TensorFlow™ is an open-source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture lets you deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device without rewriting code.

TensorFlow was originally developed by researchers and engineers working on the Google Brain team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks (DNNs) research. The system is general enough to be applicable in a wide variety of other domains, as well.

Jetson TX2

While many AI applications can utilize powerful server processing, others require processing to occur on or near the sensing device itself. These edge applications may require low latency, data privacy, or network connectivity may be limited. Some edge applications include robotics, smart cameras, drones, and portable medical devices.

Jetson is NVIDIA’s solution to AI at the edge. The Jetson TX2 is a complete System on Module (SoM) which combines a multi-core CPU, Pascal architecture GPU, and Image Signal Processor (ISP) into a single module with a low power profile. With support for CUDA, TensorFlow and other multimedia and image processing libraries, Jetson makes it easy to deploy high performance neural networks at the edge.