Tensorflow.js tf.metrics.meanSquaredError() Function

Last Updated : 22 Jul, 2021

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 Tensorflow tf.metrics.meanSquaredError() function is a Loss or metric function used to Computes the mean squared error between y_true and y_pred. the y_true is a truth tensor and y_pred is the Prediction Tensor.

Syntax:

tf.metrics.meanSquaredError(tensor1, tensor2);

Parameters: This function accepts two parameters which are illustrated below:

tensor1: It is the truth tensor (y_true).
tensor2: It is the prediction tensor (y_pred).

Return Value: It returns the mean square error tensor between truth tensor and prediction tensor.

Example 1:

JavaScript

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

// Creating the tensor
let truth = tf.tensor1d([6, 4]);
let prediction = tf.tensor1d([-3, -4]);

// Calculating mean squared Error 
// between truth and prediction tensor
const mse = tf.metrics.meanSquaredError(truth, prediction);

// Printing mean square error
mse.print();

Output:

Tensor
    72.5

Example 2:

JavaScript

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

// Calculating mean squared Error between 
// truth and prediction tensor
let mse = tf.metrics.meanSquaredError(
    tf.tensor1d([0, 1, 2, 3]), 
    tf.tensor1d([-8,-9, -10, -11])
);

// Printing mean square error 
mse.print();