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. It helps developers to develop ML models in JavaScript, and use ML directly in the browser or in Node.js.
The tf.variable() function is used to create a new variable with the provided initial value.
Syntax:
tf.variable(initialValue, trainable, name, dtype)
Parameters:
- initialValue: The initial value of the tensor from which the new variable will be initialized.
- trainable: It is an optional parameter. It is of boolean type if true optimizers are allowed to update the variable and if false optimizers are not allowed to update it.
- name: It is also an optional parameter. It is of string type. It is used for the name of the variable used as a unique ID.
- dtype: It is also an optional parameter. If it is passed as the argument the intialValue will be changed to the specified dtype.
Return Value: This function returns tf.variable.
Example 1:
Javascript
// Creating and initializing a new variable var val = tf.variable(tf.tensor2d( [8, 2, 5, 6], [2, 2]));// Printing the tensorval.print() |
Output:
Tensor
[[8, 2],
[5, 6]]
Example 2:
Javascript
// Creating and initializing a new variable var val = tf.variable(tf.tensor([1, 2, 5, 6]));// Printing the tensorval.print() |
Output:
Tensor [1, 2, 5, 6]
Example 3:
Javascript
// Creating and initializing a new variable const x = tf.variable(tf.tensor([1, 2, 3]), true,"gfg",'complex64');// Printing the tensorx.print(); |
Output:
Tensor [1 + 0j, 2 + 0j, 3 + 0j]
Reference: https://js.tensorflow.org/api/latest/#variable
Whether you’re preparing for your first job interview or aiming to upskill in this ever-evolving tech landscape, neveropen 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!
