tensorflow.math.atan2() function in Python

TensorFlow is open-source python library designed by Google to develop Machine Learning models and deep learning  neural networks. atan2() is used to find element wise arctangent of y/x.

Syntax: tf.math.atan2(y, x, name)

Parameters:

• y: It’s the input tensor. Allowed dtype for this tensor are bfloat16, half, float32, float64. 
• y: It’s the input tensor of same dtype as y.
• name(optional): It defines the name for the operation.
  

Returns:  It returns a tensor of same dtype as x.

Example 1:

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([ [-5, -7], [ 2, 0]], dtype = tf.float64)
b = tf.constant([ [1, 3], [9, 4]], dtype = tf.float64)

# Printing the input tensor
print('a: ', a)
print('b: ', b)

# Calculating result
res = tf.math.atan2(a, b)

# Printing the result
print('Result: ', res)

Output:

a:  tf.Tensor(
[[-5. -7.]
 [ 2.  0.]], shape=(2, 2), dtype=float64)
b:  tf.Tensor(
[[1. 3.]
 [9. 4.]], shape=(2, 2), dtype=float64)
Result:  tf.Tensor(
[[-1.37340077 -1.16590454]
 [ 0.21866895  0.        ]], shape=(2, 2), dtype=float64)

Example 2:

Python3

# Importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([ -.5, -.3, 0, .3, .5], dtype = tf.float64)
b = tf.constant([ 1, 2, 3, 4, 5], dtype = tf.float64)

# Printing the input tensor
print('a: ', a)
print('b: ', b)

# Calculating tangent
res = tf.math.atan2(a, b)

# Printing the result
print('Result: ', res)

Output:

a: tf.Tensor([-0.5 -0.3 0. 0.3 0.5], shape=(5, ), dtype=float64) b: tf.Tensor([1. 2. 3. 4. 5.], shape=(5, ), dtype=float64) Result: tf.Tensor([-0.46364761 -0.14888995 0. 0.07485985 0.09966865], shape=(5, ), dtype=float64)