深度学习-解读GoogleNet深度学习网络

class ConvReLU(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride, padding):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=True),
            nn.ReLU(inplace=True),
        )    
    def forward(self, x):
        return self.conv(x)
        
        
class InceptionModule(nn.Module):
    def __init__(self, in_channels, c1x1_out, c3x3_in, c3x3_out, c5x5_in, c5x5_out, pool_proj):
        super().__init__()
        self.branch1 = ConvReLU(in_channels=in_channels, out_channels=c1x1_out, kernel_size=1, stride=1, padding=0)
        self.branch2 = nn.Sequential(
            ConvReLU(in_channels=in_channels, out_channels=c3x3_in, kernel_size=1, stride=1, padding=0),
            ConvReLU(in_channels=c3x3_in, out_channels=c3x3_out, kernel_size=3, stride=1, padding=1)
        )
        self.branch3 = nn.Sequential(
            ConvReLU(in_channels=in_channels, out_channels=c5x5_in, kernel_size=1, stride=1, padding=0),
            ConvReLU(in_channels=c5x5_in, out_channels=c5x5_out, kernel_size=5, stride=1, padding=2)
        )
        self.branch4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
            ConvReLU(in_channels=in_channels, out_channels=pool_proj, kernel_size=1, stride=1, padding=0)
        )
    def forward(self, x):
        x1 = self.branch1(x)
        x2 = self.branch2(x)
        x3 = self.branch3(x)
        x4 = self.branch4(x)
        x = torch.cat([x1, x2, x3, x4], dim=1)
        return x



class AuxClassifier(nn.Module):
    def __init__(self, in_channels, n_classes):
        super().__init__()
        self.avgpool = nn.AdaptiveAvgPool2d(4)
        self.conv = ConvReLU(in_channels=in_channels, out_channels=128, kernel_size=1, stride=1, padding=0)
        self.fc1 = nn.Sequential(
            nn.Linear(in_features=128*4*4, out_features=1024, bias=True),
            nn.ReLU(inplace=True)
        )
        self.dropout = nn.Dropout(p=0.7)
        self.fc2 = nn.Linear(in_features=1024, out_features=n_classes, bias=True)
        self.softmax = nn.Softmax(dim=-1)
        
    def forward(self, x):
        b, _, _ ,_ = x.shape
        x = self.avgpool(x)
        x = self.conv(x)
        x = self.fc1(x.view(b, -1))
        x = self.dropout(x)
        x = self.fc2(x)
        x = self.softmax(x)
        return x
    
    
class GooLeNet(nn.Module):
    def __init__(self, in_channels, n_classes) -> None:
        super().__init__()
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.avgpool = nn.AdaptiveAvgPool2d(output_size=1)
        
        self.conv1 = nn.Sequential(
            ConvReLU(in_channels=in_channels, out_channels=64, kernel_size=7, stride=2, padding=3),
            nn.LocalResponseNorm(size=5, k=2, alpha=1e-4, beta=0.75),
        )
        self.conv2 = nn.Sequential(
            ConvReLU(in_channels=64, out_channels=64, kernel_size=1, stride=1, padding=0),
            ConvReLU(in_channels=64, out_channels=192, kernel_size=3, stride=1, padding=1),
            nn.LocalResponseNorm(size=5, k=2, alpha=1e-4, beta=0.75),
        )
        
        self.inception3a = InceptionModule(in_channels=192, c1x1_out=64, c3x3_in=96, c3x3_out=128, c5x5_in=16, c5x5_out=32, pool_proj=32)
        self.inception3b = InceptionModule(in_channels=256, c1x1_out=128, c3x3_in=128, c3x3_out=192, c5x5_in=32, c5x5_out=96, pool_proj=64)

        self.inception4a = InceptionModule(in_channels=480, c1x1_out=192, c3x3_in=96, c3x3_out=208, c5x5_in=16, c5x5_out=48, pool_proj=64)
        self.inception4b = InceptionModule(in_channels=512, c1x1_out=160, c3x3_in=112, c3x3_out=224, c5x5_in=24, c5x5_out=64, pool_proj=64)
        self.inception4c = InceptionModule(in_channels=512, c1x1_out=128, c3x3_in=128, c3x3_out=256, c5x5_in=24, c5x5_out=64, pool_proj=64)
        self.inception4d = InceptionModule(in_channels=512, c1x1_out=112, c3x3_in=144, c3x3_out=288, c5x5_in=32, c5x5_out=64, pool_proj=64)
        self.inception4e = InceptionModule(in_channels=528, c1x1_out=256, c3x3_in=160, c3x3_out=320, c5x5_in=32, c5x5_out=128, pool_proj=128)

        self.inception5a = InceptionModule(in_channels=832, c1x1_out=256, c3x3_in=160, c3x3_out=320, c5x5_in=32, c5x5_out=128, pool_proj=128)
        self.inception5b = InceptionModule(in_channels=832, c1x1_out=384, c3x3_in=192, c3x3_out=384, c5x5_in=48, c5x5_out=128, pool_proj=128)

