pytorch学习笔记（8）--搭建简单的神经网络以及Sequential的使用

1、神经网络图

　　输入图像是3通道的32×32的，先后经过卷积层(5×5的卷积核)、最大池化层(2×2的池化核)、卷积层(5×5的卷积核)、最大池化层(2×2的池化核)、卷积层(5×5的卷积核)、最大池化层(2×2的池化核)、拉直、全连接层的处理，最后输出的大小为10。

　　注：（1）通道变化时通过调整卷积核的个数（即输出通道）来实现的，再nn.conv2d的参数中有out_channel这个参数就是对应输出通道

　　　　（2）32个3*5*5的卷积核，然后input对其一个个卷积得到32个32*32------通道数变不变看用几个卷积核

　　　　（3）最大池化不改变通道channel数

代码输入：

# file     : nn_sequential.py
# time     : 2022/8/2 上午9:11
# function : 实现一个简单的神经网络
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        # stride 默认为1 所以不写也可
        self.conv1 = Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2)
        self.maxpool1 = MaxPool2d(kernel_size=2)
        self.conv2 = Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2)
        self.maxpool2 = MaxPool2d(kernel_size=2)
        self.conv3 = Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2)
        self.maxpool3 = MaxPool2d(kernel_size=2)
        self.flatten = Flatten()
        self.linear1 = Linear(in_features=1024, out_features=64)
        self.linear2 = Linear(in_features=64, out_features=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)
        return x

tudui = Tudui()
# 输出网络的结构情况
print(tudui)

# bitch_size = 64 ，channel通道=3，尺寸32*32
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)  # 输出output尺寸

输出：

Tudui(
  (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)
)
torch.Size([64, 10])

补充说明：

其中Hout=32，Hin（输入的高）=32，dilation[0]=1（默认设置为1），kernel_size[0]=5，将其带入到Hout的公式，

计算过程如下：
32 =((32+2×padding[0]-1×(5-1)-1)/stride[0])+1，简化之后的式子为：
27+2×padding[0]=31×stride[0]，其中stride[0]=1，所以padding[0]=2（注若stride[0]=2则padding[0]很大舍去）
2、Sequential

　　Sequential是一个时序容器。Modules 会以他们传入的顺序被添加到容器中。包含在PyTorch官网中torch.nn模块中的Containers中，在神经网络搭建的过程中如果使用Sequential，代码更简洁

    现以Sequential搭建上述一模一样的神经网络，并借助tensorboard显示计算图的具体信息。代码如下：

# file     : nn_sequential.py
# time     : 2022/8/2 上午9:11
# function : Sequential
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter

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, 64)
        )

    def forward(self, x):
        x = self.model1(x)
        return x

tudui = Tudui()
print(tudui)

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

writer = SummaryWriter("../logs")
writer.add_graph(tudui, input)
writer.close()

输出:

Tudui(
  (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=64, bias=True)
  )
)
torch.Size([64, 64])

双击打开查看具体节点信息：