Tensorflow.js tf.zeros() 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.

The tf.zeros() function is used to create a new tensor with all elements set to zero.

Syntax:

tf.zeros(shape, dataType)

Parameters:

• shape: It takes the shape of the tensor we are going to generate.
• dataType: It is the type of tensor in the resulting element. It can be a ‘float32′, ‘int32′ or ‘bool’. It defaults to the "float32" value. It is an optional parameter.

Return Value: It returns the tensor of the given shape with all elements set to zero.

Example 1: In this example, we are creating a tensor of shape 1*1 using tf.zeros().

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"

// Creating a shape variable
// which stores the shape
var shape = [1,1]

// Creating the tensor
var val = tf.zeros(shape)

// Printing the tensor
val.print()

Output: 

Tensor
     [[0],]

Example 2: In this example, we are creating a tensor of shape 2*2 using tf.zeros() and with dataType parameter.

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"

// Creating a shape variable
// which stores the shape
var shape = [2, 2]

// Creating a d_Type variable
// which stores the data-type
var d_Type = 'bool'

// Creating the tensor
var val = tf.zeros(shape, d_Type)

// Printing the tensor
val.print()

 
Output: 

Tensor
    [[false, false],
     [false, false]]

Example 3: In this example, we are creating a tensor of shape 1*1 using tf.zeros().

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"

// Creating a shape variable
// which stores the shape
var shape = [3,3]

// Creating the tensor
var val = tf.zeros(shape)

// Printing the tensor
val.print()

 
Output: 

Tensor
    [[0, 0, 0],
     [0, 0, 0],
     [0, 0, 0]]

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