Inception V1辅助分类器代码段

import torch.nn as nn
import torch
import torch.nn.functional as F# 4.定义googlenet网络
# aux_logits=True：使用辅助分类器。
# init_weights=False：初始化权重。
# self.aux_logits = aux_logits->把是否使用辅助分类器传入到类变量当中。
# ceil_mode=True->代表卷积后参数向上取整
class 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)# 按照inception结构（该层输入大小[上层输出大小],1x1,3x3reduce,3x3,5x5reduce,5x5）来写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 14# training=true/false看当前处于哪种模式,aux是否用到辅助分类器if 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, aux1 # 主分支输出值，辅助分类器输出值return 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)# 2.定义Inception结构
# 一共有4个branch,最后用torch,cat()合并成一个矩阵，1代表深度
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)# 3.定义分类器模块
# 1）nn.AvgPool2d(kernel_size=5, stride=3)：平均池化下采样-》核大小为5x5，步长为3。
# 2）BasicConv2d()：卷积激活
# 3）nn.Linear(2048, 1024)、nn.Linear(1024, num_classes);经过两个全连接层得到分类的一维向量。
# 4）torch.flatten(x, 1)：从深度方向对特征矩阵进行推平处理，从3维降到2维。
# 5）模块前向传播总流程：输入特征矩阵x->平均池化AvgPool2d->卷积BasicConv2d->降维推平flatten->随机失活Dropout->激活Relu->随机失活Dropout->全连接fc->得到分类。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# 1.首先定义一个基本卷积模块包含一个卷积层和一个Relu激活层和一个正向传播函数。
# in_channels->输入特征矩阵的深度
# out_channels->输出特征矩阵的深度。其中 self.conv = nn.Conv2d()中的out_channels也代表卷积核个数
# **kwargs 允许你将不定长度的键值对, 作为参数传递给一个函数。 如果你想要在一个函数里处理带名字的参数, 你应该使用**kwargs
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

(18条消息) 使用pytorch搭建GoogLeNet网络_Action_now的博客-CSDN博客_googlenet pytorch

感谢大佬

Inception V1辅助分类器代码段相关推荐

[计算机视觉]-经典网络inception v1、v2、v3、v4核心工作详解及总结
资源 inception v1 Going deeper with convolutions:https://arxiv.org/abs/1409.4842 BN算法 Batch Normalizat ...
经典的卷积网络架构(二)——GoogLeNet [inception v1] 详解
GoogLeNet出自论文Going Deeper With Convolutions 如有错误,欢迎指正! (未完待续) 目录论文阅读补充知识点:1*1卷积的作用网络结构分析参考博文参考代 ...
GoogLeNet（从Inception v1到v4的演进）
GoogLeNetInceptionCNN深度学习卷积神经网络 2014年,GoogLeNet和VGG是当年ImageNet挑战赛(ILSVRC14)的双雄,GoogLeNet获得了第一名.VGG获得 ...
谷歌系列 :Inception v1到v4
Paper列表: [v1] Going Deeper with Convolutions, 6.67% test error, http://arxiv.org/abs/1409.4842 [v2] ...
inception v4 官方实现_经典神经网络 | 从Inception v1到Inception v4全解析
本文介绍了 Inception 家族的主要成员,包括 Inception v1.Inception v2 .Inception v3.Inception v4 和 Inception-ResNet.它 ...
CNN经典模型：GoogLeNet（从Inception v1到v4的演进）
GoogLeNet和VGG是2014年ImageNet挑战赛(ILSVRC14)的双雄,GoogLeNet获得第一名.VGG获得第二名,这两类模型结构的共同特点是层次更深了.VGG继承了LeNet以及 ...
经典神经网络 | 从Inception v1到Inception v4全解析
本文介绍了 Inception 家族的主要成员,包括 Inception v1.Inception v2 .Inception v3.Inception v4 和 Inception-ResNet.它 ...
经典卷积神经系列（Inception v1\v2\v3\v4、ResNet、ResNext、DenseNet、SENet）
写在前面:此文只记录了下本人感觉需要注意的地方,不全且不一定准确.详细内容可以参考文中帖的链接,比较好!!! 经典的CNN:Inception v1\v2\v3\v4.Resnet.Resnext.D ...
【论文阅读】inception v1学习总结
[论文阅读总结]inception v1总结 1. 摘要 2. 序言 3. 文献综述 4.动机和高层考虑 4.1提高深度神经网络性能的最直接方法 4.1.1 增加模型的大小 4.1.2 解决增加模型大 ...

Inception V1辅助分类器代码段

Inception V1辅助分类器代码段相关推荐

最新文章

热门文章