pytorch复现3_GoogLenet-编程知识

背景：
GoogLeNeta是2014年提出的一种全新的深度学习结构，在这之前的AlexNet、VGG等结构都是通过增大网络的深度(层数)来获得更好的训练效果，但层数的增加会带来很多负作用，比如overfit、梯度消失、梯度爆炸等。GoogLeNet通过引入inception从另一种角度来提升训练结果:能更高效的利用计算资源，在相同的计算量下能提取到更多的特征，从而提升训练结果。
因此GoogLeNet在专注于加深网络结构的同时，引入了新的基本结构——Inception模块，以增加网络的宽度。

网络结构图：
在这里插入图片描述
1、Inception模块
Inception就是把多个卷积或池化操作，放在一起组装成一个网络模块

实际中需要什么样的Inception
我们在上面提供了一种Inception的结构，但是这个结构存在很多问题，是不能够直接使用的。首要问题就是参数太多，导致特征图厚度太大。为了解决这个问题，作者在其中加入了1X1的卷积核，改进后的Inception结构如下图：
在这里插入图片描述
代码：
定义BasicConv2d

class BasicConv2d(nn.Module):def __init__(self, in_channels, out_channels, **kwargs):super(BasicConv2d, self).__init__()self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)self.relu = nn.ReLU(inplace=True)def forward(self, x):x = self.conv(x)x = self.relu(x)return x

定义Inception

class Inception(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):super(Inception, self).__init__()self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch3x3red, kernel_size=1),BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1)   # 保证输出大小等于输入大小)self.branch3 = nn.Sequential(BasicConv2d(in_channels, ch5x5red, kernel_size=1),BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2)   # 保证输出大小等于输入大小)self.branch4 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=1, padding=1),BasicConv2d(in_channels, pool_proj, kernel_size=1))

定义分类器

class InceptionAux(nn.Module):def __init__(self, in_channels, num_classes):super(InceptionAux, self).__init__()self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)self.conv = BasicConv2d(in_channels, 128, kernel_size=1)  # output[batch, 128, 4, 4]self.fc1 = nn.Linear(2048, 1024)self.fc2 = nn.Linear(1024, num_classes)def forward(self, x):# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14x = self.averagePool(x)# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4x = self.conv(x)# N x 128 x 4 x 4x = torch.flatten(x, 1)x = F.dropout(x, 0.5, training=self.training)# N x 2048x = F.relu(self.fc1(x), inplace=True)x = F.dropout(x, 0.5, training=self.training)# N x 1024x = self.fc2(x)# N x num_classesreturn x

model完整代码：

import torch.nn as nn
import torch
import torch.nn.functional as Fclass GoogLeNet(nn.Module):def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):super(GoogLeNet, self).__init__()self.aux_logits = aux_logitsself.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.conv2 = BasicConv2d(64, 64, kernel_size=1)self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)if self.aux_logits:self.aux1 = InceptionAux(512, num_classes)self.aux2 = InceptionAux(528, num_classes)self.avgpool = nn.AdaptiveAvgPool2d((1, 1))self.dropout = nn.Dropout(0.4)self.fc = nn.Linear(1024, num_classes)if init_weights:self._initialize_weights()def forward(self, x):# N x 3 x 224 x 224x = self.conv1(x)# N x 64 x 112 x 112x = self.maxpool1(x)# N x 64 x 56 x 56x = self.conv2(x)# N x 64 x 56 x 56x = self.conv3(x)# N x 192 x 56 x 56x = self.maxpool2(x)# N x 192 x 28 x 28x = self.inception3a(x)# N x 256 x 28 x 28x = self.inception3b(x)# N x 480 x 28 x 28x = self.maxpool3(x)# N x 480 x 14 x 14x = self.inception4a(x)# N x 512 x 14 x 14if self.training and self.aux_logits:    # eval model lose this layeraux1 = self.aux1(x)x = self.inception4b(x)# N x 512 x 14 x 14x = self.inception4c(x)# N x 512 x 14 x 14x = self.inception4d(x)# N x 528 x 14 x 14if self.training and self.aux_logits:    # eval model lose this layeraux2 = self.aux2(x)x = self.inception4e(x)# N x 832 x 14 x 14x = self.maxpool4(x)# N x 832 x 7 x 7x = self.inception5a(x)# N x 832 x 7 x 7x = self.inception5b(x)# N x 1024 x 7 x 7x = self.avgpool(x)# N x 1024 x 1 x 1x = torch.flatten(x, 1)# N x 1024x = self.dropout(x)x = self.fc(x)# N x 1000 (num_classes)if self.training and self.aux_logits:   # eval model lose this layerreturn x, aux2, aux1return xdef _initialize_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d):nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')if m.bias is not None:nn.init.constant_(m.bias, 0)elif isinstance(m, nn.Linear):nn.init.normal_(m.weight, 0, 0.01)nn.init.constant_(m.bias, 0)class Inception(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):super(Inception, self).__init__()self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch3x3red, kernel_size=1),BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1)   # 保证输出大小等于输入大小)self.branch3 = nn.Sequential(BasicConv2d(in_channels, ch5x5red, kernel_size=1),BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2)   # 保证输出大小等于输入大小)self.branch4 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=1, padding=1),BasicConv2d(in_channels, pool_proj, kernel_size=1))def forward(self, x):branch1 = self.branch1(x)branch2 = self.branch2(x)branch3 = self.branch3(x)branch4 = self.branch4(x)outputs = [branch1, branch2, branch3, branch4]return torch.cat(outputs, 1)class InceptionAux(nn.Module):def __init__(self, in_channels, num_classes):super(InceptionAux, self).__init__()self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)self.conv = BasicConv2d(in_channels, 128, kernel_size=1)  # output[batch, 128, 4, 4]self.fc1 = nn.Linear(2048, 1024)self.fc2 = nn.Linear(1024, num_classes)def forward(self, x):# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14x = self.averagePool(x)# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4x = self.conv(x)# N x 128 x 4 x 4x = torch.flatten(x, 1)x = F.dropout(x, 0.5, training=self.training)# N x 2048x = F.relu(self.fc1(x), inplace=True)x = F.dropout(x, 0.5, training=self.training)# N x 1024x = self.fc2(x)# N x num_classesreturn xclass BasicConv2d(nn.Module):def __init__(self, in_channels, out_channels, **kwargs):super(BasicConv2d, self).__init__()self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)self.relu = nn.ReLU(inplace=True)def forward(self, x):x = self.conv(x)x = self.relu(x)return x