Tensorflow.js tf.maximum() Function

Last Updated : 12 May, 2021

Tensorflow.js is an open-source library developed by Google for running machine learning models and deep learning neural networks in the browser or node environment.

The tf.maximum() function is used to return the maximum of the two specified tensors element-wise. It supports broadcasting.

Syntax:

tf.maximum (a, b)

Parameters: This function accepts two parameters which are illustrated below:

a: The first specified tensor.
b: The second specified tensor. It must have same data type as "a".

Return Value: It returns the maximum of the two specified tensors "a" and "b" element-wise.

Example 1:

JavaScript

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

// Initializing two tensors
const a = tf.tensor1d([3, 5, 7, 9]);
const b = tf.tensor1d([1, 6, 8, 2]);

// Calling the .maximum() function
a.maximum(b).print();

Output:

Tensor
   [3, 6, 8, 9]

Example 2:

JavaScript

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

// Using two tensors as the parameter
// for the .maximum() function
tf.tensor1d([3, 5, 7, 9]).maximum(tf.tensor1d([6])).print();

Output:

Tensor
   [6, 6, 7, 9]

Example 3:

JavaScript

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

// Broadcasting maximum a with b
const a = tf.tensor1d([1, 2, 7, 3, 4]);
const b = tf.scalar(4);

// Calling the .maximum() function
a.maximum(b).print();