Chapter 2: Key Concepts of TensorFlow

TensorFlow™ is a open-sourced library using data flow graphs for numerical calculation. Each node in the graph represents a mathematical operation, and each edge represents the multi-dimensional array (i.e. tensor) connecting nodes. The flexibility of the architecture allows cross-platform computation, e.g. one or multiple CPUs (or GPUs) on PC, server, mobile devices, etc. TensorFlow was initially developed by Google Brain for researches in machine learning and deep neural networks, however its universality allows the popularity in the application of other fields of computing.

Advantages of TensorFlow:

• Flexibility: Supporting low-level numerical calculation and C++ customized operators.computing.

• Transportability: Available from Server to PC to mobile devices, and compatible with CPU, GPU and TPU

• Distributed computation: Allows distributed parallel computation and designating calculation devices for specific operator

"High buildings rise from the ground", and TensorFlow also has its base, which are the key concepts of tensor, graph and automatic differenciate.

Please leave comments in the WeChat official account "Python与算法之美" (Elegant Python and Algorithms) if you want to communicate with the author about the content. The author will try best to reply given the limited time available.

You are also welcomed to reply 加群(join group) in the WeChat official account to join the group chat with the other readers.