Skip to content
Related Articles

Related Articles

Improve Article
Save Article
Like Article

Tensorflow.js tf.losses.softmaxCrossEntropy() Function

  • Last Updated : 23 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.js tf.losses.softmaxrossEntropy() function Computes the softmax cross entropy loss between two tensors and returns a new tensor.


    logits, weights, labelSmoothing, reduction)

Parameters: This function accepts five parameters (in which the last three are optional) which are illustrated below:

  • onehotLabels: It is a hot encoded label that has the same dimensions as predictions.
  • logits: It is the predicted outputs.
  • weights: These are those tensors whose rank is either 0 or 1, and they must be broad castable to loss of shape.
  • labelSmoothing: If the value of this parameter is greater than 0, then it smooths the labels.
  • reduction: It is the type of reduction to apply to loss. It must be of Reduction type.

Note: Parameters like weights, labelSmoothing, and reduction are optional.

Return Value: It returns a tensor having softmax cross-entropy loss between two tensors.


// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
// Creating onehotLabels tensor
const a  = tf.tensor2d([[1, 4, 5], [5, 5, 7]]);
// Creating logits tensor
const b    = tf.tensor2d([[3, 2, 5], [3, 2, 7]])
// Computing soft max cross entropy distance
softmax_cross_entropy = tf.losses.softmaxCrossEntropy(a, b)



Example 2: In this example, we are passing on an optional parameter that is label smoothing. If it is greater than 0, then smooth the labels. 


// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
// const tf = require("@tensorflow/tfjs")
// Creating labels tensor
const a = tf.tensor2d([[1,2,3,4,5], [7,8,9,10,11]])
// Creating predictions tensor
const b = tf.tensor2d([[6,735,8,59,10], [45,34,322,2,3]])
const c = tf.tensor2d([[4,34,34,2,4],[65,34,3,2,3]])
// Computing cross entropy  with an option parameter number
softmax_cross_entropy = tf.losses.softmaxCrossEntropy(a, b, 5)






My Personal Notes arrow_drop_up
Recommended Articles
Page :

Start Your Coding Journey Now!