小土堆pytorch教程学习笔记P23

P23.损失函数与反向传播

1.损失函数

计算实际输出和目标之间的差距

为我们更新输出提供一定的依据（反向传播）

Pytorch官网 -> Docs -> Pytorch -> Loss Functions

class torch.nn.L1Loss(size_average=None, reduce=None, reduction='mean')

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)

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

# L1Loss = (0 + 0 + 2) / 3 = 0.6667
loss = L1Loss()
result = loss(inputs, targets)

print(result)

tensor(0.6667)

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)

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

# L1Loss = (0 + 0 + 2) / 3 = 0.6667
# reduction = 'sum', L1Loss = 0 + 0 + 2 = 2
loss = L1Loss(reduction='sum')
result = loss(inputs, targets)

print(result)

tensor(2.)

平方差

class torch.nn.MSELoss(size_average=None, reduce=None, reduction='mean')

import torch
from torch.nn import L1Loss
from torch import nn

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))

# L1Loss = (0 + 0 + 2) / 3 = 0.6667
# reduction = 'sum', L1Loss = 0 + 0 + 2 = 2
loss = L1Loss(reduction='sum')
result = loss(inputs, targets)

# MSELoss = (0 + 0 + 2^2) / 3 = 1.3333
loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets)

print(result)
print(result_mse)

tensor(2.)
tensor(1.3333)

交叉商

class torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=- 100, reduce=None, reduction='mean', label_smoothing=0.0)

It is useful when training a classification problem with C classes.

The input is expected to contain raw, unnormalized scores for each class.

import torch
from torch.nn import L1Loss
from torch import nn

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))

# L1Loss = (0 + 0 + 2) / 3 = 0.6667
# reduction = 'sum', L1Loss = 0 + 0 + 2 = 2
loss = L1Loss(reduction='sum')
result = loss(inputs, targets)

# MSELoss = (0 + 0 + 2^2) / 3 = 1.3333
loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets)

print(result)
print(result_mse)

x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss() # ln not log
result_cross = loss_cross(x, y)
print(result_cross)

 tensor(2.)
tensor(1.3333)
tensor(1.1019)

 loss在神经网络中的应用

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

dataset = torchvision.datasets.CIFAR10(root="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),
            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()
tudui = Tudui()
for data in dataloader:
    imgs, targets = data
    outputs = tudui(imgs)
    result_loss = loss(outputs, targets)
    print(result_loss)

Files already downloaded and verified
tensor(2.2012, grad_fn=<NllLossBackward>)
tensor(2.4067, grad_fn=<NllLossBackward>)
tensor(2.3914, grad_fn=<NllLossBackward>)

...

tensor(2.4390, grad_fn=<NllLossBackward>)
tensor(2.2048, grad_fn=<NllLossBackward>)

梯度下降

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

dataset = torchvision.datasets.CIFAR10(root="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),
            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()
tudui = Tudui()
for data in dataloader:
    imgs, targets = data
    outputs = tudui(imgs)
    result_loss = loss(outputs, targets)
    result_loss.backward()
    print("ok")