pytorch学习4

神经网络

nn.Sequential搭建实战

模块将按照它们在构造函数中传递的顺序添加到其中

未使用Sequential

from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear


class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.conv1 = Conv2d(3, 32, 5, padding=2)
        self.maxpool1 = MaxPool2d(2)
        self.conv2 = Conv2d(32, 32, 5, padding=2)
        self.maxpool2 = MaxPool2d(2)
        self.conv3 = Conv2d(32, 64, 5, padding=2)
        self.maxpool3 = MaxPool2d(2)
        self.flatten = Flatten()
        self.linear1 = Linear(1024, 64)
        self.linear2 = Linear(64, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.maxpool1(x)
        x = self.conv2(x)
        x = self.maxpool2(x)
        x = self.conv3(x)
        x = self.maxpool3(x)
        x = self.flatten(x)
        x = self.linear1(x)
        x = self.linear2(x)

test = MyModel()
print(test)

输出

MyModel(
  (conv1): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (flatten): Flatten(start_dim=1, end_dim=-1)
  (linear1): Linear(in_features=1024, out_features=64, bias=True)
  (linear2): Linear(in_features=64, out_features=10, bias=True)
)

测试：

input = torch.ones((64, 3, 32, 32))
output = test(input)
print(output.shape)

输出

torch.Size([64, 10])

使用Sequential

修改自定义MyModel类

class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, 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

输出（和之前一样，代码更简洁）

MyModel(
  (model1): Sequential(
    (0): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (4): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Flatten(start_dim=1, end_dim=-1)
    (7): Linear(in_features=1024, out_features=64, bias=True)
    (8): Linear(in_features=64, out_features=10, bias=True)
  )
)
torch.Size([64, 10])

查看模型示意图（双击可以查看具体模型处理步骤）

writer = SummaryWriter("logs_seq")
writer.add_graph(test, input)
writer.close()

损失函数和反向传播

L1Loss()：计算输入和目标之间的绝对误差，参数reduction有none、mean、sum

import torch
from torch.nn import L1Loss

inputs = torch.tensor([1, 1, 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='none')
result = loss(inputs, targets)
print(result)

输出（none时相当于每个求差值并显示）

tensor([[[[0., 1., 2.]]]])

reduction='mean'：tensor(0.6667)（相当于计算差值和并求平均）

reduction='sum'：tensor(2.)（相当于计算差值和）

MSELoss()：计算均方误差，参数reduction通L1Loss

案例同上

loss = MSELoss(reduction='sum')
result = loss(inputs, targets)
print(result)

输出：tensor(5.)

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

输出：

tensor(1.1019)