Tensorflow.js tf.layers.multiply() 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.multiply() function is used to perform element-wise multiplication of an array of inputs.
Syntax:
tf.layers.multiply()
Parameters:
- inputShape: If this parameter is defined, it will create another input layer to insert before this layer.
- batchInputShape: If this parameter is defined, it will create another input layer to insert before this layer.
- batchSize: Used to construct batchInputShape, if not already specified.
- dtype: Specifies the data-type for this layer. Defaults value of this parameter is ‘float32’.
- name: Specifies name for this layer.
- updatable: Specifies whether the weights of this layer can be updated by fit or not.
- trainable: Specifies whether the weights of this layer are updatable by fit.
- weights: Specifies the initial weight values of the layer.
- inputDType: ‘float32’ or ‘int32’ or ‘bool’ or ‘complex64’ or ‘string’.
Return value: Single tensor of same type as input tensors.
Example 1:
Javascript
import * as tf from "@tensorflow/tfjs"
const input1 = tf.input({shape: [3, 2]})
const input2 = tf.input({shape: [3, 2]})
const input3 = tf.input({shape: [3, 2]})
const multiplyLayer = tf.layers.multiply()
const product = multiplyLayer.apply([input1, input2, input3])
console.log(JSON.stringify(product.shape))
|
Output:
[null,3,2]
Note: Here null denotes the undetermined batch size.
Example 2:
Javascript
import * as tf from "@tensorflow/tfjs"
const input1 = tf.tensor([-2, 1, 0, 5]);
const input2 = tf.tensor([3, 2, 3, 2]);
const input3 = tf.tensor([4, 3, 1, 2]);
const multiplyLayer = tf.layers.multiply();
const product = multiplyLayer.apply(
[input1, input2, input3]);
console.log(product);
|
Output:
Tensor
[-24, 6, 0, 20]
Reference: https://js.tensorflow.org/api/latest/#layers.multiply
Last Updated :
19 Nov, 2021
Like Article
Save Article
Share your thoughts in the comments
Please Login to comment...