【图像分类】【深度学习】【Pytorch版本】 GoogLeNet(InceptionV3)模型算法详解

文章目录

【图像分类】【深度学习】【Pytorch版本】 GoogLeNet(InceptionV3)模型算法详解
前言
GoogLeNet(InceptionV3)讲解
- Factorized Convolutions卷积分解
- InceptionV3结构Ⅰ
- InceptionV3结构Ⅱ
- InceptionV3结构Ⅲ
- InceptionV3特殊结构
- 辅助分类器
- GoogLeNet(InceptionV3)模型结构
GoogLeNet(InceptionV3) Pytorch代码
完整代码
总结

前言

GoogLeNet(InceptionV3)是由谷歌的Szegedy, Christian等人在《Rethinking the Inception Architecture for Computer Vision【CVPR-2016】》【论文地址】一文中提出的带有Factorized Convolutions(分解卷积)的改进模型，即在InceptionV2的基础上将标准的卷积操作分解为1xN卷积和Nx1卷积两个步骤，这种分解模式可以显著降低参数量和计算量，同时在一定程度上保持了特征提取的能力。

GoogLeNet(InceptionV3)讲解

GoogLeNet团队在给出了一些通用的网络设计准则，以期望在不提高网络参数量的前提下提升网络的表达能力：

避免特征图(feature map)表达瓶颈：从理论上讲，尺寸(seize)才包含了相关结构等重要因素，维度(channel)仅仅提供了信息内容的粗略估计，因此特征图的尺寸应该从输入到输出慢慢减小，避免使用极端压缩。
更高的维度特征图更容易获得网络的局部表达：在卷积网络结构中，增加非线性能够使得更多的特征解耦合，相互独立的特征更多，输入的信息就被分解的更彻底，分解的子特征间相关性低，子特征内部相关性高，因此高维特征带有更多的判别信息，会更容易收敛。
在低维特征上的空间聚合(池化)不会(极少)损失太多信息：相邻的位置的信息具有强相关性，即使进行了降维，也不会带来太多的损失，并且维数的降低，也能够加速网络学习。
平衡网络的宽度与深度：最优的网络应该在每一层网络宽度和网络深度之间有个很好的平衡。

Factorized Convolutions卷积分解

分解卷积的主要目的是为了减少网络中的参数，主要方法有：大卷积分解成小卷积，小卷积分解为非对称卷积。

大卷积分解成小卷积： 大尺度的卷积可以获得更大的感受野，但是也带来参数量的增加，VggNet表明使用大于大卷积核(大于3×3)完全可以由一系列的3×3卷积核来替代，即使用小卷积核串联来替代大卷积核。因此在InceptionV2中已经通过堆叠两层3×3的卷积核的方式替代一层5×5的卷积核，这样的连接方式在保持感受野范围的同时又减少了参数量，不会造成表达缺失，降低网络性能，并且可以避免表达瓶颈，加深非线性表达能力。
小卷积分解为非对称卷积： 3x3卷积是能够完全获取上下文信息(上、下、左、右)的最小卷积核，是否能把小卷积核分解的更小呢？在InceptionV3中，GoogLeNet团队考虑了非对称卷积分解，引入了将一个较大的二维卷积拆成两个较小的一维卷积的做法，即任意n×n的卷积都可以通过1×n卷积后接n×1卷积来替代，非对称卷积能够降低运算量，并且不会降低模型的整体表征能力。

InceptionV3结构Ⅰ

与InceptionV2结构相同，即5x5卷积使用两个3x3的卷积代替，目的是减少参数量和计算量——大卷积分解成小卷积。

InceptionV3结构Ⅱ

将InceptionV2结构中3x3的卷积使用1x3和3x1的卷积组合来代替，5x5的卷积使用俩个1x3和3x1的卷积组合来代替，目的也是减少参数量和计算量———小卷积分解为非对称卷积。

