Features

• Hand-size edge AI device built with NVIDIA Jetson Nano Production Module, delivering 128 NVIDIA CUDA® cores delivers 0.5 TFLOPs (FP16).

• Nearly the same design as Jetson Nano Developer Kit’s reference carrier board, rich IOs including Gigabit Ethernet port, 4 USB 3.0 Type-A ports, HDMI port and DP port.
• Pre-installed NVIDIA official JetPack software, ready for cloud-native application.
• Support a wide range of AI applications fast building with our ecosystem partners.
• Support real-time robotic development, analysis, and remotely fleet management at Cogniteam Nimbus. 
• Support Allxon to enable secure OTA and remote device management. Unlock 90 days free trial with code H4U-NMW-CPK.
• Able to mount on the wall with mounting holes on the back.

Description

reComputer Jetson series are compact edge computers built with NVIDIA advanced AI embedded systems: Jetson-10 (Nano 4GB) and Jetson-20 (Xavier NX). With rich extension modules, industrial peripherals, thermal management, reComputer 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).

Jetson Nano: Deep Learning Inference Performance

Reference: NVIDIA, Performance of various deep learning inference networks with Jetson Nano and TensorRT, using FP16 precision and batch size 1

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 of Face Detection. Benchmark details can be found on NVIDIA®’s DeepStream SDK website.

Jetson Nano can run a wide variety of advanced networks, including the full native versions of popular ML frameworks like TensorFlow, PyTorch, Caffe/Caffe2, Keras, MXNet, and others.

reComputer Jetson series is compatible with the entire NVIDIA Jetson software stack, industry-leading AI frameworks, development platforms like Edge Impulse, AlwaysAI, and cloud-based robot development tool Nimbus.

Application: next-gen autonomous machine at the edge

reComputer Jetson series is ideal for building autonomous machines and complex AI system tasks of image recognition, object detection and localization, pose estimation, semantic segmentation, video processing, and intelligent analytics. 

Edge AI into the Wild: UAV, Drone, Wildlife protection, Agriculture

Smart City: Traffic, Retail, Healthcare

Industry 4.0: Manufacturing, Logistics, Delivery, Service

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.