均方误差损失函数（MSE，mean squared error)

推荐一下：深度学习AI-计算机视觉（CV）-整体解决方案课件（Yolo+Flask+Vue+Waitress+Nginx）

视频教程：https://www.bilibili.com/video/BV19h4y1874T/?spm_id_from=333.999.0.0

均方误差损失函数（MSE，mean squared error)

回归问题解决的是对具体数值的预测，比如房价预测、销量预测等等，解决回归问题的神经网络一般只有一个输出节点，这个节点的输出值就是预测值。本文主要介绍回归问题下的损失函数——均方误差（MSE，mean squared error）。
公式如下：

Pyorch实现的MSE

import torch
import numpy as np

loss_fn = torch.nn.MSELoss(reduce=False, size_average=False)

a=np.array([[1,2],[3,4]])
b=np.array([[2,3],[4,5]])

input = torch.autograd.Variable(torch.from_numpy(a))
target = torch.autograd.Variable(torch.from_numpy(b))

loss = loss_fn(input.float(), target.float())
print(input.float())
print(target.float())

print(loss)

a=np.array([[1,2],[3,4]])
b=np.array([[2,3],[4,6]])

loss_fn = torch.nn.MSELoss(reduce=True, size_average=True)

input = torch.autograd.Variable(torch.from_numpy(a))
target = torch.autograd.Variable(torch.from_numpy(b))

loss = loss_fn(input.float(), target.float())
print(input.float())
print(target.float())
print(loss)