采用这种分解在模型的早期网络层上不能有效发挥作用，但是在中等特征图大小(m×m，其中m在12和20之间的范围)上取得了非常好的效果。

使用3x3的卷积代替5x5的卷积，输出512通道特征图，输出128通道特征图：
参数量：512×3×3×128+128×3×3×128=737280
计算量：512×3×3×128×W×H+128×3×3×128×W×H=737280×W×H
W×H是特征图尺寸，假设卷积层的输入输出特征图尺寸保持一致
使用1x3和3x1的卷积组合代替5x5的卷积，输出512通道特征图，输出128通道特征图：
参数量：512×1×3×128+128×3×1×128+128×1×3×128+128×3×1×128=344064
计算量：512×1×3×128×W×H+128×3×1×128×W×H+128×1×3×128×W×H+128×3×1×128×W×H=344064×W×H

InceptionV3结构Ⅲ

该结构主要用于扩充通道数，网络变得更宽，该结构被放置在所以放在GoogLeNet(InceptionV3)的最后。

InceptionV3特殊结构

在传统方法中，卷积神经网络使用池化等操作以减小特征图大小。先池化再进行卷积升维会导致瓶颈结构，过程中将丢失很多信息，对于后面输出的特征图提取的图像中的特征将会更少；先卷积升维再进行池化，计算量将增加三倍，增加了计算成本：

GoogLeNet(InceptionV3)的改进方案采用一种并行的降维结构，在扩充通道数的同时下采样减小特征图大小，既减少计算量保证了计算效率又避免了瓶颈结构。
替换GoogLeNet(InceptionV1)模型中的MaxPool。

辅助分类器

GoogLeNet(InceptionV1)引入了辅助分类器的概念，最初的动机是为了将有用的梯度反向传递到网络低层，解决梯度消失的问题，提高网络的收敛能力，保证网络训练正常进行。
GoogLeNet(InceptionV3)的实验则发现1.辅助分类器并不能保证收敛更快，并且有无辅助分类器，训练过程基本保持一致，只有在训练的最后阶段，有辅助分类器略微高于无辅助分类器的网络；2.位于网络低层的辅助分类器对最终结果没有影响；3.辅助分类器充当了正则化器，如果辅助分类器带有BN或Dropout层那么主分类器性能会更好。

GoogLeNet(InceptionV3)中的辅助分类器同样不直接用于最终的预测结果。在训练过程中，辅助分类器的损失函数会被加权，并与主分类器的损失函数相结合。在推理阶段，辅助分类器被舍弃，仅使用主分类器进行预测。

GoogLeNet(InceptionV3)模型结构

下图是原论文给出的关于 GoogLeNet(InceptionV3)模型结构的详细示意图：

GoogLeNet(InceptionV3)在图像分类中分为两部分：backbone部分： 主要由InceptionV3模块、卷积层和池化层(汇聚层)组成，分类器部分：由主分类器和辅助分类器组成。
博主仿造GoogLeNet(InceptionV1)的结构绘制了以下GoogLeNet(InceptionV3)的结构。

GoogLeNet(InceptionV3) Pytorch代码

卷积层组： 卷积层+BN层+激活函数

# 卷积组: Conv2d+BN+ReLU
class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
        self.bn = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.relu(x)
        return x

InceptionV3模块Ⅰ：卷积层组+池化层

就是原始的InceptionV2模块

# InceptionV3A:BasicConv2d+MaxPool2d
class InceptionV3A(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3A, self).__init__()
        # 1×1卷积
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        # 1×1卷积+3×3卷积
        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
        )
        # 1×1卷积++3×3卷积+3×3卷积
        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=3, padding=1),
            BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=3, padding=1)         # 保证输出大小等于输入大小
        )
        # 3×3池化+1×1卷积
        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)
        # 拼接
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)

