J8 inceptionv1

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊

前言

卷积神经网络大家族中有很多经典的网络，前面已经学习resnet,densenet相关网络，今天学习一种更久远的一种网络GoogLenet

网络结构

其核心模块为inception块，这些模块由多层不同滤波器尺寸（1x1、3x3和5x5卷积）和池化操作组成。通过并行使用不同尺寸的滤波器，网络可以在多个尺度上捕获信息，从而学习更复杂的特征。

此外，为了防止由于网络深度和宽度的增加而导致参数数量爆炸，Inception v1在3x3和5x5卷积之前使用了1x1卷积等降维技术。这有助于降低计算成本和过拟合，同时保持甚至改善网络的表示能力。其结构如下图所示
在这里插入图片描述

在这里插入图片描述
同时1x1卷积的使用也影响着后续网络结构的设计如resnet继续将1x1卷积的使用发扬光大。

模型代码

class inception_block(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):super().__init__()# 1x1 分支self.branch1 = nn.Sequential(nn.Conv2d(in_channels, ch1x1, kernel_size=1),nn.BatchNorm2d(ch1x1),nn.ReLU(inplace=True))# 1x1 -> 3x3 分支self.branch2 = nn.Sequential(nn.Conv2d(in_channels, ch3x3red, kernel_size=1),nn.BatchNorm2d(ch3x3red),nn.ReLU(inplace=True),nn.Conv2d(ch3x3red, ch3x3, kernel_size=3, padding=1),nn.BatchNorm2d(ch3x3),nn.ReLU(inplace=True))# 1x1 -> 5x5 分支self.branch3 = nn.Sequential(nn.Conv2d(in_channels, ch5x5red, kernel_size=1),nn.BatchNorm2d(ch5x5red),nn.ReLU(inplace=True),nn.Conv2d(ch5x5red, ch5x5, kernel_size=5, padding=2),nn.BatchNorm2d(ch5x5),nn.ReLU(inplace=True))# 3x3 -> 1x3 分支self.branch4 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=1, padding=1),nn.Conv2d(in_channels, pool_proj, kernel_size=1),nn.BatchNorm2d(pool_proj),nn.ReLU(inplace=True))def forward(self, x):branch1_output = self.branch1(x)branch2_output = self.branch2(x)branch3_output = self.branch3(x)branch4_output = self.branch4(x)outputs = [branch1_output, branch2_output, branch3_output, branch4_output]return torch.cat(outputs, 1)


class InceptionV1(nn.Module):def __init__(self, num_classes=1000):super().__init__()self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.conv2 = nn.Conv2d(64, 64, kernel_size=1, stride=1, padding=0)self.conv3 = nn.Conv2d(64, 192, kernel_size=3, stride=1, padding=1)self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32)self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64)self.maxpool3 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64)self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64)self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64)self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64)self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128)self.maxpool4 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128)self.inception5b = nn.Sequential(inception_block(832, 384, 192, 384, 48, 128, 128),nn.AvgPool2d(kernel_size=7, stride=1, padding=0),nn.Dropout(0.4))# 全连接层self.classifier = nn.Sequential(nn.Linear(in_features=1024, out_features=1024),nn.ReLU(),nn.Linear(in_features=1024, out_features=num_classes),nn.Softmax(dim=1))def forward(self, x):x = self.conv1(x)x = F.relu(x)x = self.maxpool1(x)x = self.conv2(x)x = F.relu(x)x = self.conv3(x)x = F.relu(x)x = self.maxpool2(x)x = self.inception3a(x)x = self.inception3b(x)x = self.maxpool3(x)x = self.inception4a(x)x = self.inception4b(x)x = self.inception4c(x)x = self.inception4d(x)x = self.inception4e(x)x = self.maxpool4(x)x = self.inception5a(x)x = self.inception5b(x)x = torch.flatten(x, start_dim=1)x = self.classifier(x)return xmodel = InceptionV1().to(device)