【图像分类】【深度学习】【Pytorch版本】GoogLeNet(InceptionV4)模型算法详解

【图像分类】【深度学习】【Pytorch版本】GoogLeNet(InceptionV4)模型算法详解

文章目录

  • 【图像分类】【深度学习】【Pytorch版本】GoogLeNet(InceptionV4)模型算法详解
  • 前言
  • GoogLeNet(InceptionV4)讲解
    • Stem结构
    • Inception-A结构
    • Inception- B结构
    • Inception-C结构
    • redution-A结构
    • redution-B结构
    • GoogLeNet(InceptionV4)模型结构
  • GoogLeNet(InceptionV4) Pytorch代码
  • 完整代码
  • 总结

前言

GoogLeNet(InceptionV4)是由谷歌的Szegedy, Christian等人在《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning【AAAI-2017】》【论文地址】一文中提出的改进模型，InceptionV4保留了此前的Inception模块的核心思想基础上进行了改进和优化，InceptionV4的所有模块都采用了统一的设计原则，即采用Inception模块作为基本单元，通过堆叠纯Inception基本单元来实现复杂的网络结构。

因为InceptionV4、Inception-Resnet-v1和Inception-Resnet-v2同出自一篇论文，大部分读者对InceptionV4存在误解，认为它是Inception模块与残差学习的结合，其实InceptionV4没有使用残差学习的思想，它基本延续了Inception v2/v3的结构，只有Inception-Resnet-v1和Inception-Resnet-v2才是Inception模块与残差学习的结合产物。

GoogLeNet(InceptionV4)讲解

InceptionV4的三种基础Inception结构与InceptionV3【参考】中使用的结构基本一样，但InceptionV4引入了一些新的模块形状及其间的连接设计，在网络的早期阶段引入了“Stem”模块，用于快速降低特征图的分辨率，从而减少后续Inception模块的计算量。

Stem结构

stem结构实际上是替代了此前的Inception系列网络中Inception结构组之前的网络层，Stem中借鉴了InceptionV3中使用的并行结构、不对称卷积核结构，并使用1*1的卷积核用来降维和增加非线性，可以在保证信息损失足够小的情况下，使得计算量降低。

所有卷积中没有标记为V表示填充方式为"SAME Padding"，输入和输出维度一致；标记为V表示填充方式为"VALID Padding"，输出维度视具体情况而定。

Inception-A结构

对应InceptionV3中的结构Ⅰ。

Inception- B结构

对应InceptionV3中的结构Ⅱ，只是1×3卷积和3×1卷积变成了1×7卷积和7×1卷积。

Inception-C结构

对应InceptionV3中的结构Ⅲ，只是3×3卷积变成了1×3卷积和3×1卷积的串联结构。

redution-A结构

对应InceptionV3中的特殊结构。

k和l表示卷积个数，不同网络结构的redution-A结构k和l是不同的，Inception-ResNet会在其他博文中介绍。

redution-B结构

采用并行、不对称卷积和1*1的卷积来降低计算量。

GoogLeNet(InceptionV4)模型结构

下图是原论文给出的关于 GoogLeNet(InceptionV4)模型结构的详细示意图：

GoogLeNet(InceptionV4)在图像分类中分为两部分：backbone部分： 主要由InceptionV4模块、Stem模块和池化层(汇聚层)组成，分类器部分：由全连接层组成。
InceptionV4三种Inception模块的个数分别为4、7、3个，而InceptionV3中则为3、5、2个，因此InceptionV4的层次更深、结构更复杂，feature map更多。为了降低计算量，在Inception-A和Inception-B后面分别添加了Reduction-A和Reduction-B的结构，用来降低计算量。

