Skip to content
Related Articles

Related Articles

Improve Article
Save Article
Like Article

Tensorflow.js tf.metrics.categoricalCrossentropy() Function

  • Last Updated : 26 May, 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. It also helps the developers to develop ML models in JavaScript language and can use ML directly in the browser or in Node.js.

The tf.metrics.categoricalCrossentropy() function categorically finds the categorical crossentropy between a target and an output tensor.

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!

Syntax:

tf.metrics.categoricalCrossentropy(yTrue, yPred)

Parameters: This function accepts the following two parameters:



  • yTrue: It is the truth tensor, and it is of type tf.Tensor.
  • yPred: It is the prediction tensor, and it is of type tf.Tensor.

Return Value: It returns the tf.Tensor object.

Example 1:

Javascript




// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
  
// Initialising first 2d tensor.
let geek1 = tf.tensor2d([[2, 4], [1, 3]]);
  
// Initialising second 2d tensor.
let geek2 = tf.tensor2d([11, 22, 33, 44], [2, 2]);
  
// Using .categoricalCrossentropy() function
// to find categorical accuracy metric.
let result = tf.metrics.categoricalCrossentropy(geek1, geek2);
  
// Printing the result.
result.print();

Output:

Tensor
    [3.8190854, 2.526145]

Example 2:

Javascript




// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
  
// Using .categoricalCrossentropy() function
// to find categorical accuracy metric
tf.metrics.categoricalCrossentropy(
  tf.tensor1d([1, 2]), 
   tf.tensor2d([50], [1, 1]))
      .print();

Output:

Tensor
    [4e-7]

Reference: https://js.tensorflow.org/api/3.6.0/#metrics.categoricalCrossentropy




My Personal Notes arrow_drop_up
Recommended Articles
Page :