torch.nn.MSEloss

计算公式：

loss_fn = torch.nn.MSELoss()

例子

import torch
loss_fn = torch.nn.MSELoss()
input = torch.randn(1,2)
target = torch.autograd.Variable(torch.randn(1,2))
loss = loss_fn(input, target)
print(input); print(target); print(loss)
print(input.size(), target.size(), loss.size())

运行结果

loss=((input1-target1)**2+(input2-target2)**2)/2=0.1996