Python – tensorflow.math.reciprocal_no_nan()

TensorFlow 是由 Google 设计的开源Python库，用于开发机器学习模型和深度学习神经网络。 reciprocal_no_nan()用于查找 x 的元素安全倒数，即如果 x 为 0，则它的倒数也为 0。

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

Parameter:

• x: It’s the input tensor. Allowed dtype for this tensor are bfloat16, half, float32, float64, int32, int64, complex64, complex128.
• name(optional): It’s defines the name for the operation.

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

示例 1：此示例使用实张量。

Python3

# Importing the library
import tensorflow as tf
  
# Initializing the input tensor
a = tf.constant([0, 2, -3, -4], dtype = tf.float64)
  
# Printing the input tensor
print('Input: ', a)
  
# Calculating result
res = tf.math.reciprocal_no_nan(a)
  
# Printing the result
print('Result: ', res)

输出：

Input:  tf.Tensor([ 0.  2. -3. -4.], shape=(4, ), dtype=float64)
Result:  tf.Tensor([ 0.          0.5        -0.33333333 -0.25      ], shape=(4, ), dtype=float64)

示例 2：此示例使用复张量。

Python3

# importing the library
import tensorflow as tf
  
# Initializing the input tensor
a = tf.constant([0 + 0j, 2-5j, -3 + 7j, -4-8j], dtype = tf.complex128)
  
# Printing the input tensor
print('Input: ', a)
  
# Calculating result
res = tf.math.reciprocal_no_nan( a)
  
# Printing the result
print('Result: ', res)

输出：

Input:  tf.Tensor([ 0.+0.j  2.-5.j -3.+7.j -4.-8.j], shape=(4, ), dtype=complex128)
Result:  tf.Tensor(
[ 0.        +0.j          0.06896552+0.17241379j -0.05172414-0.12068966j
 -0.05      +0.1j       ], shape=(4, ), dtype=complex128)