Jetson Nano Module

Jetson Nano Module

• AI Perf: 472 GFLOPS

• GPU: NVIDIA Maxwell™ architecture with 128 NVIDIA CUDA® cores 0.5 TFLOPs (FP16)

• CPU: Quad-core ARM® Cortex®-A57 MPCore processor

• Memory: 4 GB 64-bit LPDDR4 1600MHz - 25.6 GB/s

• Storage: 16 GB eMMC 5.1 Flash

The  NVIDIA® Jetson  Nano™  moduledelivers  up  to  472  GFLOPS  of  accelerated computing from NVIDIA CUDA cores in an unprecedented size, power and cost. Jetson nano   natively   supports   all   types   of   AI   models   and   popular   AI   frameworks   e.g. TensorFlow,  PyTorch  and  MxNet.  This  makes  Jetson  nano  the  ideal  platform  for developing  mass  market  AI  products  such  as  AIIoT  gateways,  smart  network  video recorders and cameras, consumer robots, and optical inspection systems.     

The system-on-module is powered by the NVIDIA Maxwell GPU with 4GB of memory which  enables  real-time  processing  of  high  resolution  inputs.  It  has  a  combination  of performance, power advantage and rich set of IOs, from high speed CSI and PCIe to low speed  I2Cs  and  GPIOs.  It  can  also  support  multiple  diverse  sets  of  sensors  to  enable  a variety of applications with incredible power efficiency, consuming as little as 5W.

Jetson  Nano  is  supported  byNVIDIA  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 much more. The  comprehensive  software  stackmakes  AI  deployment  on  autonomous  machines  fast, reduces complexity and time to market.

The same JetPack SDK is used across the entire NVIDIA Jetson™ family of products and  is  fully  compatible  with  NVIDIA’s  world-leading  AI  platform for  training  and deploying AI software.