Tensorflow.js tf.layers.repeatVector() 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.layers.repeatVector() function is used to repeat the input n number of times in a new specified dimension. It is an inbuilt function of TensorFlow’s.js library.

Syntax:

tf.layers.repeatVector(n)

Parameters:

• n: Integer, specifying the number of times the input will be repeated.

Return value: It returns the tf.layers.Layer

Example 1:

Javascript

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


// Create a new model
const model = tf.sequential();

// Add repeatVector layer to the model
model.add(tf.layers.repeatVector({
    n: 5, inputShape: [2]}
));

const x = tf.tensor2d([[10, 15]]);

console.log(model.predict(x).shape)

Output:

1, 5, 2

Example 2:

Javascript

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

// Create a new model
const model = tf.sequential();

// Add repeatVector layer to the model
model.add(tf.layers.repeatVector(
      {n: 8, inputShape: [2]}
));

const x = tf.tensor2d([[0,1]]);

model.predict(x).print();

Output:

Tensor
    [[[0, 1],
      [0, 1],
      [0, 1],
      [0, 1],
      [0, 1],
      [0, 1],
      [0, 1],
      [0, 1]]]

Reference: https://js.tensorflow.org/api/latest/#layers.repeatVector