深度学习基础：9.复现经典网络：LeNet5与AlexNet

import torch
from torch import nn
from torch.nn import functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)  # (H+2p-K)/S + 1
        self.pool1 = nn.AvgPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.pool2 = nn.AvgPool2d(2)
        self.fc1 = nn.Linear(5 * 5 * 16, 120)
        self.fc2 = nn.Linear(120, 84)

    def forward(self, x):
        x = torch.tanh(self.conv1(x))
        x = self.pool1(x)
        x = torch.tanh(self.conv2(x))
        x = self.pool2(x)
        x = x.view(-1, 5 * 5 * 16)  
        x = torch.tanh(self.fc1(x))
        output = F.softmax(self.fc2(x), dim=1)  # (samples, features)

from torchinfo import summary

net = Model()
summary(net, input_size=(10, 1, 32, 32))

class Model(nn.Module):
    def __init__(self):
        super().__init__()

        # 为了处理尺寸较大的原始图片，先使用11x11的卷积核和较大的步长来快速降低特征图的尺寸
        # 同时，使用比较多的通道数，来弥补降低尺寸造成的数据损失
        self.conv1 = nn.Conv2d(3, 96, kernel_size=11, stride=4)
        self.pool1 = nn.MaxPool2d(kernel_size=3, stride=2)  # overlap pooling

        # 已经将特征图尺寸缩小到27x27，计算量可控，可以开始进行特征提取了
        # 卷积核、步长恢复到业界常用的大小，进一步扩大通道来提取数据
        self.conv2 = nn.Conv2d(96, 256, kernel_size=5, padding=2)
        self.pool2 = nn.MaxPool2d(kernel_size=3, stride=2)

        # 疯狂提取特征，连续用多个卷积层
        # kernel 5, padding 2, kernel 3, padding 1 可以维持住特征图的大小
        self.conv3 = nn.Conv2d(256, 384, kernel_size=3, padding=1)
        self.conv4 = nn.Conv2d(384, 384, kernel_size=3, padding=1)
        self.conv5 = nn.Conv2d(384, 256, kernel_size=3, padding=1)
        self.pool3 = nn.MaxPool2d(kernel_size=3, stride=2)

        # 进入全连接层，进行信息汇总
        self.fc1 = nn.Linear(6 * 6 * 256, 4096)  # 上层所有特征图上的所有像素
        self.fc2 = nn.Linear(4096, 4096)
        self.fc3 = nn.Linear(4096, 1000)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = self.pool1(x)

        x = F.relu(self.conv2(x))
        x = self.pool2(x)

        x = F.relu(self.conv3(x))
        x = F.relu(self.conv4(x))
        x = F.relu(self.conv5(x))
        x = self.pool3(x)

        x = x.view(-1, 6 * 6 * 256)  # 将数据拉平

        x = F.dropout(x, p=0.5)
        x = F.relu(F.dropout(self.fc1(x), p=0.5))
        x = F.relu(self.fc2(x))
        output = F.softmax(self.fc3(x), dim=1)

net = Model()
summary(net, input_size=(10, 3, 227, 227))