GoogLeNet(InceptionV4) 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

Stem模块： 卷积层组+池化层

# Stem:BasicConv2d+MaxPool2d
class Stem(nn.Module):def __init__(self, in_channels, out_channels):super(Stem, self).__init__()# conv3*3(32 stride2 valid)self.conv1 = BasicConv2d(in_channels, 32, kernel_size=3, stride=2)# conv3*3(32 valid)self.conv2 = BasicConv2d(32, 32, kernel_size=3)# conv3*3(64)self.conv3 = BasicConv2d(32, 64, kernel_size=3, padding=1)# maxpool3*3(stride2 valid) & conv3*3(96 stride2 valid)self.maxpool4 = nn.MaxPool2d(kernel_size=3, stride=2)self.conv4 = BasicConv2d(64, 96, kernel_size=3, stride=2)# conv1*1(64)+conv3*3(96 valid)self.conv5_1_1 = BasicConv2d(160, 64, kernel_size=1)self.conv5_1_2 = BasicConv2d(64, 96, kernel_size=3)# conv1*1(64)+conv7*1(64)+conv1*7(64)+conv3*3(96 valid)self.conv5_2_1 = BasicConv2d(160, 64, kernel_size=1)self.conv5_2_2 = BasicConv2d(64, 64, kernel_size=(7, 1), padding=(3, 0))self.conv5_2_3 = BasicConv2d(64, 64, kernel_size=(1, 7), padding=(0, 3))self.conv5_2_4 = BasicConv2d(64, 96, kernel_size=3)# conv3*3(192 valid) & maxpool3*3(stride2 valid)self.conv6 = BasicConv2d(192, 192, kernel_size=3, stride=2)self.maxpool6 = nn.MaxPool2d(kernel_size=3, stride=2)def forward(self, x):x1_1 = self.maxpool4(self.conv3(self.conv2(self.conv1(x))))x1_2 = self.conv4(self.conv3(self.conv2(self.conv1(x))))x1 = torch.cat([x1_1, x1_2], 1)x2_1 = self.conv5_1_2(self.conv5_1_1(x1))x2_2 = self.conv5_2_4(self.conv5_2_3(self.conv5_2_2(self.conv5_2_1(y1))))x2 = torch.cat([x2_1, x2_2], 1)x3_1 = self.conv6(x2)x3_2 = self.maxpool6(x2)x3 = torch.cat([x3_1, x3_2], 1)return x3

Inception-A模块： 卷积层组+池化层

# InceptionV4A:BasicConv2d+MaxPool2d
class InceptionV4A(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):super(InceptionV4A, self).__init__()# conv1*1(96)self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)# conv1*1(64)+conv3*3(96)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)# conv1*1(64)+conv3*3(96)+conv3*3(96)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)# avgpool + conv1*1(96)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)

Inception-B模块： 卷积层组+池化层

# InceptionV4B:BasicConv2d+MaxPool2d
class InceptionV4B(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3_1, ch3x3_2, ch3x3redX2, ch3x3X2_1, ch3x3X2_2, pool_proj):super(InceptionV4B, self).__init__()# conv1*1(384)self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)# conv1*1(192)+conv1*7(224)+conv1*7(256)self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch3x3red, kernel_size=1),BasicConv2d(ch3x3red, ch3x3_1, kernel_size=[1, 7], padding=[0, 3]),BasicConv2d(ch3x3_1, ch3x3_2, kernel_size=[7, 1], padding=[3, 0])   # 保证输出大小等于输入大小)# conv1*1(192)+conv1*7(192)+conv7*1(224)+conv1*7(224)+conv7*1(256)self.branch3 = nn.Sequential(BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),BasicConv2d(ch3x3redX2, ch3x3redX2, kernel_size=[1, 7], padding=[0, 3]),BasicConv2d(ch3x3redX2, ch3x3X2_1, kernel_size=[7, 1], padding=[3, 0]),BasicConv2d(ch3x3X2_1, ch3x3X2_1, kernel_size=[1, 7], padding=[0, 3]),BasicConv2d(ch3x3X2_1, ch3x3X2_2, kernel_size=[7, 1], padding=[3, 0])  # 保证输出大小等于输入大小)# avgpool+conv1*1(128)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)

