What is Tensor in TensorFlow

This article is to share with you about what the Tensor in TensorFlow is, the editor thinks it is very practical, so I share it with you to learn. I hope you can get something after reading this article.

Tensor (tensor)

The word "tensor" was first introduced by William Ron Hamilton in 1846. Yes, it's the Hamilton who invented the quaternion:

Tensor is actually a multidimensional array (multidimensional array).

The purpose of Tensor is to create higher dimensional matrices and vectors.

An example of color

Color image files (RGB) are generally processed as 3D tensor, where element in each 2d array represents one pixel, and R represents Red,G for Green,B and Blue for Blue.

Multidimensional array

Draw a three-dimensional tensor into a cube:

A higher-dimensional tensor:

Initialize a vector 0-dimensional tf.tensor (1). Print (); 1-dimensional tf.tensor ([1, 2, 3, 4]). Print (); / / ortf.tensor1d ([1, 2, 3]). Print (); 2-dimensional tf.tensor ([[1, 2], [3, 4]). Print (); / ortf.tensor2d ([[1,2], [3,4]). Print () 3-dimensional tf.tensor ([1], [2], [[3], [4]]). Print (); / / ortf.tensor3d ([1], [2], [[3], [4]). Print (); 4-dimensional tf.tensor ([1], [2], [3], [4]). Print () / ortf.tensor4d ([1], [2], [[3], [4]). Print (); 5-dimensional tf.tensor ([1], [2], [[3], [4]). Print (); / / ortf.tensor5d ([1], [2], [3], [4]). Print () 6 dimensional tf.tensor ([1], [2], [3], [4]], [[5], [6], [7], [8]). Print (); / / ortf.tensor6d ([1], [2], [[3], [4]], [[5], [6], [7], [8]). Print ()

This is what the Tensor in TensorFlow is, and the editor believes that there are some knowledge points that we may see or use in our daily work. I hope you can learn more from this article. For more details, please follow the industry information channel.