P13：损失函数与反向传播-优快云博客

本文链接：https://blog.youkuaiyun.com/The_friends/article/details/128682625

该文介绍了三种常用的损失函数在PyTorch中的使用：L1Loss用于计算绝对差，MSELoss计算均方误差，CrossEntropyLoss用于分类问题。接着展示了如何将损失函数与神经网络结合，通过反向传播更新网络参数。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1、损失函数的使用（L1loss）：

import torch
from torch.nn import L1Loss, MSELoss, CrossEntropyLoss

inputs = torch.tensor([1,2,3], dtype=torch.float32)
targets = torch.tensor([1,2,5], dtype=torch.float32)

inputs = torch.reshape(inputs, (1,1,1,3))
targets = torch.reshape(targets, (1,1,1,3))

loss = L1Loss()
result = loss(inputs, targets)

结果如下：

2、损失函数的使用（MSE）：

loss_mse = MSELoss()
result_mse = loss_mse(inputs, targets)
print(result_mse)

结果如下：

3、损失函数的使用（CrossRntropy）：

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)

结果如下：

4、损失函数与神经网络的结合：

import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear, CrossEntropyLoss
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("dataset",train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(dataset, batch_size=1)
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2, stride=1),
            MaxPool2d(kernel_size=2),
            Conv2d(32, 32, kernel_size=5, padding=2, stride=1),
            MaxPool2d(kernel_size=2),
            Conv2d(32, 64, kernel_size=5, padding=2, stride=1),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

    def forward(self, x):
        x = self.model1(x)
        return x

loss = CrossEntropyLoss()
tudui = Tudui()
for data in dataloader:
    imgs, targets = data
    outputs = tudui(imgs)
    # print(outputs)
    # print(targets)
    result_loss = loss(outputs, targets)
    result_loss.backward()
    print()

loss() 计算完损失之后，使用result_loss.backward() 计算grad，为后续更新网络的使用。