损失函数和反向传播

损失函数Loss

1.概念理解

2.官方文档
使用不难，要明白loss是如何计算的需要一定数学功底

（1）L1loss

X:1,2,3
Y:1,2,5
L1loss = (0+0+2) / 3 = 0.6
MSE = (0+0+2^2) / 3 = 1.333

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)
print(inputs.shape)

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

loss = L1Loss(reduction='mean')
result = loss(inputs, targets)
print(result)

结果：
（2）MSELOSS

loss_mse = nn.MSELoss()
result2 = loss_mse(inputs,targets)
print(result2)

结果：
（3）CROSSENTROPYLOSS

x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1, 3))

loss_cross = nn.CrossEntropyLoss()
result3 = loss_cross(x,y)
print(result3)

结果：

与卷积网络结合

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

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


class Peipei(nn.Module):
    def __init__(self) -> None:
        super(Peipei, self).__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, padding=2, stride=1),
            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.model1(x)
        return x


peipei = Peipei()
loss = nn.CrossEntropyLoss()
for data in dataloader:
    imgs, targets = data
    outputs = peipei(imgs)
    result_loss = loss(outputs,targets)
    print(result_loss)
    # 反向传播，计算每个节点的梯度/参数，以便于后续选择合适的优化器
    result_loss.backward()

结果：