PyTorch学习笔记（十一）——损失函数

忧郁小薯条_

已于 2023-05-16 15:37:28 修改

阅读量132

点赞数

文章标签： pytorch

于 2023-05-01 16:32:59 首次发布

本文链接：https://blog.csdn.net/weixin_45827876/article/details/130452420

版权

pytorch入门专栏收录该内容

17 篇文章 2 订阅

订阅专栏

本文介绍了PyTorch中的三种损失函数——L1Loss、MSELoss和CrossEntropyLoss，并展示了它们的使用示例。L1Loss计算绝对差，MSELoss计算均方误差，CrossEntropyLoss用于多分类问题。接着，文章演示了如何在神经网络中应用CrossEntropyLoss进行训练，并执行反向传播计算误差。

摘要由CSDN通过智能技术生成

1 损失函数

1.1 L1Loss

import torch
from torch.nn import L1Loss

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

# loss = L1Loss(reduction='sum')
loss = L1Loss() #默认是取平均的方式
result = loss(inputs,targets)
print(result)

1.2 MSELoss

import torch
from torch.nn import MSELoss

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

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

1.3 CrossEntropyLoss

适用于训练分类问题，有C个类别

import torch
from torch.nn import 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)

2 神经网络中用到 Loss Function

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

dataset = torchvision.datasets.CIFAR10("./datasets",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset,batch_size=1)

class myNN(nn.Module):
    def __init__(self):
        super(myNN, self).__init__()
        self.model1 = Sequential(
            Conv2d(in_channels=3,out_channels=32,kernel_size=5,stride=1,padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )

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

loss = CrossEntropyLoss()
mynn = myNN()
for data in dataloader:
    imgs,targets = data # imgs为输入，放入神经网络中
    outputs = mynn(imgs) # outputs为输入通过神经网络得到的输出，targets为实际输出
    # print(outputs)
    # print(targets)
    result_loss = loss(outputs,targets)
    print(result_loss) # 神经网络输出与真实输出的误差
    result_loss.backward() # backward反向传播，是对result_loss，而不是对loss