PRODUCT DETAILS

 

Features

• Hand-size edge AI device: built with Jetson Xavier NX 8GB Production Module, delivering 384 NVIDIA CUDA® cores delivers up to 21 TOPs AI performance with the small form factor of 130mm x120mm x 50mm.
• NVIDIA Jetson Xavier NX Dev Kit alternative: the carrier board brings rich IOs including Gigabit Ethernet port, 4 USB 3.0 Type-A ports, HDMI port, and DP port
• Pre-installed NVIDIA JetPack: support entire  and various  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 
• Power-efficient: as little as 10 watts, delivering high performance, accurate, multi-modal AI inference at the edge.  
• 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 builtith NVIDIA advanced AI embedded systems: J10 () and J20 (Jetson Xavier NX 8GB and ). With rich extension modules, industrial peripherals, 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, you will find everything you want to work with  – official NVIDIA Jetson Dev Kits, Seeed-designed carrier boards, and edge devices, as well as accessories.

Welcome to check out our . We are looking forward to leveraging local and global resources to accelerate next-gen AI product together with you.

 

Application: build your next-gen autonomous machine at the edge

 

Edge AI Applications

 

reComputer J2011 and J2022 are ideal for building autonomous applications and complex AI tasks of image recognition, object detection, pose estimation, semantic segmentation, video processing, and many more. 

• license plate detection
• car detection
• pedestrian detection
• Industry 4.0: 
• , , and custom PPE detection
• Retail: 
• sentiment analysis(: learn your customer with AI by Zenus smart camera),
• Robotics: 
• Edge AI into the Wild:  
• Agriculture: weeding machine, Tractors, Livestock detection 
• Healthcare: medical imaging analysis 

Developers Tools

Pre-installed Jetpack for fast development and edge AI integration

 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

•  Seeed latest open-source project for deploying AI application within 3 nodes. 
•  delivers a complete streaming analytics toolkit for AI-based multi-sensor processing and video and image understanding on Jetson.
• , built on TensorFlow and PyTorch, is a low-code version of the NVIDIA TAO framework that accelerates the model training 
• : 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  guide to get started with alwaysAI.
• : the easiest embedded machine learning pipeline for deploying audio, classification, and object detection applications at the edge with zero dependencies on the cloud. 
•  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  for deploying to NVIDIA Jetson with Roboflow.
• : use transfer learning to realize few-shot object detection with YOLOv5 which needs only a very few training samples. See our step-by-step tutorials

Speech AI

•  is a GPU-accelerated SDK for building Speech AI applications that are customized for your use case and deliver real-time performance.

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  
•  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  on Connect your ROS Project to the Cloud with Nimbus.

Model Optimization

• : optimize your models on NVIDIA Jetson devices. Check  at Deci of Automatically Benchmark and Optimize Runtime Performance on NVIDIA Jetson Nano and Xavier NX Devices

 

Remote Fleet Management

Enable secure OTA and remote device management with . Unlock 90 days free trial with code H4U-NMW-CPK.

 

Jetson Xavier NX and Jetson AGX Orin MLPerf v2.0 Results

Model	Jetson Xavier NX (TensorRT)
	Image Classification ResNet-50	1243.14	6138.84
Object Detection SSD-small	1782.53	6883.49
Object Detection SSD-Large	36.69	207.66
Speech to Text RNN-T	260.52	1110.23
Natural Language Processing BERT-Large	61.40	476.34

• These are preview results, and can be found at: 

Hardware specification

 Comparison among reComputer J20 series and Official Dev Kits 

 

Product
Module	Xavier NX (not production version)	Xavier NX (production version)	Xavier NX 16GB (production version)
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	8 GB 128-bit LPDDR4x @ 59.7GB/s	16 GB 128-bit LPDDR4x @ 59.7GB/s
Storage	microSD (Card not included)	16 GB eMMC
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;
CSI Camera Connect	2*CSI Camera (15 pos, 1mm pitch, MIPI CSI-2 )
Display	1*HDMI Type A; 1*DP
FAN	1* FAN(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
Multifunctional port	1* 40-Pin header
Power Requirements	DC Jack 19V 4.74A (MAX 90W)
Mechanical	103 mm x 90.5 mm x 31 mm	130mm x120mm x 50mm

 

  

Interface-rich reference carrier board :

Nearly the same functional design as Jetson Xavier NX Developer Kit

 

Seeed reference carrier board for reComputer J20 is a high-performance, interface rich NVIDIA Jetson Xavier NX compatible carrier board, providing HDMI 2.0, Gigabit Ethernet, USB 3.0, USB 2.0, 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 .

Take advantage of the small form factor, sensor-rich interfaces, and big performance to bring new capability to all your embedded AI and edge systems.

  

Desktop, Wall Mount, or fit in anywhere

With an overall dimension of 130mm*120mm*50mm, it is only around 1/10 of the size of an ordinary computer case which makes it possible to fit in edge AI scenarios. The back screw holes allow you to hang the product as you need. We also provide other editions case like blue, silver and silver mental, whose stackable structure allows you to stack more middle layers to create rooms very easily.

  

Part List

1 x Acrylic Cover

1 x Aluminium Frame 

1 x Jetson Xavier NX module 

1 x Heatsink 

1 x Carrier board 

1 x 19V/4.74A (MAX 90W) Power Adapter (Power cable not included)

We will not include a power cord, please choose a suitable form according to your country.
We will not include a 3V RTC battery (CR1220）

 

Note

• Name change: 'reComputer Jetson-20-1-H1' has changed to 'reComputer J2011'.
• We have already installed JetPack 4.6 system in the reComputer and you can directly use it by powering on.
• Please check our for reflashing Jetpack and expanding the storage.
• We'd like to hear from you, welcome to join our Discord channel to share your thoughts () 

 

Note 

• We will not include a power cord, please choose a suitable form according to your country.
• We will not include a 3V RTC battery (CR1220）

 

ECCN/HTS

HSCODE	8471419000
USHSCODE	8471490000
UPC

FCC	1
CE	1

LEARN AND DOCUMENTS

Documentations

Learn

 

[Documentation] 

Explore the interfaces, AI performances, and all differences among Seeed's edge AI devices carrier boards for Jetson.

 

[Wiki] 

MaskCam is a prototype reference design for a Jetson Nano-based smart camera system that measures crowd face mask usage in real-time, with all AI computation performed at the edge. MaskCam detects and tracks people in its field of view and determines whether they are wearing a mask via an object detection, tracking, and voting algorithm.