Inception-C模块： 卷积层组+池化层

# InceptionV4C:BasicConv2d+MaxPool2d
class InceptionV4C(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2_1, ch3x3X2_2, ch3x3X2_3,pool_proj):super(InceptionV4C, self).__init__()# conv1*1(256)self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)# conv1*1(384)+conv1*3(256) & conv3*1(256)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])# conv1*1(384)+conv1*3(448)+conv3*1(512)+conv3*1(256) & conv7*1(256)self.branch3_0 = nn.Sequential(BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),BasicConv2d(ch3x3redX2, ch3x3X2_1, kernel_size=[1, 3], padding=[0, 1]),BasicConv2d(ch3x3X2_1, ch3x3X2_2, kernel_size=[3, 1], padding=[1, 0]),)self.branch3_1 = BasicConv2d(ch3x3X2_2, ch3x3X2_3, kernel_size=[1, 3], padding=[0, 1])self.branch3_2 = BasicConv2d(ch3x3X2_2, ch3x3X2_3, kernel_size=[3, 1], padding=[1, 0])# avgpool+conv1*1(256)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)

redutionA模块： 卷积层组+池化层

# redutionA:BasicConv2d+MaxPool2d
class redutionA(nn.Module):def __init__(self, in_channels, k, l, m, n):super(redutionA, self).__init__()# conv3*3(n stride2 valid)self.branch1 = nn.Sequential(BasicConv2d(in_channels, n, kernel_size=3, stride=2),)# conv1*1(k)+conv3*3(l)+conv3*3(m stride2 valid)self.branch2 = nn.Sequential(BasicConv2d(in_channels, k, kernel_size=1),BasicConv2d(k, l, kernel_size=3, padding=1),BasicConv2d(l, m, kernel_size=3, stride=2))# maxpool3*3(stride2 valid)self.branch3 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=2))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)

redutionB模块： 卷积层组+池化层

# redutionB:BasicConv2d+MaxPool2d
class redutionB(nn.Module):def __init__(self, in_channels, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2):super(redutionB, self).__init__()# conv1*1(192)+conv3*3(192 stride2 valid)self.branch1 = nn.Sequential(BasicConv2d(in_channels, ch3x3red, kernel_size=1),BasicConv2d(ch3x3red, ch3x3, kernel_size=3, stride=2))# conv1*1(256)+conv1*7(256)+conv7*1(320)+conv3*3(320 stride2 valid)self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),BasicConv2d(ch3x3redX2, ch3x3redX2, kernel_size=(1, 7), padding=(0, 3)),# 保证输出大小等于输入大小BasicConv2d(ch3x3redX2, ch3x3X2, kernel_size=(7, 1), padding=(3, 0)),BasicConv2d(ch3x3X2, ch3x3X2, kernel_size=3, stride=2))#  maxpool3*3(stride2 valid)self.branch3 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=2))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)

