Sequential的使用

Sequential的作用：代码更加简洁。

1.不使用Sequential

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

# 搭建网络
from torch.utils.tensorboard import SummaryWriter


class net(nn.Module):
    def __init__(self):
        super(net, self).__init__()
        # 1.卷积层
        self.conv1 = Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2)
        # 池化部分
        self.maxpool1 = MaxPool2d(kernel_size=2)
        # 卷积
        self.conv2 = Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2)
        # 池化部分
        self.maxpool2 = MaxPool2d(kernel_size=2)
        # 卷积
        self.conv3 = Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2)
        # 池化
        self.maxpool3 = MaxPool2d(kernel_size=2)
        # 线性层
        self.flatten1 = Flatten()
        self.Linear1 = Linear(in_features=1024, out_features=64)
        self.Linear2 = Linear(in_features=64, out_features=10)

    def forward(self, x):
        # 1.调用
        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.flatten1(x)
        x = self.Linear1(x)
        x = self.Linear2(x)
        return x


wang = net()
# 全是1，batch_size=64 , 3通道 32*32
input = torch.ones((64, 3, 32, 32))
output = wang(input)
print(wang)
print(output.shape)
writer = SummaryWriter("r10")
writer.add_graph(wang, input)
writer.close()

2.使用Sequential

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


# 搭建网络
from torch.utils.tensorboard import SummaryWriter


class net(nn.Module):
    def __init__(self):
        super(net, self).__init__()
        # 2.Sequential的使用
        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(in_features=1024, out_features=64),
            Linear(in_features=64, out_features=10)
        )

    def forward(self, x):
        # 2.调用 代码简洁
        x = self.model1(x)
        return x


wang = net()
# 全是1，batch_size=64 , 3通道 32*32
input = torch.ones((64, 3, 32, 32))
output = wang(input)
print(wang)
print(output.shape)

writer = SummaryWriter("r10")
writer.add_graph(wang, input)
writer.close()