reComputer J4012-Edge AI Device with Jetson Orin™ NX 16GB module, 4xUSB 3.2, M.2 Key E & Key M Slot, Aluminum case, 128GB NVMe SSD, Pre-installed JetPack System

reComputer J4012 is a powerful and compact intelligent edge box to bring up to 100 TOPS modern AI performance to the edge, which offers up to 5X the performance of Jetson Xavier NX and up to 3X the performance of Jetson AGX Xavier. Combining the NVIDIA Ampere™ GPU architecture with 64-bit operating capability, Orin NX integrates advanced multi-function video and image processing, and NVIDIA Deep Learning Accelerators.

The full system includes one Jetson Orin™ NX production module, a heatsink, and a power adapter. reComputer J4012 is preinstalled with Jetpack 5.1, simplifies development, and fits for deployment for edge AI solution providers working in video analytics, object detection, natural language processing, medical imaging, and robotics across industries of smart cities, security, industrial automation, smart factories.

Features

• Brilliant AI Performance for production: on-device processing with up to 100 TOPS AI performance with low power and low latency
• Hand-size edge AI device: compact size at 130mm x120mm x 58.5mm, includes Jetson Orin™ NX production module, a cooling fan with a heatsink, enclosure, and a power adapter. Support desktop, wall mount, fit in anywhere
• Expandable with rich I/Os: 4x USB 3.2, HDMI 2.1, 2xCSI, 1xRJ45 for GbE, M.2 Key E, M.2 Key M, CAN, and GPIO.
• Accelerate solution to market: pre-installed JetPack 5.1, Linux OS BSP, 128GB SSD, support Jetson software and leading AI frameworks and software platforms
• Comprehensive certificates: FCC, CE, RoHS, UKCA

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). Now we introduce the reComputer J4012 which is powered by Jetson Orin™ NX 16GB module and reComputer J401 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.

We have prepared abundant guides to get started with NVIDIA Jetson using leading AI frameworks and software. For example, with Deepstream and TensorRT, developers can deploy custom YOLOv5 models on Jetson Orin at over 100FPS

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

• 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.

Comparison among reComputer J40 and J20 series boards

Hardware Overview

Interface-rich reference carrier board

Seeed carrier board for reComputer J4012 is a high-performance, interface-rich board, providing HDMI 2.1, Gigabit Ethernet, USB 3.2, M.2 key E, M.2 key M, CSI camera, CAN, GPIO, I2C, I2S, fan, and other rich peripheral interfaces.

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.

Applications

reComputer J40 series, powered by Orin 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. The following are few of the applications that have been tested with Xavier NX and you can take them for reference in order to build applications using Orin NX as well.

• 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!

Note

If you want to use SSDs with reComputer, we only recommend you choose 128GB, 256GB, 512GB versions from Seeed, because some of the SSDs in the market will work with this product under a particular JetPack version and some will not work with a different JetPack version. Even the official NVIDIA dev kits have the same behavior with SSDs

Part List

Documentations

reComputer J401X Datasheet

NVIDIA Jetson Devices and carrier boards comparisions