JETSON NANO 4GB

————

NVIDIA JETSONNANO is a compact yet powerful computer that allows you to run multiple applications such as neural networks, object detection, segmentation, and speech processing in parallel. JETSONNANO is equipped with a quad core CORTEX-A57 processor, 128 core MAXWELLLGPU, and 4GBLPDDR memory, providing sufficient Al computing power, offering 472GFLOP, and supporting a range of popular Al frameworks and algorithms such as TENSORFLOW, PYTORCH, CAFFE/CAFE2, KERAS, MXNET, etc.

Parameter comparison

————

Functional distribution

————

Package  recommendatior

————

Hello！ Al Artificial Intelligence

————

JetsonNano can run various advanced neural networks, such as TensorFlow, PyTorch, Caffe/Caf2, Keras, MXNet, etc. These networks can be used to build autonomous robots and complex artificial intelligence systems by implementing capabilities such as image recognition, object detection and localization, speech segmentation, video enhancement, and intelligent analysis.

                                         Real time image recognition                                                                           Mobile Person Tracking

                                          Segmented data statistics                                                                                   AI intelligent car

AI 'brain' neural network

————

JetsonNano applies real-time computer vision and inference to various complex deep neural network (DNN) models. These capabilities enable multi-sensor autonomous robots, IoT devices with intelligent edge analysis capabilities, and advanced artificial intelligence systems.

Multi stream video analysis

————

JetsonNano processes up to 8 high-definition full motion video streams in real-time and can be deployed as a low-power edge intelligent video analysis platform for network video recorders (Nvr), smart cameras, and IoT gateways

Neural Network SDK

Artificial Intelligence AI Computing

————

Jetson Development Pack (JetPack) is an on-demand integrated software package that bundles and installs all development software tools for the NVIDIA Jetson embedded platform. JetPack includes tools for the following features:

Support system mirroring

Hands on practice and AI creation

————

Provided a complete desktop Linux environment for JetsonNano based on Ubuntu 18.04, with accelerated graphics, support for 

NVIDIA CUDA Toolkit 10.0, as well as libraries such as cuDNN7.3 and TensorRT.

Common power supply methods

The SUB version and B01 official public version have the same power supply method

————

JetsonNano's microUSB interface only supports 2A current, and DC power supply is highly recommended to meet most of JetsonNano's usage scenarios. It can also drive loads such as cameras, displays, USB devices, etc.

① POE power supply          ② 5V3A (GPIO pin)         ③5V2A(micro USB)          ④ 5V4A (DC interface)/5V6A (DC interface)

Why is a 5V 4A power supply recommended?

————

When testing YOLOV3 to detect and recognize objects, there is a fan and a 7-inch screen that require power supply. The CPU occupies about 70% and the current is approximately 2.9A. If USB power supply is used, it can only reach 2A, which cannot meet the testing conditions; If the DC uses 3A, the power supply will remain at full load and overheat protection will occur. Therefore, it is recommended to choose a 5V4A power supply, which can meet most application testing needs. In extreme testing situations, multiple loads such as CPUs, GPUs, cameras, and displays can run simultaneously, and the entire system can reach 3.5A. A 4A power supply can handle it with ease, while a 6A power supply is smoother.

                                        Meet various usage scenarios                                                              Only suitable for some usage scenarios

Development board comparison

————

Our services

————

Our goal is to continuously improve our own technical capabilities and place greater emphasis on the customer's product experience.