【打好基础之深度学习】Task 2：复现LeNet5

LeNet5学习（2024.3.4）

代码复现 

1.导入库

# 导入torch包
import torch
import torch.nn as nn
import torch.nn.functional as F

2.构建网络，利用nn.Model继承搭建LenNet网络

# 构建网络，继承nn.Module
class LeNet(nn.Module):
    # 初始化函数
    def __init__(self,):
        # 多继承，把Model里所有的东西继承过来，以供LeNet使用
        super(LeNet, self).__init__()
        
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5)
        self.conv2 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
        
        self.fc1 = nn.Linear(16*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    
    # 前向传播函数
    def forward(self, x):
        #处理的是tensor数据[batch, channel, H, W]
        x = self.conv1(x)
        x = F.relu(x)
        x = F.max_pool2d(x,(2,2))
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x,(2,2))
        
        # 需要把tensor拉平，即16*5*5 -> 400*1，行数和batch生成因此用-1保持不变，[1:]将batch去掉，后面的channel和H和W拉平
        x = x.view(-1,x.size()[1:], num1())
        
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        
        return x

3.测试打印输出

model = LeNet()
print(model)