运行代码时报错： TypeError: unsupported operand type(s) for -: ‘list‘ and ‘list‘

建立均方误差函数时，运行代码时报错： TypeError: unsupported operand type(s) for -: 'list' and 'list'

import numpy as np
def mean_squared(y, t):
    """
    :param y:神经网络输出y
    :param t: 监督数据
    :return: 均方误差
    """
    return 0.5*np.sum((y-t)**2)

t = [0,0,1,0,0,0,0,0]
y = [0.1,0.05,0.1,0.0,0.05,0.1,0.0,0.6]
mean_square = mean_squared(y,t)

print(mean_square)

代码输出：

Traceback (most recent call last):
  File "D:\pycharm\pythonProject2\deep-learing\均方误差.py", line 12, in <module>
    mean_square = mean_squared(y,t)
  File "D:\pycharm\pythonProject2\deep-learing\均方误差.py", line 8, in mean_squared
    return 0.5*np.sum((y-t)**2)
TypeError: unsupported operand type(s) for -: 'list' and 'list'

出错原因： 列表支持加法运算（合并列表），但是不支持减法运算，如下代码所示：

#  列表执行加法操作
a = [11,22,33]
b = [1,2,3]
print(a+b)

代码运行正常：

[11, 22, 33, 1, 2, 3]

#  列表执行减法操作
a = [11,22,33]
b = [1,2,3]
print(a-b)

代码运行报错：

TypeError: unsupported operand type(s) for -: 'list' and 'list'

正确解决方式：使用numpy

import numpy as np

a=np.array([11,22,33])
print(a)
b=np.array([1,2,3])
print(b)
print(a-b)

代码运行正常：

[11 22 33]
[1 2 3]
[10 20 30]

因此解决均方误差函数的方法时：使用numpy

t = np.array([0,1,0,0,0,0])
y = np.array([0.05,0.1,0.05,0.1,0.0,0.6])

或者：

m = mean_squared_error(np.array(y),np.array(t))

所以，正确的完整代码时：

import numpy as np
def mean_squared(y, t):
    """
    :param y:神经网络输出y
    :param t: 监督数据
    :return: 均方误差
       return 0.5*np.sum((y-t)**2)

t = np.array([0,0,1,0,0,0,0,0])
y = np.array([0.1,0.05,0.1,0.0,0.05,0.1,0.0,0.6])
mean_square = mean_squared(y,t)
# mean_square = mean_squared(np.array(y),np.array(t))

print(mean_square)

0.5975