Tensorflow.js tf.valueAndGrad() Function
Last Updated :
21 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.valueAndGrad() function is used to return the gradient of the specified function f(x) with respect to x along with the value of f().
Syntax:
tf.valueAndGrad (f)
Parameters: This function accepts a parameter which is illustrated below:
- f: The specified function f(x) for which gradient is being calculated.
Return Value: It returns the gradient of the specified function f(x) with respect to x along with the value of f().
Example 1:
Javascript
import * as tf from "@tensorflow/tfjs"
const f = x => x.square();
const g = tf.valueAndGrad(f);
const x = tf.tensor1d([0, 1, 2, 3]);
const {value, grad} = g(x);
console.log('value ');
value.print();
// Getting the gradient of f(x) at
// the above tensor values
console.log(' grad');
grad.print();
|
Output:
value
Tensor
[0, 1, 4, 9]
grad
Tensor
[0, 2, 4, 6]
Example 2:
Javascript
import * as tf from "@tensorflow/tfjs"
const g = tf.valueAndGrad(x => x.pow(tf.scalar(3, 'int32 ')));
// Using a Tensor of values at which
// value of gradient is calculated
const {value, grad} = g(tf.tensor1d([-1, 0, 0.3, 4]));
// Getting the value of f()
console.log(' value ');
value.print();
// Getting the gradient of f(x)
console.log(' grad');
grad.print();
|
Output:
value
Tensor
[-1, 0, 0.027, 64]
grad
Tensor
[3, 0, 0.27, 48]
Reference:https://js.tensorflow.org/api/latest/#valueAndGrad
Share your thoughts in the comments
Please Login to comment...