reComputer J1020 V2 – IoT Edge AI Computer w/ Jetpack

The reComputer J1020 v2 is a compact edge AI box that is perfect for your next AI application development and deployment. It is built with the Jetson Nano module, which has 128 NVIDIA CUDA cores that deliver 0.5 TFLOPs (FP16) of performance. This allows you to run AI frameworks and models for applications such as image classification, object detection, segmentation, and speech processing.

The reComputer J1020 v2 comes with a pre-installed NVIDIA Jetpack, which includes a board support package (BSP), Linux OS, NVIDIA CUDA, cuDNN, and TensorRT software libraries for deep learning, computer vision, GPU computing, multimedia processing, and more. It also has a rich set of I/Os, including GPIO, CSI, Gigabit Ethernet, 4x USB 3.0 Type A, and an onboard 16 GB eMMC. The device is housed in an aluminum case with a passive heatsink and is ready to be used right out of the box.

This intelligent edge box is ideal for solution providers working in industries such as smart cities, security, industrial automation, and smart factories. It can be used for applications such as video analytics, object detection, natural language processing, and medical imaging. It is also a great choice for AI beginners looking to get started with deep learning, as it comes with access to NVIDIA’s Deep Learning Institute (DLI), which provides practical, hands-on training and certification.

In addition, Unmanned Tech shop offers outstanding after sales service and fast shipping, so you can trust that you’ll be well taken care of when you purchase the reComputer J1020 v2.

Features

• NVIDIA Jetson Nano Dev Kit alternative: hand-size Edge AI device built with Jetson Nano 4GB Production Module, the carrier board brings extensive I/Os: GPIO, CSI, Gigabit Ethernet, 4 x USB 3.0 Type A, onboard 16 GB eMMC, Please check here for SSD storage expansion.
• 128 NVIDIA CUDA® cores deliver 0.5 TFLOPs (FP16) to run AI frameworks and models for applications like image classification, object detection, segmentation, and speech processing.
• Pre-installed NVIDIA Jetpack, JetPack SDK includes a board support package (BSP), Linux OS, NVIDIA CUDA, cuDNN, and TensorRT software libraries for deep learning, computer vision, GPU computing, multimedia processing, etc.
• Support the entire Jetson software stack and various developer tools for building fast and robust AI applications provided by Seeed Edge AI partners.

Compare NVIDIA Jetson Nano Dev Kit B01 with reComputer J10 series

Application: For next-gen autonomous machine

With edge AI developers can deploy machine learning models in solving demanding challenges for advanced robotics and autonomous machines in the fields:

• Edge AI into the Wild: UAV, Drone, Wildlife protection, Agriculture
• Smart City: Traffic, Retail, Healthcare
• Industry 4.0: Manufacturing, Logistics, Deliver, Service

The reComputer J1020 v2 is a powerful and compact intelligent edge box that is ideal for a variety of AI applications. Some possible applications include:

1. Video analytics: The device can be used to perform real-time video analysis for applications such as surveillance, traffic monitoring, and event detection.
2. Object detection: The device can be used to detect and classify objects in images or video streams, enabling applications such as automated inspection, inventory management, and quality control.
3. Natural language processing: The device can be used to process and analyze text data, enabling applications such as voice recognition, language translation, and sentiment analysis.
4. Medical imaging: The device can be used to analyze medical images such as CT scans and MRI scans, enabling applications such as diagnosis and treatment planning.
5. Robotics: The device can be used to enable autonomous robots to perceive and understand their environment, enabling applications such as navigation and manipulation.

These are just a few examples of the many possible applications of the reComputer J1020 v2. Its powerful AI capabilities make it suitable for a wide range of use cases, including those in the areas of smart cities, security, industrial automation, and smart factories.

Power-efficient AI computer, compact rich I/Os for Endless AI possibilities:

reComputer Jetson – 10 comes with Jetson Nano delivers 0.5 TFLOPs (FP16), making it ideal for high-performance compute and AI in embedded and edge systems. You get the performance of 128 NVIDIA CUDA® Cores, quad-Core ARM CPUs. Combined with over 25.6GB/s of memory bandwidth, video encoded and decoded, these features make Jetson Nano the platform of choice to run multiple modern neural networks in parallel and process high-resolution data from multiple sensors simultaneously.

Now, you can innovate at the edge with powerful and efficient AI, computer vision, and high-performance computing at just 5 to 10 watts.

Powerful reference carrier board:

The Seeed reference carrier board for the J1020 v2 is a high-performance carrier board that is compatible with the NVIDIA Jetson Nano. It offers a range of interfaces, including HDMI 2.0, Gigabit Ethernet, USB 3.0, CSI camera, GPIO, I2C, I2S, and more, making it a versatile and functional choice for your AI application development needs. It is nearly identical in design to the Jetson Nano Developer Kit, making it easy to use and integrate into your project.

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.

Prebuild system for edge AI integration

All NVIDIA® Jetson™ modules and developer kits are supported by the same software stack, enabling you to develop once and deploy everywhere. Jetson Software is designed to provide end-to-end acceleration for AI applications and accelerate your time to market. We bring the same powerful NVIDIA technologies that power data center and cloud deployments to the edge.

NVIDIA JetPack includes NVIDIA Container Runtime with Docker integration, enabling GPU accelerated containerized applications on Jetson platform. Jetpack also brings support for NVIDIA Triton™ Inference Server to simplify the deployment of AI models at scale.

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

Specifications

Module Technical Specifications

Carrier Board Technical Specifications

Part List

1 x Acrylic Cover

1 x Aluminium Frame

1 x Jetson Nano module

1 x Heatsink

1 x Carrier board

1 x 12V/2A  Power Adapter (with 5 interchangeable adapter plugs）