reComputer J1010 is a compact edge computer built with NVIDIA Jetson Nano 4GB production module, comes with 128 NVIDIA CUDA® cores that deliver 0.5 TFLOPs (FP16) to run AI frameworks and applications like image classification, object detection, and speech processing. The production modules offer 16GB eMMC, a longer warranty, and a 5-10 year operating life in a production environment(Jetson FAQ). We also have reComputer J20 series built with a Jetson Xavier NX module, delivering 21 TOPS AI performance for more complex AI workloads.
Besides the Jetson module, reComputer J1010 also includes a J101 carrier board with onboard microSD card slot, 1*USB 3.0, 2*USB2.0, HDMI, M.2 Key E for WiFI, LTE and Bluetooth, RTC, Raspberry Pi GPIO 40-pin, and so on, as well as a heatsink, and aluminum case. The device has been pre-installed Jetpack 4.6.1, just plug in a USB C 5V/3A power supply, keyboard, mouse, and ethernet cable, and you are ready to start your embedded AI journey! If you need more USB 3.0 and onboard M.2 key M for attaching SSD, you can choose reComputer J1020.
Note: We received customer inquiries they need more storage than the 16GB eMMC offered. For orders after July 30th, 2022, we have included the microSD card slot on the carrier board of reComputer J1010. Please check the guide on boot images to a microSD card and adjust the I/O speed.
Documentation
data sheetHighlighted Features
- Hand-size edge AI full system delivering modern AI power of 0.5 TFLOPs (FP16) and rich interfaces for embedded development.
- Ready for development and deployment: pre-installed NVIDIA JetPack supports the entire Jetson software stack and industry-leading AI developer tools for building robust AI applications such as logistics, retail, service, agriculture, smart city, healthcare, and life sciences, etc
- Power efficient: powered by Type C 5V/3A, consuming as little as 5 watts.
- Expandable with the onboard interfaces and reComputer case, able to mount on the wall with mounting holes on the back.
If you are a beginner in Deep Learning, NVIDIA prepared this deep learning tutorial of Hello AI World and Two Days to a Demo. You can even earn certificates to demonstrate your understanding of Jetson and AI when you complete free, open-source courses. For most applications, you also need to connect with cameras, and you might need plug-and-play Grove sensors to use with Raspberry Pi HAT to extend more ideas.
Please also check out Seeed wiki guide including the getting started guide also different projects such as using helmet detection and deploying a custom YOLOv5 model at Jetson Nano.
Application
- Object detection use YOLOv5 and roboflow such as roadsign detection, and wildfire smoke detection. You can also follow this guide to train and deploy a custom model!
- Hard hat detection uses Edge Impulse for workplace safety
- Pedestrian detection by Edge Impulse
- nanosaur: the smallest Jetson Nano dinosaur robot, open-source, fully 3D printable, based on ROS2 & Isaac ROS.
- DeepCamera NVR (network video recorder)
- Pose estimation uses alwaysAI
- Retail store items detection
- Wildfire detection
- Animal detection
- Visual anomaly detection using NVIDIA Deepstream IoT
