经典的卷积神经网络实现(二)---VGGNet、GoogLeNet

一、VGGNet

1. 使用了更深层次的网络，和33的滤波器、22的池化层。
   1. 使用很小的滤波器堆叠，可以做到一个大滤波器同样的效果。并且可以减少参数。
2. 网络结构图
   1. 是2个卷积层与1个pool层作为一个整体。
   2. 在全连接层后，使用Softmax作为激活函数。

二、GoogLeNet

1. GoogLeNet采用了比VGGNet更深的网络结构，一共有22层，但是参数比AlexNet少。没有使用全连接层
2. GooLeNet使用了了Inception作为网络模块
   1. 在以往的网络中，我们一层只使用一种操作，而且卷积核大小固定。
   2. 在GooLeNet中，我们使用Inception来使得网络可以自己进行选择，能更好的调节。
3. Inception的结构
   
   1. 维度减小的Inception模块，引入了1×1的卷积层，来降低输入层的维度，从而减小网络参数。
4. 整体网络结构
   
5. 代码实现

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

class BasicConv2d(nn.Module):
    def __init__(self,in_channels,out_channels,**kwargs):
        super(BasicConv2d, self).__init__()

        self.conv = nn.Conv2d(in_channels,out_channels,bias=False,**kwargs)
        self.bn = nn.BatchNorm2d(out_channels,eps=0.001)

    def forward(self,x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x,inplace=True)
    
class Inception(nn.Module):
    def __init__(self,in_channels,pool_features):
        super(Inception, self).__init__()
        self.branch1x1 = BasicConv2d(in_channels,64,kernel_size=1)
        
        self.branch5x5_1 = BasicConv2d(in_channels,48,kernel_size=1)
        self.branch5x5_2 = BasicConv2d(48,64, kernel_size=5,padding=2)

        self.branch3x3_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)
        
        self.branch_pool = BasicConv2d(
            in_channels,pool_features,kernel_size=1
        )
    def forward(self,x):
        branch1x1 = self.branch1x1(x)
        
        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        branch3x3 = self.branch3x3_3(branch3x3)
        
        branch_pool = F.avg_pool2d(x,kernel_size=3,stride=1,padding=1)
        branch_pool = self.branch_pool(branch_pool)
        
        outputs = [branch1x1,branch3x3,branch5x5,branch_pool]
        return outputs