LossFunction

nn.LiLoss()

• 
• 可以取平均也可以取和

nn.MSELoss()

• 比LiLoss()多了一个平方
• 

CrossEntropyLoss()

• 
• 示例代码：

import torch
from torch.nn import L1Loss, MSELoss, CrossEntropyLoss
input = torch.tensor([1,2,5],dtype=torch.float32)
target = torch.tensor([1,2,3],dtype=torch.float32)
input = torch.reshape(input,(1,1,1,3))
target = torch.reshape(target,(1,1,1,3))
# L1Loss()
loss = L1Loss(reduction='sum')
result = loss(input,target)
# MSELoss()
mse_loss = MSELoss()
result_mse = mse_loss(input,target)
print(result)
print(result_mse)
# CrossEntropyLoss()
x = torch.tensor([0.1,0.2,0.3])
y = torch.tensor([1])
x = torch.reshape(x,(1,3))
loss_cross = CrossEntropyLoss()
result_cross = loss_cross(x,y)
print(result_cross)

反向传播

• 示例代码：

from torch import nn
import torchvision
from torch.nn import Conv2d, Sequential, MaxPool2d, Flatten, Linear, CrossEntropyLoss
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("./download_data",transform=torchvision.transforms.ToTensor(),
                                      train=False, download=True)
dataloader = DataLoader(dataset,batch_size=1)
class Liucy(nn.Module):
    def __init__(self):
        super(Liucy,self).__init__()
        self.modle = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self,x):
        x = self.modle(x)
        return x
liu = Liucy()
cross = CrossEntropyLoss()
for data in dataloader:
    img,label = data
    output = liu(img)
    # print(output) #最后会有十个分类
    result = cross(output,label)
    result.backward()
    print(result)