Tensorflow.js tf.selu() Function

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

The .selu() function is used to find the scaled exponential linear and is done element wise.

Syntax:

tf.selu(x)

Where, x < 0 ? scale * alpha * (exp(x) – 1) : x

Parameters:

x: It is the stated tensor input, and it can be of type tf.Tensor, TypedArray, or Array.

Return Value: It returns the tf.Tensor object.

Example 1:

Javascript

// Importing the tensorflow.js library 

import * as tf from "@tensorflow/tfjs"

// Defining tensor input elements 
const y = tf.tensor1d([-1, 76, 0, NaN, -4]); 

// Calling selu() method and 
// Printing output 
y.selu().print();

Output:

Tensor
    [-1.1113307, 79.8532791, 0, NaN, -1.7258986]

Example 2:

Javascript

// Importing the tensorflow.js library  

import * as tf from "@tensorflow/tfjs"

// Defining tensor input 

var val = [8.5, .14, .22, 'a']; 

// Calling tensor1d method 
const y = tf.tensor1d(val); 

// Calling selu() method 

var res = tf.selu(y) 

// Printing output 
res.print();

Output:

Tensor
    [8.9309587, 0.1470981, 0.2311542, NaN]

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

Article Tags :

JavaScript

Web Technologies

Tensorflow.js