        self.dropout = nn.Dropout(p=0.4)
        self.fc = nn.Linear(in_features=1024, out_features=n_classes, bias=True)
        self.softmax = nn.Softmax(dim=-1)
        
        self.aux_classfier1 = AuxClassifier(in_channels=512, n_classes=n_classes)
        self.aux_classfier2 = AuxClassifier(in_channels=528, n_classes=n_classes)

    def forward(self, x):
        b, _, _, _ = x.shape
        x = self.conv1(x)
        print('# Conv1 output shape:', x.shape)
        x = self.maxpool(x)
        print('# Pool1 output shape:', x.shape)
        x = self.conv2(x)
        print('# Conv2 output shape:', x.shape)
        x = self.maxpool(x)
        print('# Pool2 output shape:', x.shape)
        x = self.inception3a(x)
        print('# Inception3a output shape:', x.shape)
        x = self.inception3b(x)
        print('# Inception3b output shape:', x.shape)
        x = self.maxpool(x)
        print('# Pool3 output shape:', x.shape)
        x = self.inception4a(x)
        print('# Inception4a output shape:', x.shape)
        aux1 = self.aux_classfier1(x)
        print('# aux_classifier1 output shape:', aux1.shape)
        x = self.inception4b(x)
        print('# Inception4b output shape:', x.shape)
        x = self.inception4c(x)
        print('# Inception4c output shape:', x.shape)
        x = self.inception4d(x)
        print('# Inception4d output shape:', x.shape)
        aux2 = self.aux_classfier2(x)
        print('# aux_classifier2 output shape:', aux2.shape)
        x = self.inception4e(x)
        print('# Inception4e output shape:', x.shape)
        x = self.maxpool(x)
        print('# Pool4 output shape:', x.shape)
        x = self.inception5a(x)
        print('# Inception5a output shape:', x.shape)
        x = self.inception5b(x)
        print('# Inception5b output shape:', x.shape)
        x = self.avgpool(x)
        print('# Avgpool output shape:', x.shape)
        x = self.dropout(x.view(b, -1))
        print('# dropout output shape:', x.shape)
        x = self.fc(x)
        print('# FC output shape:', x.shape)
        x = self.softmax(x)
        print('# Softmax output shape:', x.shape)
        return x, aux1, aux2

    
inputs = torch.randn(4, 3, 224, 224)
cnn = GooLeNet(in_channels = 3, n_classes = 1000)
outputs = cnn(inputs)

在这里插入图片描述

大家可以和前面的对照差异，也可以一窥DeepLearning技术的突破点。

在VGGNet 是一大创举，DeepMind团队更闻名的是在围棋开创一片天地，AlphaGo风靡一时，把人工智能推向又一个高潮，CNN网络引领的深度学习蓬勃发展，造就人工智能技术革命的起点。

觉得有用 收藏收藏收藏

点个赞点个赞点个赞

End

GPT专栏文章：

GPT实战系列-实战Qwen通义千问在Cuda 12+24G部署方案_通义千问 ptuning-CSDN博客

GPT实战系列-ChatGLM3本地部署CUDA11+1080Ti+显卡24G实战方案

GPT实战系列-Baichuan2本地化部署实战方案

GPT实战系列-让CodeGeeX2帮你写代码和注释_codegeex 中文-CSDN博客

GPT实战系列-ChatGLM3管理工具的API接口_chatglm3 api文档-CSDN博客

GPT实战系列-大话LLM大模型训练-CSDN博客

GPT实战系列-LangChain + ChatGLM3构建天气查询助手

GPT实战系列-大模型为我所用之借用ChatGLM3构建查询助手

GPT实战系列-P-Tuning本地化训练ChatGLM2等LLM模型，到底做了什么？(二)

GPT实战系列-P-Tuning本地化训练ChatGLM2等LLM模型，到底做了什么？(一)

GPT实战系列-ChatGLM2模型的微调训练参数解读

GPT实战系列-如何用自己数据微调ChatGLM2模型训练

GPT实战系列-ChatGLM2部署Ubuntu+Cuda11+显存24G实战方案

GPT实战系列-Baichuan2等大模型的计算精度与量化

GPT实战系列-GPT训练的Pretraining，SFT，Reward Modeling，RLHF

GPT实战系列-探究GPT等大模型的文本生成-CSDN博客

Alex_StarSky

关注

37
点赞
踩
20

收藏

觉得还不错? 一键收藏
打赏
1
评论
深度学习-解读GoogleNet深度学习网络

深度学习中，经典网络引领一波又一波的技术革命，从LetNet到当前最火的GPT所用的Transformer，它们把AI技术不断推向高潮。2012年AlexNet大放异彩，它把深度学习技术引领第一个高峰，打开人们的视野。用pytorch构建CNN经典网络模型GoogleNet，又称为Inception V1 ，还可以用数据进行训练模型，得到一个优化的模型。
复制链接

扫一扫