InceptionV3模块Ⅱ：卷积层组+池化层

# InceptionV3B:BasicConv2d+MaxPool2d
class InceptionV3B(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3B, self).__init__()
        # 1×1卷积
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        # 1×1卷积+1×3卷积+3×1卷积
        self.branch2 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3red, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=[1, 3], padding=[0, 1]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[3, 1], padding=[1, 0])   # 保证输出大小等于输入大小
        )
        # 1×1卷积+1×3卷积+3×1卷积+1×3卷积+3×1卷积
        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=[1, 3], padding=[0, 1]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[3, 1], padding=[1, 0]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[1, 3], padding=[0, 1]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[3, 1], padding=[1, 0])  # 保证输出大小等于输入大小
        )
        # 3×3池化+1×1卷积
        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)
        # 拼接
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)

InceptionV3模块Ⅲ：卷积层组+池化层

# InceptionV3C:BasicConv2d+MaxPool2d
class InceptionV3C(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3C, self).__init__()
        # 1×1卷积
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        # 1×1卷积+1×3卷积+3×1卷积
        self.branch2_0 = BasicConv2d(in_channels, ch3x3red, kernel_size=1)
        self.branch2_1 = BasicConv2d(ch3x3red, ch3x3, kernel_size=[1, 3], padding=[0, 1])
        self.branch2_2 = BasicConv2d(ch3x3red, ch3x3, kernel_size=[3, 1], padding=[1, 0])

        # 1×1卷积+3×3卷积+1×3卷积+3×1卷积
        self.branch3_0 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=3, padding=1),
        )
        self.branch3_1 = BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=[1, 3], padding=[0, 1])
        self.branch3_2 = BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=[3, 1], padding=[1, 0])

        # 3×3池化+1×1卷积
        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_0 = self.branch2_0(x)
        branch2 = torch.cat([self.branch2_1(branch2_0), self.branch2_2(branch2_0)], dim=1)
        branch3_0 = self.branch3_0(x)
        branch3 = torch.cat([self.branch3_1(branch3_0), self.branch3_2(branch3_0)], dim=1)
        branch4 = self.branch4(x)
        # 拼接
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)

InceptionV3特殊模块(三分支)： 卷积层组+池化层

# InceptionV3D:BasicConv2d+MaxPool2d
class InceptionV3D(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3D, self).__init__()
        # ch1x1:没有1×1卷积
        # 1×1卷积+3×3卷积,步长为2
        self.branch1 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3red, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=3, stride=2)   # 保证输出大小等于输入大小
        )
        # 1×1卷积+3×3卷积+3×3卷积,步长为2
        self.branch2 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=3, padding=1),   # 保证输出大小等于输入大小
            BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=3, stride=2)         # 保证输出大小等于输入大小
        )
        # 3×3池化,步长为2
        self.branch3 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=2))
        # pool_proj:池化层后不再接卷积层

    def forward(self, x):
        branch1 = self.branch1(x)
        branch2 = self.branch2(x)
        branch3 = self.branch3(x)
        # 拼接
        outputs = [branch1,branch2, branch3]
        return torch.cat(outputs, 1)

辅助分类器： 池化层+卷积层组+全连接层+dropout

# 辅助分类器:AvgPool2d+BasicConv2d+Linear+dropout
class InceptionAux(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(InceptionAux, self).__init__()

        self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
        self.conv1 = BasicConv2d(in_channels=in_channels, out_channels=128, kernel_size=1)
        self.conv2 = BasicConv2d(in_channels=128, out_channels=768, kernel_size=5, stride=1)
        self.dropout = nn.Dropout(p=0.7)
        self.linear = nn.Linear(in_features=768, out_features=out_channels)
    def forward(self, x):
        # N x 768 x 17 x 17
        x = self.averagePool(x)
        # N x 768 x 5 x 5
        x = self.conv1(x)
        # N x 128 x 5 x 5
        x = self.conv2(x)
        # N x 768 x 1 x 1
        x = x.view(x.size(0), -1)
        # N x 768
        out = self.linear(self.dropout(x))
        # N x num_classes
        return out

