Python – tensorflow.math.squared_difference()

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。

squared_difference()用于逐元素计算 (xy)(xy)。

Syntax: tensorflow.math.squared_difference(x, y, name)

Parameters:

• x: It’s a tensor. Allowed dtypes are bfloat16, half, float32, float64, complex64, complex128.
• y: It’s a tensor of same dtype as x.
• name(optional): It defines the name for the operation.

Returns: It returns a tensor.

示例 1：

Python3

# importing the library
import tensorflow as tf
  
# Initializing the input tensor
a = tf.constant([ -5, -7, 2, 5, 7], dtype = tf.float64)
b = tf.constant([ 1, 3, 9, 4, 7], dtype = tf.float64)
  
# Printing the input tensor
print('a: ', a)
print('b: ', b)
  
# Calculating result
res = tf.math.squared_difference(a, b)
  
# Printing the result
print('Result: ', res)

输出：

a:  tf.Tensor([-5. -7.  2.  5.  7.], shape=(5, ), dtype=float64)
b:  tf.Tensor([1. 3. 9. 4. 7.], shape=(5, ), dtype=float64)
Result:  tf.Tensor([ 36. 100.  49.   1.   0.], shape=(5, ), dtype=float64)

示例 2：采用复杂输入

Python3

# importing the library
import tensorflow as tf
  
# Initializing the input tensor
a = tf.constant([ -5 + 3j, -7-2j, 2 + 1j, 5-7j, 7 + 3j], dtype = tf.complex128)
b = tf.constant([ 1 + 5j, 3 + 1j, 9-5j, 4 + 3j, 7-6j], dtype = tf.complex128)
  
# Printing the input tensor
print('a: ', a)
print('b: ', b)
  
# Calculating result
res = tf.math.squared_difference(a, b)
  
# Printing the result
print('Result: ', res)

输出：

a:  tf.Tensor([-5.+3.j -7.-2.j  2.+1.j  5.-7.j  7.+3.j], shape=(5, ), dtype=complex128)
b:  tf.Tensor([1.+5.j 3.+1.j 9.-5.j 4.+3.j 7.-6.j], shape=(5, ), dtype=complex128)
Result:  tf.Tensor([ 40.+0.j 109.+0.j  85.+0.j 101.+0.j  81.+0.j], shape=(5, ), dtype=complex128)