完整代码

GoogLeNet(InceptionV4)的输入图像尺寸是299×299

import torch.nn as nn
import torch
from torchsummary import summaryclass GoogLeNetV4(nn.Module):def __init__(self, num_classes=1000, init_weights=False):super(GoogLeNetV4, self).__init__()# stem模块self.stem = Stem(3, 384)# InceptionA模块self.inceptionA = InceptionV4A(384, 96, 64, 96, 64, 96, 96)# RedutionA模块self.RedutionA = redutionA(384, 192, 224, 256, 384)# InceptionB模块self.InceptionB = InceptionV4B(1024, 384, 192, 224, 256, 192, 224,256,128)# RedutionB模块self.RedutionB = redutionB(1024,     192, 192, 256, 320)# InceptionC模块self.InceptionC = InceptionV4C(1536, 256, 384, 256, 384, 448, 512, 256,256)self.avgpool = nn.AdaptiveAvgPool2d((1, 1))self.dropout = nn.Dropout(0.8)self.fc = nn.Linear(1536, num_classes)if init_weights:self._initialize_weights()def forward(self, x):# Stem Module# N x 3 x 299 x 299x = self.stem(x)# InceptionA Module * 4# N x 384 x 26 x 26x = self.inceptionA(self.inceptionA(self.inceptionA(self.inceptionA(x))))# ReductionA Module# N x 384 x 26 x 26x = self.RedutionA(x)# InceptionB Module * 7# N x 1024 x 12 x 12x = self.InceptionB(self.InceptionB(self.InceptionB(self.InceptionB(self.InceptionB(self.InceptionB(self.InceptionB(x)))))))# ReductionB Module# N x 1024 x 12 x 12x = self.RedutionB(x)# InceptionC Module * 3# N x 1536 x 5 x 5x = self.InceptionC(self.InceptionC(self.InceptionC(x)))# Average Pooling# N x 1536 x 5 x 5x = self.avgpool(x)# N x 1536 x 1 x 1x = x.view(x.size(0), -1)# Dropout# N x 1536x = self.dropout(x)# Linear(Softmax)# N x 1536x = self.fc(x)# N x 1000return 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)# InceptionV4A:BasicConv2d+MaxPool2d
class InceptionV4A(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2, pool_proj):super(InceptionV4A, self).__init__()# conv1*1(96)self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)# conv1*1(64)+conv3*3(96)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)# conv1*1(64)+conv3*3(96)+conv3*3(96)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)# avgpool+conv1*1(96)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)# InceptionV4B:BasicConv2d+MaxPool2d
class InceptionV4B(nn.Module):def __init__(self, in_channels, ch1x1, ch_red, ch_1, ch_2, ch_redX2, ch_X2_1, ch_X2_2, pool_proj):super(InceptionV4B, self).__init__()# conv1*1(384)self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)# conv1*1(192)+conv1*7(224)+conv1*7(256)self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch_red, kernel_size=1),BasicConv2d(ch_red, ch_1, kernel_size=[1, 7], padding=[0, 3]),BasicConv2d(ch_1, ch_2, kernel_size=[7, 1], padding=[3, 0])   # 保证输出大小等于输入大小)# conv1*1(192)+conv1*7(192)+conv7*1(224)+conv1*7(224)+conv7*1(256)self.branch3 = nn.Sequential(BasicConv2d(in_channels, ch_redX2, kernel_size=1),BasicConv2d(ch_redX2, ch_redX2, kernel_size=[1, 7], padding=[0, 3]),BasicConv2d(ch_redX2, ch_X2_1, kernel_size=[7, 1], padding=[3, 0]),BasicConv2d(ch_X2_1, ch_X2_1, kernel_size=[1, 7], padding=[0, 3]),BasicConv2d(ch_X2_1, ch_X2_2, kernel_size=[7, 1], padding=[3, 0])  # 保证输出大小等于输入大小)# avgpool+conv1*1(128)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)# InceptionV4C:BasicConv2d+MaxPool2d
