TensorFlow is open-source python library designed by Google to develop Machine Learning models and deep learning neural networks. pow() is used to find element wise x^y.
Syntax: tf.math.pow(x, y, name)
Parameter:
- x: It’s the input tensor. Allowed dtype for this tensor are float16, float32, float64, int32, int64, complex64, or complex128.
- y: It’s the input tensor of same dtype as x.
- name(optional): It defines the name for the operation.
Returns: It returns a tensor of same dtype as x.
Example 1:
Python3
# Importing the libraryimport tensorflow as tf# Initializing the input tensora = tf.constant([.2, .5, .7, 1], dtype = tf.float64)b = tf.constant([.1, .3, 1, 5], dtype = tf.float64)# Printing the input tensorprint('a: ', a)print('b: ', b)# Calculating resultres = tf.math.pow(x = a, y = b)# Printing the resultprint('Result: ', res) |
Output:
a: tf.Tensor([0.2 0.5 0.7 1. ], shape=(4, ), dtype=float64) b: tf.Tensor([0.1 0.3 1. 5. ], shape=(4, ), dtype=float64) Result: tf.Tensor([0.85133992 0.8122524 0.7 1. ], shape=(4, ), dtype=float64)
Example 2: This example uses negative values in y that will raise error.
Python3
# importing the libraryimport tensorflow as tf# Initializing the input tensora = tf.constant([2, 5, 7, 1], dtype = tf.int64)b = tf.constant([-1, -6, 8, 0], dtype = tf.int64)# Printing the input tensorprint('a: ', a)print('b: ', b)# Calculating resultres = tf.math.pow(x = a, y = b)# Printing the resultprint('Result: ', res) |
Output:
a: tf.Tensor([2 5 7 1], shape=(4, ), dtype=int64)
b: tf.Tensor([-1 -6 8 0], shape=(4, ), dtype=int64)
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
in ()
11
12 # Calculating result
---> 13 res = tf.math.pow(x = a, y = b)
14
15 # Printing the result
4 frames
/usr/local/lib/python3.6/dist-packages/six.py in raise_from(value, from_value)
InvalidArgumentError: Integers to negative integer powers are not allowed [Op:Pow]