完整代码

GoogLeNet(InceptionV3)的输入图像尺寸是299×299

import torch.nn as nn
import torch
from torchsummary import summary

class GoogLeNetV3(nn.Module):
    def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
        super(GoogLeNetV3, self).__init__()
        self.aux_logits = aux_logits
        # 3个3×3卷积替代7×7卷积
        self.conv1_1 = BasicConv2d(3, 32, kernel_size=3, stride=2)
        self.conv1_2 = BasicConv2d(32, 32, kernel_size=3, stride=1)
        self.conv1_3 = BasicConv2d(32, 64, kernel_size=3, stride=1, padding=1)
        # 池化层
        self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

        self.conv2 = BasicConv2d(64, 80, kernel_size=3)
        self.conv3 = BasicConv2d(80, 192, kernel_size=3, stride=2)
        self.conv4 = BasicConv2d(192, 192, kernel_size=3, padding=1)

        self.inception3a = InceptionV3A(192, 64, 48, 64, 64, 96, 32)
        self.inception3b = InceptionV3A(256, 64, 48, 64, 64, 96, 64)
        self.inception3c = InceptionV3A(288, 64, 48, 64, 64, 96, 64)

        self.inception4a = InceptionV3D(288, 0, 384, 384, 64, 96, 0)
        self.inception4b = InceptionV3B(768, 192, 128, 192, 128, 192, 192)
        self.inception4c = InceptionV3B(768, 192, 160, 192, 160, 192, 192)
        self.inception4d = InceptionV3B(768, 192, 160, 192, 160, 192, 192)
        self.inception4e = InceptionV3D(768, 0, 384, 384, 64, 128, 0)

        if self.aux_logits == True:
            self.aux = InceptionAux(in_channels=768, out_channels=num_classes)

        self.inception5a = InceptionV3C(1280, 320, 384, 384, 448, 384, 192)
        self.inception5b = InceptionV3C(2048, 320, 384, 384, 448, 384, 192)

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.dropout = nn.Dropout(0.5)
        self.fc = nn.Linear(2048, num_classes)
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        # N x 3 x 299 x 299
        x = self.conv1_1(x)
        # N x 32 x 149 x 149
        x = self.conv1_2(x)
        # N x 32 x 147 x 147
        x = self.conv1_3(x)
        #  N x 32 x 147 x 147
        x = self.maxpool1(x)
        # N x 64 x 73 x 73
        x = self.conv2(x)
        # N x 80 x 71 x 71
        x = self.conv3(x)
        # N x 192 x 35 x 35
        x = self.conv4(x)
        # N x 192 x 35 x 35
        x = self.inception3a(x)
        # N x 256 x 35 x 35
        x = self.inception3b(x)
        # N x 288 x 35 x 35
        x = self.inception3c(x)
        # N x 288 x 35x 35
        x = self.inception4a(x)
        # N x 768 x 17 x 17
        x = self.inception4b(x)
        # N x 768 x 17 x 17
        x = self.inception4c(x)
        # N x 768 x 17 x 17
        x = self.inception4d(x)
        # N x 768 x 17 x 17
        if self.training and self.aux_logits:    # eval model lose this layer
            aux = self.aux(x)
        # N x 768 x 17 x 17
        x = self.inception4e(x)
        # N x 1280 x 8 x 8
        x = self.inception5a(x)
        # N x 2048 x 8 x 8
        x = self.inception5b(x)
        # N x 2048 x 7 x 7
        x = self.avgpool(x)
        # N x 2048 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:  # 训练阶段使用
            return x, aux
        return x
    # 对模型的权重进行初始化操作
    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)

# InceptionV3A:BasicConv2d+MaxPool2d
class InceptionV3A(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3A, self).__init__()
        # 1×1卷积
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        # 1×1卷积+3×3卷积
        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
        )
        # 1×1卷积++3×3卷积+3×3卷积
        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=3, padding=1),
            BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=3, padding=1)         # 保证输出大小等于输入大小
        )
        # 3×3池化+1×1卷积
        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)
        # 拼接
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)