class InceptionV4C(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch3x3redX2, ch3x3X2_1, ch3x3X2_2, ch3x3X2_3,pool_proj):super(InceptionV4C, self).__init__()# conv1*1(256)self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)# conv1*1(384)+conv1*3(256) & conv3*1(256)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])# conv1*1(384)+conv1*3(448)+conv3*1(512)+conv3*1(256) & conv7*1(256)self.branch3_0 = nn.Sequential(BasicConv2d(in_channels, ch3x3redX2, kernel_size=1),BasicConv2d(ch3x3redX2, ch3x3X2_1, kernel_size=[1, 3], padding=[0, 1]),BasicConv2d(ch3x3X2_1, ch3x3X2_2, kernel_size=[3, 1], padding=[1, 0]),)self.branch3_1 = BasicConv2d(ch3x3X2_2, ch3x3X2_3, kernel_size=[1, 3], padding=[0, 1])self.branch3_2 = BasicConv2d(ch3x3X2_2, ch3x3X2_3, kernel_size=[3, 1], padding=[1, 0])# avgpool+conv1*1(256)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)# redutionA:BasicConv2d+MaxPool2d
class redutionA(nn.Module):def __init__(self, in_channels, k, l, m, n):super(redutionA, self).__init__()# conv3*3(n stride2 valid)self.branch1 = nn.Sequential(BasicConv2d(in_channels, n, kernel_size=3, stride=2),)# conv1*1(k)+conv3*3(l)+conv3*3(m stride2 valid)self.branch2 = nn.Sequential(BasicConv2d(in_channels, k, kernel_size=1),BasicConv2d(k, l, kernel_size=3, padding=1),BasicConv2d(l, m, kernel_size=3, stride=2))# maxpool3*3(stride2 valid)self.branch3 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=2))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)# redutionB:BasicConv2d+MaxPool2d
class redutionB(nn.Module):def __init__(self, in_channels, ch3x3red, ch3x3, ch_redX2, ch_X2):super(redutionB, self).__init__()# conv1*1(192)+conv3*3(192 stride2 valid)self.branch1 = nn.Sequential(BasicConv2d(in_channels, ch3x3red, kernel_size=1),BasicConv2d(ch3x3red, ch3x3, kernel_size=3, stride=2))# conv1*1(256)+conv1*7(256)+conv7*1(320)+conv3*3(320 stride2 valid)self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch_redX2, kernel_size=1),BasicConv2d(ch_redX2, ch_redX2, kernel_size=(1, 7), padding=(0, 3)),# 保证输出大小等于输入大小BasicConv2d(ch_redX2, ch_X2, kernel_size=(7, 1), padding=(3, 0)),BasicConv2d(ch_X2, ch_X2, kernel_size=3, stride=2))#  maxpool3*3(stride2 valid)self.branch3 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=2))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)# Stem:BasicConv2d+MaxPool2d
class Stem(nn.Module):def __init__(self, in_channels, out_channels):super(Stem, self).__init__()# conv3*3(32 stride2 valid)self.conv1 = BasicConv2d(in_channels, 32, kernel_size=3, stride=2)# conv3*3(32 valid)self.conv2 = BasicConv2d(32, 32, kernel_size=3)# conv3*3(64)self.conv3 = BasicConv2d(32, 64, kernel_size=3, padding=1)# maxpool3*3(stride2 valid) & conv3*3(96 stride2 valid)self.maxpool4 = nn.MaxPool2d(kernel_size=3, stride=2)self.conv4 = BasicConv2d(64, 96, kernel_size=3, stride=2)# conv1*1(64)+conv3*3(96 valid)self.conv5_1_1 = BasicConv2d(160, 64, kernel_size=1)self.conv5_1_2 = BasicConv2d(64, 96, kernel_size=3)# conv1*1(64)+conv7*1(64)+conv1*7(64)+conv3*3(96 valid)self.conv5_2_1 = BasicConv2d(160, 64, kernel_size=1)self.conv5_2_2 = BasicConv2d(64, 64, kernel_size=(7, 1), padding=(3, 0))self.conv5_2_3 = BasicConv2d(64, 64, kernel_size=(1, 7), padding=(0, 3))self.conv5_2_4 = BasicConv2d(64, 96, kernel_size=3)# conv3*3(192 valid) & maxpool3*3(stride2 valid)self.conv6 = BasicConv2d(192, 192, kernel_size=3, stride=2)self.maxpool6 = nn.MaxPool2d(kernel_size=3, stride=2)def forward(self, x):x1_1 = self.maxpool4(self.conv3(self.conv2(self.conv1(x))))x1_2 = self.conv4(self.conv3(self.conv2(self.conv1(x))))x1 = torch.cat([x1_1, x1_2], 1)x2_1 = self.conv5_1_2(self.conv5_1_1(x1))x2_2 = self.conv5_2_4(self.conv5_2_3(self.conv5_2_2(self.conv5_2_1(x1))))x2 = torch.cat([x2_1, x2_2], 1)x3_1 = self.conv6(x2)x3_2 = self.maxpool6(x2)x3 = torch.cat([x3_1, x3_2], 1)return x3# 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 xif __name__ == '__main__':device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")model = GoogLeNetV4().to(device)summary(model, input_size=(3, 229, 229))

