残差网络添加SE注意力机制

残差网络添加SE注意力机制的步骤如下：

1. 定义SE模块，它由两个全连接层组成，第一个全连接层将输入特征图压缩到一定的维度，第二个全连接层将其还原到原始维度，并进行sigmoid激活。

import torch.nn as nn

class SEModule(nn.Module):
    def __init__(self, channels, reduction):
        super(SEModule, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc1 = nn.Conv2d(channels, channels // reduction, kernel_size=1, padding=0)
        self.relu = nn.ReLU(inplace=True)
        self.fc2 = nn.Conv2d(channels // reduction, channels, kernel_size=1, padding=0)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        module_input = x
        x = self.avg_pool(x)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = self.sigmoid(x)
        return module_input * x

2. 在残差块的最后一层卷积层后面添加SE模块。

import torch.nn as nn

class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None, reduction=16):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample
        self.stride = stride
        self.se_module = SEModule(out_channels, reduction)

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out = self.se_module(out)  # 添加SE模块

        out += residual
        out = self.relu(out)

        return out

3. 在主干网络中使用ResidualBlock构建残差网络，并在需要的地方添加SE模块。

import torch.nn as nn

class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=1000, reduction=16):
        super(ResNet, self).__init__()
        self.in_channels = 64

        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self.make_layer(block, 64, layers[0], stride=1, reduction=reduction)
        self.layer2 = self.make_layer(block, 128, layers[1], stride=2, reduction=reduction)
        self.layer3 = self.make_layer(block, 256, layers[2], stride=2, reduction=reduction)
        self.layer4 = self.make_layer(block, 512, layers[3], stride=2, reduction=reduction)

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def make_layer(self, block, out_channels, blocks, stride=1, reduction=16):
        downsample = None
        if stride != 1 or self.in_channels != out_channels * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channels, out_channels * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * block.expansion),
            )

        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample, reduction=reduction))
        self.in_channels = out_channels * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.in_channels, out_channels, reduction=reduction))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x