Skip to content
Related Articles

Related Articles

Improve Article
Save Article
Like Article

Tensorflow.js tf.layers dispose() Method

  • Last Updated : 27 Jul, 2021

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 dispose() function is used to dispose the weights of the layers stated. Moreover, it decrease the stated layer object’s reference count via one.

Hey geek! The constant emerging technologies in the world of web development always keeps the excitement for this subject through the roof. But before you tackle the big projects, we suggest you start by learning the basics. Kickstart your web development journey by learning JS concepts with our JavaScript Course. Now at it's lowest price ever!

Note:

  • Here, a layer is reference counted. Where, its reference number is raised via one for the first time its apply() method is invoked as well as when it becomes a segment of a new Node by invoking the apply() method on a tf.SymbolicTensor.
  • Here, when a layer’s reference number becomes zero then its every single weights will be disposed and the basic memory i.e. the textures assigned in WebGL will also be cleared.
  • When the reference count of a layer is greater than zero following the deduction then the Layer weights will not be disposed.
  • Finally, when a Layer is disposed, it cannot be utilized in the invokes like apply(), getWeights() or setWeights() any longer.

Syntax:



dispose()

Parameters:

This method has no parameters.

Return Value: It returns DisposeResult.

Example 1:

Javascript




// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
  
// Creating a model
const model = tf.sequential();
  
// Adding a layer
model.add(tf.layers.dense({units: 1, inputShape: [3]}));
  
// Calling dispose method
const val = model.layers[0].dispose();
  
// Printing output
console.log(val);

Output:

{
  "refCountAfterDispose": 0,
  "numDisposedVariables": 2
}

Example 2:

Javascript




// Importing the tensorflow.js library
//import * as tf from "@tensorflow/tfjs"
  
// Creating a model
const model = tf.sequential();
  
// Adding layers
model.add(tf.layers.dense({units: 1, inputShape: [5, 1]}));
model.add(tf.layers.dense({units: 4}));
model.add(tf.layers.dense({units: 2, inputShape: [6], batchSize: 5}));
  
// Calling dispose() method
const val1 = model.layers[0].dispose();
const val2 = model.layers[1].dispose();
const val3 = model.layers[2].dispose();
  
// Printing output
console.log(val1);
console.log(val2);
console.log(val3);

Output:

{
  "refCountAfterDispose": 0,
  "numDisposedVariables": 2
}
{
  "refCountAfterDispose": 0,
  "numDisposedVariables": 2
}
{
  "refCountAfterDispose": 0,
  "numDisposedVariables": 2
}

Reference: https://js.tensorflow.org/api/latest/#tf.layers.Layer.dispose




My Personal Notes arrow_drop_up
Recommended Articles
Page :

Start Your Coding Journey Now!