TensorFlow Matrices

Any format of data(audio,images and video) has to be converted to the form of numbers(numpy arrays) for processing them and tensorflow has its own representaion of data in it’s internal implementation as shown below The following syntax  is a vector of vectors of the same length. This vector contains two elements,and each one represents a row of the matrix.

These tensors are even more nested vectors.A  2-by-3-by-2 tensor is [[[1,2], [3,4], [5,6]], [[7,8], [9,10], [11,12]]], which can be thought of as two matrices, each of size 3-by-2.The rank of tensor is 3 In general, the rank of a tensor is the number of indices required to specify an element.

This tensor can be thought of as multiple matrices stacked on top of each other. To access an element, you have to indicate the row and column, as well as which matrix is being accessed. Hence, rank of this tensor is 3.