summary可以打印网络结构和参数，方便查看搭建好的网络结构。

总结

尽可能简单、详细的介绍了InceptionV4的改进方案，讲解了GoogLeNet(InceptionV4)模型的结构和pytorch代码。

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：http://www.rhkb.cn/news/198759.html

如若内容造成侵权/违法违规/事实不符，请联系长河编程网进行投诉反馈email:809451989@qq.com，一经查实，立即删除！

相关文章

2024年山东省职业院校技能大赛中职组 “网络安全”赛项竞赛试题-A卷

2024年山东省职业院校技能大赛中职组 “网络安全”赛项竞赛试题-A卷

2024年山东省职业院校技能大赛中职组 “网络安全”赛项竞赛试题-A卷 2024年山东省职业院校技能大赛中职组 “网络安全”赛项竞赛试题-A卷A模块基础设施设置/安全加固（200分）A-1：登录安全加固（Windows, Linux）A-2&#…
阅读更多...
大力说企微入门系列第二课：搭建体系

大力说企微入门系列第二课：搭建体系

对于大部分人来说，学习有三动： 学习之前非常激动； 学习时候非常感动；学习之后是一动不动； 不知道大家看了上一课的《大力说企微入门系列第一课：企业微信的注册验证和认证》之后，是一动不动还是…
阅读更多...
java基础练习缺少项目？看这篇文章就够了（下）！

java基础练习缺少项目？看这篇文章就够了（下）！

公众号：全干开发 。 专注分享简洁但高质量的动图技术文章！ 回顾 在上节内容中，我们实现了用户开户的功能createAccount public void start(){System.out.println("欢迎您进入到了ATM系统");System.out.println("1、用户登录&…
阅读更多...
基于JavaWeb的智慧停车管理系统设计与实现

基于JavaWeb的智慧停车管理系统设计与实现

项目描述 临近学期结束，还是毕业设计，你还在做java程序网络编程，期末作业，老师的作业要求觉得大了吗?不知道毕业设计该怎么办?网页功能的数量是否太多?没有合适的类型或系统?等等。你想解决的问题，今天给大家介绍…
阅读更多...
2024年测试工程师必看系列之fiddler设置手机端抓包全套教程

2024年测试工程师必看系列之fiddler设置手机端抓包全套教程

fiddler设置手机端抓包 安卓手机抓包 第一步：配置电脑和安卓的相关设置 1、手机和fiddler位于同一个局域网内；首先从fiddler处获取到ip地址和端口号： ，点击online，最后一行就是ip地址 2、路径：Tools》Op…
阅读更多...
（动手学习深度学习）第13章 计算机视觉---微调

（动手学习深度学习）第13章 计算机视觉---微调

文章目录 微调总结 微调代码实现 微调 总结 微调通过使用在大数据上的恶道的预训练好的模型来初始化模型权重来完成提升精度。预训练模型质量很重要微调通常速度更快、精确度更高 微调代码实现 导入相关库 %matplotlib inline import os import torch import torchvision f…
阅读更多...
Linux网络——HTTP

Linux网络——HTTP

目录 一.应用层 二.认识URL 1.域名 2.urlencode和urldecode 三.HTTP协议格式 1.请求格式http 2.响应格式 四.HTTP响应状态码 五.HTTP常见Header 六.简单的HTTP服务器 七.HTTP的方法 1.GET方法 2.POST方法 一.应用层 我们程序员写的一个个解决我们实际问题, 满足…
阅读更多...
深入分析高性能互连点对点通信开销

深入分析高性能互连点对点通信开销

今天分享最近阅读的一篇文章：“Breaking Band，A Breakdown of High-Performance Communication”，这篇文章发表在ICPP 2019会议。由加州大学欧文分校和ARM公司合作完成。从题目中可以看到，这篇文章是一篇评测型的文章，…
阅读更多...
JDY蓝牙注意事项

JDY蓝牙注意事项

波特率设置：9600，不接受115200，或者38400. 不同于WiFi测试，jdy蓝牙不接受AT"指令，可以使用“ATVERSION"指令测试 安信可公司的那个蓝牙指令在这里没有用，不知道是不是生产的公司不一样
阅读更多...
网络协议入门 笔记一

网络协议入门 笔记一

一、服务器和客户端及java的概念 JVM (Java Virtual Machine) : Java虚拟机，Java的跨平台:一次编译，到处运行，编译生成跟平台无关的字节码文件 (class文件)，由对应平台的JVM解析字节码为机器指令 (010101)。 如下图所示&#xff0…
阅读更多...
Java入门篇 之 抽象类接口

