whitebox_wm/models/googlenet.py

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


# 定义GoogLeNet模型
class InceptionModule(nn.Module):
    def __init__(self, in_channels, out1, out2_in, out2, out3_in, out3, out4):
        super(InceptionModule, self).__init__()
        self.branch1 = nn.Sequential(
            nn.Conv2d(in_channels, out1, kernel_size=1),
        )
        self.branch2 = nn.Sequential(
            nn.Conv2d(in_channels, out2_in, kernel_size=1),
            nn.Conv2d(out2_in, out2, kernel_size=3, padding=1),
        )
        self.branch3 = nn.Sequential(
            nn.Conv2d(in_channels, out3_in, kernel_size=1),
            nn.Conv2d(out3_in, out3, kernel_size=5, padding=2),
        )
        self.branch4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels, out4, kernel_size=1),
        )

    def forward(self, x):
        out1 = self.branch1(x)
        out2 = self.branch2(x)
        out3 = self.branch3(x)
        out4 = self.branch4(x)
        return torch.cat([out1, out2, out3, out4], 1)


class GoogLeNet(nn.Module):
    def __init__(self, num_classes=10):
        super(GoogLeNet, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 192, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
        )
        self.inception3a = InceptionModule(192, 64, 96, 128, 16, 32, 32)
        self.inception3b = InceptionModule(256, 128, 128, 192, 32, 96, 64)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.inception4a = InceptionModule(480, 192, 96, 208, 16, 48, 64)
        self.inception4b = InceptionModule(512, 160, 112, 224, 24, 64, 64)
        self.inception4c = InceptionModule(512, 128, 128, 256, 24, 64, 64)
        self.inception4d = InceptionModule(512, 112, 144, 288, 32, 64, 64)
        self.inception4e = InceptionModule(528, 256, 160, 320, 32, 128, 128)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.inception5a = InceptionModule(832, 256, 160, 320, 32, 128, 128)
        self.inception5b = InceptionModule(832, 384, 192, 384, 48, 128, 128)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.dropout = nn.Dropout(0.4)
        self.fc = nn.Linear(1024, num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.inception3a(x)
        x = self.inception3b(x)
        x = self.maxpool(x)
        x = self.inception4a(x)
        x = self.inception4b(x)
        x = self.inception4c(x)
        x = self.inception4d(x)
        x = self.inception4e(x)
        x = self.maxpool(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