Skip to content
Related Articles

Related Articles

Tensorflow.js tf.leakyRelu() Function

View Discussion
Improve Article
Save Article
  • Last Updated : 12 May, 2021

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

The .leakyRelu() function is used to find the leaky rectified linear of the stated tensor input and is done elements wise.


tf.leakyRelu(x, alpha?)


  • x: It is the tensor input, and it can be of type tf.Tensor, or TypedArray, or Array.
  • alpha: It is the optional parameter which is of type number. It defines the scaling factor for the negative values and the by default value is 0.2.

Return Value: It returns the tf.Tensor object.

Example 1: In this example, we are defining an input tensor and then printing the leaky rectified linear values. For creating an input tensor we are utilizing the .tensor1d() method and in order to print the output we are using the .print() method.  


// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Defining tensor input elements
const y = tf.tensor1d([4, -4, 38, NaN]);
// Calling leakyRelu() method and
// printing output


    [4, -0.8, 38, NaN]

Example 2: In this example, all the parameters are passed directly to the leakyRelu function.


// Importing the tensorflow.js library 
import * as tf from "@tensorflow/tfjs"
// Defining tensor input
var val = [3.6, 77, 5.78799797, 'a'];
// Calling tensor1d method
const y = tf.tensor1d(val);
// Calling leakyRelu() method
var res = tf.leakyRelu(y, 1.7)
// printing output


    [3.5999999, 77, 5.7879982, NaN]


My Personal Notes arrow_drop_up
Recommended Articles
Page :

Start Your Coding Journey Now!