卷积神经网络（一） Lenet Pytorch实现

Lenet 这个网络是最基础的卷积神经网络，学过一段时间的pytorch看着结构图应该就可以搭建出来了

1. lenet 网络结构图

2. lenet模型 代码实现

import torch.nn as nn
import torch.nn.functional as F
class LeNet(nn.Module):
    #定义conv pool  fc
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 5)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(32*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    #前向传播
    def forward(self, x):
        x = F.relu(self.conv1(x))
        #(32-5)/1+1=28
        # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)
        # output(16, 14, 14)
        x = F.relu(self.conv2(x))
        #(14-5)+1=10
        # 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

3.查看模型输出：

这两行代码比较通用的，查看模型结构的时候直接写这两行代码接可以了

model=LeNet()
print(model)

4. 模型输出：

"""
LeNet(
  (conv1): Conv2d(3, 16, kernel_size=(5, 5), stride=(1, 1))
  (pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1))
  (pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (fc1): Linear(in_features=800, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)
"""

参考：
pytorh官方demo
论文地址：http://www.dengfanxin.cn/wp-content/uploads/2016/03/1998Lecun.pdf