Java入门篇 之 抽象类接口

本篇碎碎念：个人认为压力是一种前进的动力，但是不要有太多压力，不然会使心情烦躁，会控制不住自己的情绪，会在一个临界值爆发，一旦爆发，将迟迟不能消散 今日份励志文案: 努力的背后必有加倍的赏赐…
阅读更多...
Word中NoteExpress不显示的问题

Word中NoteExpress不显示的问题

首先确认我们以及安装了word插件 我们打开word却没有。此时我们打开：文件->选项->加载项 我们发现被禁用了 选择【禁用项目】（如果没有，试一试【缓慢且禁用的加载项】），点击转到 选择启用 如果没有禁用且没有出…
阅读更多...
海康威视综合安防管理平台任意文件上传

海康威视综合安防管理平台任意文件上传

系统介绍 HIKVISION iSecure Center综合安防管理平台是一套“集成化”、“智能化”的平台，通过接入视频监控、一卡通、停车场、报警检测等系统的设备，获取边缘节点数据，实现安防信息化集成与联动，公众号：web安全工具库…
阅读更多...
使用centos搭建内网的yum源

使用centos搭建内网的yum源

1.安装httpd服务 2.启动服务，设置开机自启 #启动服务 systemctl start httpd # 设置开机自动启动 systemctl enable httpd systemctl status httpd3.新建一个目录，将rpm文件放到该目录下 4.将/etc/httpd/conf/httpd.conf文件中的DocumentRoot "…
阅读更多...
SASS/SCSS精华干货教程

SASS/SCSS精华干货教程

目录 介绍 基本说明 特点 sass语法格式sass的语法格式一共有两种，一种是以".scss"作为拓展名，一种是以".sass"作为拓展名，这里我们只讲拓展名： 编译环境安装 Vscode安装编译插件 简单使用 sass语法扩张…
阅读更多...
合并两个有序链表(冒泡排序实现)

合并两个有序链表(冒泡排序实现)

实例要求：将两个升序链表合并为一个新的 升序 链表并返回；新链表是通过拼接给定的两个链表的所有节点组成的；实例分析：先拼接两个链表，在使用冒泡排序即可；示例代码： struct ListNode* mergeTwo…
阅读更多...
docker的基本使用以及使用Docker 运行D435i

docker的基本使用以及使用Docker 运行D435i

1.一些基本的指令 1.1 容器 要查看正在运行的容器&#xff1a; sudo docker ps 查看所有的容器&#xff08;包括停止状态的容器&#xff09; sudo docker ps -a 重新命名容器 sudo docker rename <old_name> <new_name> <old_name> 替换为你的容器名称…
阅读更多...
查询数据库DQL

查询数据库DQL

DQL 查询基本语法 -- DQL :基本语法; -- 1查询指定的字段 name entrydate 并返回select name , entrydate from tb_emp;-- 2 查询 所有字段 并返回select id, username, password, name, gender, image, job, entrydate, create_time, update_time from tb_emp;-- 2 查询…
阅读更多...
C++ 继承和派生 万字长文超详解

C++ 继承和派生 万字长文超详解

本文章内容来源于C课堂上的听课笔记 继承和派生基础 继承是一种概念&#xff0c;它允许一个新创建的类&#xff08;称为子类或派生类&#xff09;获取另一个已经存在的类&#xff08;称为父类或基类&#xff09;的属性和行为。这就好比是子类继承了父类的特征。想象一下&…
阅读更多...
【dc-dc】世微 电动车摩托车灯 5-80V 1.2A 一切二降压恒流驱动器AP2915

【dc-dc】世微 电动车摩托车灯 5-80V 1.2A 一切二降压恒流驱动器AP2915

产品描述 AP2915 是一款可以一路灯串切换两路灯串的降压恒流驱动器,高效率、外围简单、内置功率管&#xff0c;适用于5-80V 输入的高精度降压 LED 恒流驱动芯片。内置功率管输出最大功率可达 12W&#xff0c;最大电流 1.2A。AP2915 一路灯亮切换两路灯亮&#xff0c;其中一路灯…
阅读更多...
最新文章
推荐文章

Copyright @ 2022~2023