Tensorflow.js tf.atan2() Function

Tensorflow.js is an open-source library that is being developed by Google for running machine learning models as well as deep learning neural networks in the browser or node environment.

The .atan2() function is used to find the arctangent of the stated tensor inputs and is done element wise. Moreover, it also helps in broadcasting.

Syntax :  

tf.atan2(a, b)

Parameters:  

• a: It is the first tensor input that can be of type tf.Tensor, or TypedArray, or Array.
• b: It is the second tensor input which can be of type tf.Tensor, or TypedArray, or Array, and it must have identical datatype as that of a.

Return Value: It returns the tf.Tensor object.

Example 1: In this example, we are defining an input tensor of integer type and then printing the atan2 value of it. For creating an input tensor we are utilizing the .tensor1d() method and in order to print the output we are using the .print() method.  

Javascript

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

// Defining first tensor input elements
const y = tf.tensor1d([9, 10, 11, 12]);

// Defining second tensor input elements
const z = tf.tensor1d([13, 14, 15, 17]);

// Calling atan2() method and
// Printing output
(y).atan2(z).print();

Output:

Tensor
    [0.6055371, 0.6202452, 0.6327478, 0.6146573]

Example 2: In this example, float type values are considered as tensor input and both the parameters are passed directly to the atan2 function.

Javascript

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

// Defining float values for first tensor
var val1 = [.5, 4.9, .275];

// Defining float values for second tensor
var val2 = [1.5, 5.9, .775];

// Calling tensor1d method
const y = tf.tensor1d(val1);
const z = tf.tensor1d(val2);

// Calling atan2() method
var res = tf.atan2(y,z);

// Printing output
res.print();

Output:

Tensor
    [0.3217588, 0.6930802, 0.340989]

Reference: https://js.tensorflow.org/api/latest/#atan2