. Reference: Jetson series benchmark for Deepstream: end-to-end application performance from data ingestion, decoding, image processing to inference If you are developing an application that requires processioning multiple video streams at high resolution while performing ASR/NLP or other GPU-related tasks (CUDA-enabled SLAM for example), then its deep learning accelerators can take on CNN inference and leave GPU for other tasks – TX2 or Jetson Nano maybe not satisfied. We recommend reComputer J2012 and J2022. Check our comparison blog here. Hardware Overview The interface-rich reference carrier board Nearly the same functional design as the Jetson Xavier NX Developer Kit Seeed carrier board for reComputer J2022 is a high-performance, interface-rich NVIDIA Jetson Xavier NX compatible carrier board, providing HDMI 2.0, Gigabit Ethernet, USB 3.1 Gen2, M.2 key E, M.2 key M, CSI camera, CAN, GPIO, I2C, I2S, fans, and other rich peripheral interfaces. It has the same functional design and size as the carrier board of NVIDIA® Jetson Xavier™ NX DEVELOPER KIT. Take advantage of the small form factor, sensor-rich interfaces, and big performance to bring new capabilities to all your embedded AI and edge systems. Desktop, Wall Mount, Expandable or fit in anywhere The back screw holes allow you to hang the product as you need. We also provide other editions case like blue, silver, and silver metal, whose stackable structure allows you to stack more middle layers to create rooms very easily. Note If you want to use SSDs with reComputer Jetson, we only recommend you choose 128GB, 256GB, and 512GB versions from Seeed, because some of the SSDs in the market will not work with this product. Part List Acrylic Cover 1 Aluminum Frame 1 Jetson Xavier NX 16GB module 1 Aluminum heatsink with fan 1 Carrier Board 1 We will not include a power cord, please choose a suitable form according to your country. Note We have already installed JetPack 4.6 system in the reComputer and you can directly use it by powering it on. Please check our wiki for reflashing Jetpack and expanding the storage. We'd like to hear from you, welcome to join our Discord channel to share your thoughts (Jetson edge AI) FAQ 1. What is the main difference between the reComputer J2021 and J2022? The difference between them is memory. The module on the reComputer J2021 is Jetson Xavier 8GB. If you require more memory, the J2022 with Jetson Xavier 16GB may meet your needs. 2. Can I install the Jetson Nano module on the reComputer J2022 carrier board? Yes, the reComputer J2022 carrier board J202 supports both the Jetson Nano module and the Jetson Xavier module. 3. What type of RTC is recommended for RTC socket? CR1220 and ML1220. The non-rechargeable design of the RTC circuit of the carrier board allows both rechargeable and non-rechargeable RTC batteries to be used.