NVIDIA Jetson Nano Developer Kit

NVIDIA Jetson Nano Developer Kit / 945-13450-0000-100 is a developer kit that includes a small but powerful NVIDIA Jetson Nano microcomputer, implemented in the form factor of a computing module with an air cooling radiator installed on it, which is located on the base board, allowing you to use all the features of the computing module and connect all the physical interfaces included in its design: Ethernet, MIPI CSI-2 DPHY, HDMI 2.0, DP (DisplayPort), 4xUSB 3.0, USB 2.0 (Micro USB), GPIO 40-pin, I2C, I2S, SPI, UART.

The NVIDIA Jetson Nano is a very productive microcomputer and allows you to run multiple neural networks in parallel for applications such as image classification, object detection, segmentation, and speech processing. And all this on an easy-to-use and energy-efficient platform (power consumption is only 5 watts).

Jetson Nano delivers 472 GFLOPS of performance for fast operation of modern AI algorithms on a quad-core 64-bit ARM processor and 128-core integrated NVIDIA GPU based on Maxwell™ architecture with 4 GB of LPDDR4 RAM. All of this allows you to run multiple neural networks in parallel and processes multiple high-resolution cameras simultaneously.

The Jetson Nano is also supported by the NVIDIA JetPack, which includes a board support package (BSP), CUDA, cuDNN, and TensorRT software libraries for Deep Learning, computer vision, GPU computing, multimedia processing, and more. The JetPack SDK also includes the ability to natively install popular open source machine learning (ML) platforms such as TensorFlow, PyTorch, Caffe/Caffe2, Keras, and MXNet, allowing developers to quickly and easily integrate their favorite AI model.

Specifications:

GPU: 128-core GPU based on Maxwell™ architecture

Processor: quad-core processor based on ARM® Cortex®-A57 architecture

RAM: 4 GB, 64-bit LPDDR4

Storage: Micro SD card slot (requires a minimum 16 GB external card)

Video:

• Encoding: 4K @ 30 (H.264 / H.265)
• Decoding: 4K @ 60 (H.264 / H.265)

Interfaces:

• Ethernet: 10/100 / 1000BASE-T with auto-negotiation
• Camera: 12-channel (3x4 OR 4x2) MIPI CSI-2 DPHY 1.1 (1.5 Gbps)
• Display: HDMI 2.0, DP (DisplayPort)
• USB: 4x USB 3.0, USB 2.0 (Micro USB)
• Others: GPIO, I2C, I2S, SPI, UART

Power supply:

• Micro USB (5V 2A)
• DC power socket (5V, 4A)

Overall dimensions:

• Main module: 69.6mm × 45mm
• Complete kit: 100mm × 80mm × 29mm

Microcomputer elements:

1. MicroSD card slot for main storage
2. 40-pin GPIO expansion connector
3. Micro-USB port for 5V power input or for data transfer
4. Gigabit Ethernet port
5. USB 3.0 ports (4 pcs.)
6. HDMI output port
7. DisplayPort connector
8. DC Barrel connector for 5V power input
9. MIPI CSI-2 camera connectors

NVIDIA Jetson Nano, along with Raspberry Pi 4, are representatives of the same segment of budget microcomputers, but at the same time have some significant differences. For those who are in doubt about the choice between these two models, we recommend watching a video with a detailed comparison of the characteristics and performance of these microcomputers in different modes:

And for the developer community, NVIDIA has released an engaging and informative webinar with a Q&A session to tell you more about the Jetson Nano hardware and software. In it, you will learn how you can create and deploy your own deep learning models, as well as create autonomous robots and intelligent devices based on artificial intelligence.

The package includes:

1. NVIDIA Jetson Nano module and base board
2. Quick start guide and support information
3. Paper stand

NOT included:

1. MicroSD card (minimum 32 GB UHS-1 recommended)
2. USB keyboard and mouse
3. Computer display (HDMI or DP). HDMI-DVI adapters are not supported. Use a display that has an HDMI or DP input.
4. Micro-USB power supply
5. You also need a computer with an internet connection and the ability to flash a microSD card to get started.