Python – tensorflow.math.round()

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

Syntax: tf.math.round(x, name)

Parameter:

• x: It’s the input tensor. Allowed dtype for this tensor are bfloat16, half, float32, float64.
• 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([.2, 1.6, 3.7, 1], dtype = tf.float64)

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

# Calculating result
res = tf.math.round(a)

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

Output:

a:  tf.Tensor([0.2 1.6 3.7 1. ], shape=(4, ), dtype=float64)
Result:  tf.Tensor([0. 2. 4. 1.], shape=(4, ), dtype=float64)

Example 2: It rounds half to even.

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([2.5, 5.5, 1.5, 6.5], dtype = tf.float64)

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

# Calculating result
res = tf.math.round(a)

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

Output:

a:  tf.Tensor([2.5 5.5 1.5 6.5], shape=(4, ), dtype=float64)
Result:  tf.Tensor([2. 6. 2. 6.], shape=(4, ), dtype=float64)