# InceptionV3B:BasicConv2d+MaxPool2d
class InceptionV3B(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3B, self).__init__()
        # 1×1卷积
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        # 1×1卷积+1×3卷积+3×1卷积
        self.branch2 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3red, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=[1, 3], padding=[0, 1]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[3, 1], padding=[1, 0])   # 保证输出大小等于输入大小
        )
        # 1×1卷积+1×3卷积+3×1卷积+1×3卷积+3×1卷积
        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=[1, 3], padding=[0, 1]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[3, 1], padding=[1, 0]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[1, 3], padding=[0, 1]),
            BasicConv2d(ch3x3, ch3x3, kernel_size=[3, 1], padding=[1, 0])  # 保证输出大小等于输入大小
        )
        # 3×3池化+1×1卷积
        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)
        # 拼接
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)

# InceptionV3C:BasicConv2d+MaxPool2d
class InceptionV3C(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3C, self).__init__()
        # 1×1卷积
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
        # 1×1卷积+1×3卷积+3×1卷积
        self.branch2_0 = BasicConv2d(in_channels, ch3x3red, kernel_size=1)
        self.branch2_1 = BasicConv2d(ch3x3red, ch3x3, kernel_size=[1, 3], padding=[0, 1])
        self.branch2_2 = BasicConv2d(ch3x3red, ch3x3, kernel_size=[3, 1], padding=[1, 0])

        # 1×1卷积+3×3卷积+1×3卷积+3×1卷积
        self.branch3_0 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=3, padding=1),
        )
        self.branch3_1 = BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=[1, 3], padding=[0, 1])
        self.branch3_2 = BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=[3, 1], padding=[1, 0])

        # 3×3池化+1×1卷积
        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_0 = self.branch2_0(x)
        branch2 = torch.cat([self.branch2_1(branch2_0), self.branch2_2(branch2_0)], dim=1)
        branch3_0 = self.branch3_0(x)
        branch3 = torch.cat([self.branch3_1(branch3_0), self.branch3_2(branch3_0)], dim=1)
        branch4 = self.branch4(x)
        # 拼接
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)

# InceptionV3D:BasicConv2d+MaxPool2d
class InceptionV3D(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):
        super(InceptionV3D, self).__init__()
        # ch1x1:没有1×1卷积
        # 1×1卷积+3×3卷积,步长为2
        self.branch1 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3red, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=3, stride=2)   # 保证输出大小等于输入大小
        )
        # 1×1卷积+3×3卷积+3×3卷积,步长为2
        self.branch2 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),
            BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=3, padding=1),   # 保证输出大小等于输入大小
            BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=3, stride=2)         # 保证输出大小等于输入大小
        )
        # 3×3池化,步长为2
        self.branch3 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=2))
        # pool_proj:池化层后不再接卷积层

    def forward(self, x):
        branch1 = self.branch1(x)
        branch2 = self.branch2(x)
        branch3 = self.branch3(x)
        # 拼接
        outputs = [branch1,branch2, branch3]
        return torch.cat(outputs, 1)

# 辅助分类器:AvgPool2d+BasicConv2d+Linear+dropout
class InceptionAux(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(InceptionAux, self).__init__()

        self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
        self.conv1 = BasicConv2d(in_channels=in_channels, out_channels=128, kernel_size=1)
        self.conv2 = BasicConv2d(in_channels=128, out_channels=768, kernel_size=5, stride=1)
        self.dropout = nn.Dropout(p=0.7)
        self.linear = nn.Linear(in_features=768, out_features=out_channels)
    def forward(self, x):
        # N x 768 x 17 x 17
        x = self.averagePool(x)
        # N x 768 x 5 x 5
        x = self.conv1(x)
        # N x 128 x 5 x 5
        x = self.conv2(x)
        # N x 768 x 1 x 1
        x = x.view(x.size(0), -1)
        # N x 768
        out = self.linear(self.dropout(x))
        # N x num_classes
        return out

# 卷积组: Conv2d+BN+ReLU
class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
        self.bn = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.relu(x)
        return x

if __name__ == '__main__':
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    model = GoogLeNetV3().to(device)
    summary(model, input_size=(3, 299, 299))