Tensorflow tf.sub() Function

The tf.sub() function returns the subtraction of two tf.Tensor objects element wise. The tf.Tensor object represents the multidimensional array of numbers.

Syntax:

tf.sub( a, b )

Parameters:

• a: It contains the first tf.Tensor object. The value of this parameter can be tf.TensorTypedArray|Array.
• b: It contains the second tf.Tensor object that subtract from first tf.Tensor object. The value of this parameter can be (tf.Tensor|TypedArray|Array). The type of this parameter is same as type of a.

Return Value: This function returns the tf.Tensor object.

Example 1:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"

// Declare the Tensor array
const arr1 = tf.tensor1d([10, 20, 30, 40, 50]);
const arr2 = tf.tensor1d([5, 10, 15, 20, 25]);

// Use sub() function to subtract
// two Tensor objects
arr1.sub(arr2).print();

Output:

Tensor
    [5, 10, 15, 20, 25]

Example 2:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"

// Declare the Tensor array
const arr1 = tf.tensor1d([30, 40, 50]);
const arr2 = tf.tensor1d([5, 10, 15, 20, 25]);

// Use sub() function to subtract
// two Tensor objects
arr1.sub(arr2).print();

Output:

An error occurred on line: 7
Operands could not be broadcast together with shapes 3 and 5.

Example 3:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"

// Declare the Tensor array
const arr = tf.tensor1d([15, 10, 25, 20, 35]);

// Declare a number
const num = tf.scalar(30);

// Use sub() function to subtract number
// from Tensor object
arr.sub(num).print();

Output: 

Tensor
    [-15, -20, -5, -10, 5]

Reference: https://js.tensorflow.org/api/latest/#sub