Tensorflow.js tf.grads() Function

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. It also helps the developers to develop ML models in JavaScript language and can use ML directly in the browser or in Node.js.

The tf.grads() function takes a function f(x) and return a function gx

Syntax:

tf.grads (f)

Parameters:

f: This is the given function for which gradients are calculated.

Return Value: It returns an array.

Example 1:

Javascript

// Importing the @tensorflow/tjs library 

const tf=require("@tensorflow/tfjs") 
const f = (a, b) => b.add(a); 

// Grad function is used 
const g = tf.grads(f); 

// Tensor is declared 
const a = tf.tensor1d([5, 6]); 
const b = tf.tensor1d([-10, -20]); 

// Variables are defined 
const [gfg1] = g([b, a]); 

// Variable is printed 
gfg1.print();

Output:

Tensor
    [1, 1]

Example 2:

Javascript

// Importing the @tensorflow/tfjs library 

const tf=require("@tensorflow/tfjs") 
const f = (a) => a.mul(8); 

// Grad function is used 
const g = tf.grads(f); 

// Tensor is declared 
const a = tf.tensor1d([50, 60]); 

// Variables are defined 
const [gfg1] = g([a]); 

// Variable is printed 
gfg1.print();

Output:

Tensor
    [8, 8]

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

Article Tags :

JavaScript

Web Technologies

Tensorflow.js