Skip to content
Related Articles

Related Articles

Improve Article

Tensorflow.js tf.train.Optimizer class .applyGradients() Method

  • Last Updated : 03 Sep, 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.

Tensorflow.js tf.train.Optimizer .apply Gradients( ) is used for Updating variables by using the computed gradients.

Syntax: 

Optimizer.applyGradients( variableGradients );

Parameters:

  • variableGradients( { [ name : String ] : tf.Tensor } | NamedTensor[ ]):  A mapping of variable name to its gradients value.

Returns: void



Example 1:   In this example, we will updates the value of variable with the help of applyGradients( ) method of the default value optimizer. 

Javascript




// Importing tensorflow
import * as tf from "@tensorflow/tfjs"
     
const xs = tf.tensor1d([0, 1, 2]);
const ys = tf.tensor1d([1.58, 2.24, 3.41]);
     
const x = tf.scalar(Math.random()).variable();
const y = tf.scalar(Math.random()).variable();
     
// Define a function f(x) = x^2 + y.
const f = x => (x.square()).add(y);
 
     
const learningRate = 0.05;
     
// Create adagrad optimizer
const optimizer =
tf.train.rmsprop(learningRate);
     
 
 
// Updating variable
const varGradients = f(xs).dataSync();
for (let i = 0; i < 5; i++){
  optimizer.applyGradients(varGradients);
}
 
// Make predictions.
console.log(
`x: ${x.dataSync()}, y: ${y.dataSync()}`);
const preds = f(xs).dataSync();
preds.forEach((pred, i) => {
console.log(`x: ${i}, pred: ${pred}`);
});

Output:  

x: -0.526353657245636, y: 0.15607579052448273
x: 0, pred: 0.15607579052448273
x: 1, pred: 1.1560758352279663
x: 2, pred: 4.156075954437256

Example 2:  In this example, we will update the variable with the help of applyGradients( ) method of custom optimizer.  

Javascript




// Importing tensorflow
import * as tf from "@tensorflow/tfjs"
     
const xs = tf.tensor1d([0, 1, 2, 3]);
const ys = tf.tensor1d([1.3, 3.7, 12.4, 26.6]);
     
// Choosing random coefficients
const a = tf.scalar(Math.random()).variable();
const b = tf.scalar(Math.random()).variable();
const c = tf.scalar(Math.random()).variable();
     
// Defining function f = (a*x^2 + b*x + c)
const f = x => a.mul(x.mul(3)).add(b.square(x)).add(c);
 
     
// Setting configurations for our optimizer
const learningRate = 0.01;
const initialAccumulatorValue = 10;
 
     
// Create the Optimizer
const optimizer = tf.train.adagrad(learningRate,
        initialAccumulatorValue);
     
// Updating variable
 const varGradients = f(xs).dataSync();
 for (let i = 0; i < 8; i++){
 optimizer.applyGradients(varGradients)}
 
// Make predictions.
console.log(`a: ${a.dataSync()},
    b: ${b.dataSync()}, c: ${c.dataSync()}`);
const preds = f(xs).dataSync();
preds.forEach((pred, i) => {
console.log(`x: ${i}, pred: ${pred}`);
});

Output: 

a: 0.032658617943525314,
    b: 0.9213025569915771, c: 0.7167015671730042
x: 0, pred: 1.565500020980835
x: 1, pred: 1.663475751876831
x: 2, pred: 1.7614517211914062
x: 3, pred: 1.8594274520874023

Reference: https://js.tensorflow.org/api/3.8.0/#tf.train.Optimizer.applyGradients

 




My Personal Notes arrow_drop_up
Recommended Articles
Page :