损失函数与反向传播

损失函数

1.计算实际输出与目标之间的差距

2.为更新输出提供一定的依据（反向传播）--grad

损失函数（L1Loss、MSELoss、CrossEntropyLoss）

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(reduction="sum")
result = loss(inputs, targets)
# 平方差
loss_mse = MSELoss()
result_mse = loss_mse(inputs, targets)
# 交叉熵
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)
print(result_mse)
print(result_cross)

----

lossnetwork

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


dataset = torchvision.datasets.CIFAR10("./dataset1", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset,batch_size=64)

class Test(nn.Module):
    def __init__(self):
        super().__init__()
        self.model1 = Sequential(
            Conv2d(3, 32, 5, 1, 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.model1(x)
        return x

loss = nn.CrossEntropyLoss()

test = Test()
for data in dataloader:
    imgs, targets = data
    outputs = test(imgs)
    result = loss(outputs,targets)
    result.backward()
    print(result)