##Understanding Tensors and Graphs before diving into TensorFlow
TensorFlow the latest from Google for deep learning libraries. I started learning it some days back and already started having fun with it! Before we deep dive into tensorFlow a good knowledge of tensors and graphs are preferred as those are the two basic building blocks of the TensorFlow in Google’s deep learning framework.
What are Tensors:
Wikipedia says
Tensors are geometric objects that describe linear relations between geometric vectors, scalars, and other tensors. Elementary examples of such relations include the dot product, the cross product, and linear maps. Geometric vectors, often used in physics and engineering applications, and scalars themselves are also tensors.
But tensorflow explains Tensors as a Multidimensional Arrays. But Tensors and multidimensional arrays are two different type of object. Tensor is a type of function and multidimensional array is a data structure suitable for representing a tensor in a coordinate system.
What are Graphs:
According to official tensorflow blog on getting started A computational graph is a series of tensorflow operations arranged in a graph of nodes. Each node takes zero or more tensors as inputs and produce a tensor as an output.
Reference: https://www.analyticsvidhya.com/blog/2017/03/tensorflow-understanding-tensors-and-graphs/