用python的pytorch框架实现GoogLeNet模型

好的，下面是使用 PyTorch 实现 GoogLeNet 模型的代码：

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

class Inception(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
        super(Inception, self).__init__()
        
        # 1x1 conv branch
        self.branch1 = nn.Sequential(
            nn.Conv2d(in_channels, ch1x1, kernel_size=1),
            nn.BatchNorm2d(ch1x1),
            nn.ReLU(inplace=True)
        )
        
        # 1x1 conv -> 3x3 conv branch
        self.branch2 = nn.Sequential(
            nn.Conv2d(in_channels, ch3x3red, kernel_size=1),
            nn.BatchNorm2d(ch3x3red),
            nn.ReLU(inplace=True),
            nn.Conv2d(ch3x3red, ch3x3, kernel_size=3, padding=1),
            nn.BatchNorm2d(ch3x3),
            nn.ReLU(inplace=True)
        )
        
        # 1x1 conv -> 5x5 conv branch
        self.branch3 = nn.Sequential(
            nn.Conv2d(in_channels, ch5x5red, kernel_size=1),
            nn.BatchNorm2d(ch5x5red),
            nn.ReLU(inplace=True),
            nn.Conv2d(ch5x5red, ch5x5, kernel_size=5, padding=2),
            nn.BatchNorm2d(ch5x5),
            nn.ReLU(inplace=True)
        )
        
        # 3x3 pool -> 1x1 conv branch
        self.branch4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels, pool_proj, kernel_size=1),
            nn.BatchNorm2d(pool_proj),
            nn.ReLU(inplace=True)
        )
        
    def forward(self, x):
        branch1 = self.branch1(x)
        branch2 = self.branch2(x)
        branch3 = self.branch3(x)
        branch4 = self.branch4(x)
        
        output = torch.cat([branch1, branch2, branch3, branch4], 1)
        return output


class GoogLeNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(GoogLeNet, self).__init__()
        
        # Base 1: 7x7 conv -> 3x3 max pool
        self.base1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        )
        
        # Base 2: 1x1 conv -> 3x3 conv -> 3x3 max pool
        self.base2 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=1),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 192, kernel_size=3, padding=1),
            nn.BatchNorm2d(192),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        )
        
        # Inception 3a - 5b
        self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
        self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
        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.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
        self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
        
        # Classification (avg pool -> dropout -> linear)
        self.avgpool = nn.AdaptiveAvgPool2d((1,1))
        self.dropout = nn.Dropout(p=0.4)
        self.fc = nn.Linear(1024, num_classes)
        
    def forward(self, x):
        x = self.base1(x)
        x = self.base2(x)
        x = self.inception3a(x)
        x = self.inception3b(x)
        x = self.inception4a(x)
        x = self.inception4b(x)
        x = self.inception4c(x)
        x = self.inception4d(x)
        x = self.inception4e(x)
        x = self.inception5a(x)
        x = self.inception5b(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.dropout(x)
        x = self.fc(x)
        return x

其中 `Inception` 类定义了 Inception 模块的结构，`GoogLeNet` 类定义了整个 GoogLeNet 模型的结构。在 `GoogLeNet` 类中，我们通过 `nn.Sequential` 和 `nn.ModuleList` 来定义了多个 Inception 模块，并在 `forward` 方法中按顺序执行这些模块。最后，我们通过 `nn.Linear` 定义了一个全连接层来进行分类。