一个损失函数需要一对输入:模型输出和目标,然后计算一个值来评估输出距离目标有多远。
loss = criterion(output, target)
有一些不同的损失函数在 nn 包中。一个简单的损失函数就是 nn.MSELoss ,这计算了均方误差。
criterion = nn.MSELoss()
import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net,self).__init__()
self.conv1 = nn.Conv2d(1,6,5)
self.conv2 = nn.Conv2d(6,16,5)
self.fc1 = nn.Linear(16*5*5, 120)
self.fc2 = nn.Linear(120,84)
self.fc3 = nn.Linear(84,10)
def forward(self,x):
x= F.max_pool2d(F.relu(self.conv1(x)),(2,2))
x= F.max_pool2d(F.relu(self.conv2(x)),2)
x= x.view(-1,self.num_flat_feature(x))
x = F.relu(self.fc1(x))
x= F.relu(self.fc2(x))
x = self.fc3(x)
return x
def num_flat_feature(self,x):
size = x.size()[1:]
num_features=1
for s in size:
num_features *=s
return num_features
net = Net()
input = torch.randn(1,1,32,32)
output=net(input)
target = torch.randn(10) # a dummy target, for example
-1在这里的意思是让电脑帮我们计算
target = target.view(1,-1)
#举个栗子
import torch
a = torch.arange(0,20) #此时a的shape是(1,20)
a.view(4,5).shape #输出为(4,5)
a.view(-1,5).shape #输出为(4,5)
a.view(4,-1).shape #输出为(4,5)
criterion = nn.MSELoss()
loss = criterion(output, target)
print(loss)