Python | tensorflow.math.angle() method

TensorFlow is open-source python library designed by Google to develop Machine Learning models  and deep learning  neural networks.

angle() is method in tensorflow math module. This method is used to find the element wise argument of a tensor. By default all elements are considered as complex number (a+bi). In case of real number complex part (b) is considered as zero. atan2(b,a) is the argument calculated by this function.

Syntax:
tensorflow.math.angle(
    input, name
)

Argument:
1. input: It is a tensor. Allowed dtype for this tensor are  float, double, complex64, complex128.
2. name: It is an optional argument that defines the name for the operation.
 
Return:
It returns a tensor of type float32 or float64.

Example 1:

Python3

# importing the library
import tensorflow as tf

# initializing the constant tensor
a = tf.constant([-1.5 + 7.8j, 3 + 5.75j], dtype=tf.complex64)

# calculating the arguments
b = tf.math.angle(a)

# printing the argument tensor
print('Tensor: ',b)

Output:

Tensor:  tf.Tensor([1.7607845 1.0899091], shape=(2,), dtype=float32)

Example 2:

In case of real numbers calculated argument is always zero.

Python3

# importing the library
import tensorflow as tf

# initializing the constant tensor
a = tf.constant([-1.5, 3 ], dtype=tf.float64)

# calculating the arguments
b = tf.math.angle(a)

# printing the argument tensor
print('Tensor: ',b)

Output:

Tensor:  tf.Tensor([0. 0.], shape=(2,), dtype=float64)