Tensorflow.js tf.Variable class

0 0 2 minutes read

TensorFlow is an open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks in the browser or node environment.

The tf.Variable class is used to make a new mutable tf.Tensor and is provided with an assign value that copies the tf.Tensor to this new variable containing the same shape and dtype.

tf.Variable class extends tf.Tensor class.

Syntax:

tensorflow.Variable(initialTensor)

Parameters:

initialTensor: It is the initial tensor that is assigned to the Variable class object.

Return Value: It returns nothing (i.e. void).

Example 1: This example only uses the initial value to create tf.Variable object. No optional parameters are passed.

Javascript

// Defining tf.Tensor object for initial value
initialValue = tf.tensor([[1, 2, 3]])
 
// Defining tf.Variable object 
const x = new tf.Variable(initialValue);
 
// Checking variables dtype
console.log("dtype:", x.dtype)
 
// Checking variable shape
console.log("shape:", x.shape)
 
// Printing the tf.Variable object
x.print()

Output:

dtype: float32
shape: 1,3
Tensor
     [[1, 2, 3],]

Example 2: This example uses optional parameters along with the initial value to create a Variable object.

Javascript

// Defining tf.Tensor object for initial value
initialValue = tf.tensor([[1, 2, 3]])
 
// Defining tf.Variable object 
const x = new tf.Variable(initialValue,
    false, 'example_variable', 'int32');
 
// Checking if variable is trainable
console.log("Is trainable:", x.trainable)
 
// Checking variables dtype
console.log("dtype:", x.dtype)
 
// Checking variable shape
console.log("shape:", x.shape)
 
// Checking variable name
console.log("Name:", x.name)
 
// Printing the tf.Variable object
x.print()

Output:

Is trainable: false
dtype: int32
shape: 1,3
Name: example_variable
Tensor
     [[1, 2, 3],]

Example 3: This example creates a tf.Variable object using initial value then again adds the initial value to the Variable.

Javascript

// Defining tf.Tensor object for initial value
initialValue = tf.tensor([[1, 2, 3]])
 
// Defining tf.Variable object 
const x = new tf.Variable(initialValue);
 
// Printing the tf.Variable object
x.print()
 
// Adding initial value Tensor to Variable
result = x.add(initialValue)
 
// Printing result
result.print()

Output:

Tensor
     [[1, 2, 3],]
Tensor
     [[2, 4, 6],]

Whether you’re preparing for your first job interview or aiming to upskill in this ever-evolving tech landscape, zambiatek Courses are your key to success. We provide top-quality content at affordable prices, all geared towards accelerating your growth in a time-bound manner. Join the millions we’ve already empowered, and we’re here to do the same for you. Don’t miss out – check it out now!