Open In App

Tensorflow.js tf.layers build() Method

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 .build() function is used to create the weights of the layer stated. This method should be applied on every layers that hold weights. Moreover, its invoked when the apply() method is invoked in order to build the weights.



Syntax:

build(inputShape)

Parameters:



Return Value: It returns void.

Example 1:




// 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]}));
  
// Defining input
const input = tf.input({shape: [6, 2, 6]});
  
// Calling build method with its 
// parameter
model.layers[0].build([input.Shape]);
  
// Printing output
console.log(JSON.stringify(input.shape));
model.layers[0].getWeights()[0].print();

Output:

[null,6,2,6]
Tensor
    [[-0.3726568],
     [0.7343086 ],
     [-0.2459907]]

Here, getWeights() method is used to print the weights.

Example 2:




// 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: [2]}));
model.add(tf.layers.dense({units: 2}));
  
  
// Defining inputs
const input1 = tf.input({shape: [1, 2]});
const input2 = tf.input({shape: [1.7, 2.7, 6.5]});
  
// Calling build method with its 
// parameter
model.layers[0].build([input1.Shape]);
model.layers[1].build([input2.Shape]);
  
// Printing outputs
console.log(JSON.stringify(input1.shape));
console.log(JSON.stringify(input2.shape));
model.layers[0].getWeights()[0].print();
model.layers[1].getWeights()[0].print();

Output:

[null,1,2]
[null,1.7,2.7,6.5]
Tensor
    [[0.6224715],
     [1.2144204]]
Tensor
     [[0.8342852, 0.4770206],]

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


Article Tags :