# Pytorch Practice - LeNet for cifar10

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

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        # input channels: 输入特征矩阵的深度, 例如RGB图像的in_channels = 3
        # output channels: 使用的卷积核的个数 = 输出特征矩阵的深度
        # kernel size: 卷积核的大小
        self.conv1 = nn.Conv2d(3, 16, 5)  
        
        # 特征矩阵的长宽都缩小一半
        self.pool1 = nn.MaxPool2d(2, 2)
        
        
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)pshb
        
        
        self.fc1 = nn.Linear(32*5*5, 120) # 因为conv2卷积后特征矩阵的形状为(32,5,5)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))    # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)            # output(16, 14, 14)
        x = F.relu(self.conv2(x))    # output(32, 10, 10)
        x = self.pool2(x)            # output(32, 5, 5)
        x = x.view(-1, 32*5*5)       # output(32*5*5)
        x = F.relu(self.fc1(x))      # output(120)
        x = F.relu(self.fc2(x))      # output(84)
        x = self.fc3(x)              # output(10)
        return x

**经卷积后的矩阵尺寸大小为**
$$
N=(W-F+2 P) / S+1
$$

- 输入图片大小 W x W
- Filter/kernel大小 F x F
- 步长 S
- padding的像素数P