GoogLeNet详解

最新推荐文章于 2026-04-07 21:01:14 发布

原创最新推荐文章于 2026-04-07 21:01:14 发布 · 2.1k 阅读

54 ·

本内容遵循CC 4.0 BY-SA版权协议

GEO检测

标签

#python #深度学习 #卷积神经网络 #计算机视觉 #googlenet

网络背景

GoogLeNet是由Google研究人员开发的一种深度卷积神经网络架构，其以6.7%的Top-5错误率赢得ILSVRC 2014冠军（第二名VGG为7.3%），证明了其高效性和性能优势。其中大写的L是为了致敬LeNet。

网络创新

1.引入了Inception结构(融合不同尺度的特征信息)

并行多分支结构：Inception模块同时使用1×1、3×3、5×5卷积核和3×3最大池化，在不同尺度上提取特征，再拼接（Concat）输出。

解决传统CNN的局限性：传统网络需手动选择卷积核大小（如VGG只用3×3），而Inception通过自动融合多尺度信息，增强特征表达能力。

适应不同视觉模式：大卷积核捕捉全局特征，小卷积核提取局部细节，池化保留平移不变性。

突破了当时“堆叠相同卷积层”的设计范式（如AlexNet、VGG），成为后续多尺度特征提取的标杆。

2.使用1x1的卷积核进行降维以及映射处理

降维（减少计算量）：在3×3/5×5卷积前用1×1卷积压缩通道数（如输入256通道→1×1卷积输出64通道→再3×3卷积），大幅减少参数量。

非线性增强：1×1卷积后接ReLU，引入额外非线性变换，提升模型表达能力。

计算效率提升：例如，Inception模块参数量比直接使用大卷积核减少约90%。1×1卷积被称为“网络中的网络”（NiN）思想的应用，实现了跨通道信息融合。影响了后续所有轻量化设计（如MobileNet的深度可分离卷积）。

3.添加两个辅助分类器帮助训练

中间层监督：在网络中部（Inception 4a和4d输出处）添加两个辅助分类器，计算损失并反向传播。

缓解梯度消失：深层网络的梯度通过辅助分类器强化，避免训练初期梯度信号过弱。

正则化作用：辅助分类器在训练阶段充当“隐式正则项”，防止过拟合。

解决了深度网络（22层）的梯度传播难题，为更深的模型（如ResNet）铺路。测试阶段移除辅助分类器，不影响推理效率，属于训练技巧的创新。

4.使用平均池化层(大大减少模型参数)

参数大幅减少：传统网络（如AlexNet）全连接层占参数量90%以上，GoogLeNet直接用全局平均池化将最后一层特征图转换为类别概率。

防止过拟合：全连接层易过拟合，GAP通过空间维度降维保留关键特征。

模型参数量从AlexNet的6000万降至GoogLeNet的500万，效率提升显著。成为后续网络的标配（如ResNet、SqueezeNet均采用GAP）。

网络结构

输入 (224×224×3)
↓
[7×7 conv, 64, stride=2] → ReLU → [3×3 maxpool, stride=2] → 56×56×64
↓
[Inception 3a] → [Inception 3b] → 28×28×256
↓
[Inception 4a] → [辅助分类器1] → ... → [Inception 4e] → 14×14×512
↓
[Inception 5a] → [Inception 5b] → 7×7×1024
↓
[全局平均池化] → 1×1×1024 → Dropout → 1000-way Softmax

网络代码

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


class GoogLeNet(nn.Module):
    def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
        super(GoogLeNet, self).__init__()
        self.aux_logits = aux_logits

        self.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 224
        x = self.conv1(x)
        # N x 64 x 112 x 112
        x = self.maxpool1(x)
        # N x 64 x 56 x 56
        x = self.conv2(x)
        # N x 64 x 56 x 56
        x = self.conv3(x)
        # N x 192 x 56 x 56
        x = self.maxpool2(x)

        # N x 192 x 28 x 28
        x = self.inception3a(x)
        # N x 256 x 28 x 28
        x = self.inception3b(x)
        # N x 480 x 28 x 28
        x = self.maxpool3(x)
        # N x 480 x 14 x 14
        x = self.inception4a(x)
        # N x 512 x 14 x 14
        if self.training and self.aux_logits:    # eval model lose this layer
            aux1 = self.aux1(x)

        x = self.inception4b(x)
        # N x 512 x 14 x 14
        x = self.inception4c(x)
        # N x 512 x 14 x 14
        x = self.inception4d(x)
        # N x 528 x 14 x 14
        if self.training and self.aux_logits:    # eval model lose this layer
            aux2 = self.aux2(x)

        x = self.inception4e(x)
        # N x 832 x 14 x 14
        x = self.maxpool4(x)
        # N x 832 x 7 x 7
        x = self.inception5a(x)
        # N x 832 x 7 x 7
        x = self.inception5b(x)
        # N x 1024 x 7 x 7

        x = self.avgpool(x)
        # N x 1024 x 1 x 1
        x = torch.flatten(x, 1)
        # N x 1024
        x = self.dropout(x)
        x = self.fc(x)
        # N x 1000 (num_classes)
        if self.training and self.aux_logits:   # eval model lose this layer
            return x, aux2, aux1
        return x

    def _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),
            # 在官方的实现中，其实是3x3的kernel并不是5x5，这里我也懒得改了，具体可以参考下面的issue
            # Please see https://github.com/pytorch/vision/issues/906 for details.
            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 14
        x = self.averagePool(x)
        # aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
        x = self.conv(x)
        # N x 128 x 4 x 4
        x = torch.flatten(x, 1)
        x = F.dropout(x, 0.5, training=self.training)
        # N x 2048
        x = F.relu(self.fc1(x), inplace=True)
        x = F.dropout(x, 0.5, training=self.training)
        # N x 1024
        x = self.fc2(x)
        # N x num_classes
        return x


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