怎么在resnet50加入cbam

要在ResNet-50中添加CBAM（Convolutional Block Attention Module），你需要对ResNet-50的基本结构进行修改。

首先，导入所需的库和模块：

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

接下来，定义CBAM模块的两个子模块：通道注意力模块（Channel Attention Module）和空间注意力模块（Spatial Attention Module）。

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        self.fc1 = nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False)
        self.relu1 = nn.ReLU()
        self.fc2 = nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False)
        
    def forward(self, x):
        avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
        max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
        out = avg_out + max_out
        return torch.sigmoid(out)


class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        
    def forward(self, x):
        avg_out = torch.mean(x, dim=1, keepdim=True)
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        x = torch.cat([avg_out, max_out], dim=1)
        x = self.conv1(x)
        return torch.sigmoid(x)

然后，定义包含CBAM模块的ResNet-50网络。

class CBAMResNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(CBAMResNet, self).__init__()
        self.in_planes = 64
        
        # ResNet-50 layers (without fully connected layers)
        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(64, 3)
        self.layer2 = self._make_layer(128, 4, stride=2)
        self.layer3 = self._make_layer(256, 6, stride=2)
        self.layer4 = self._make_layer(512, 3, stride=2)
        
        # CBAM attention modules
        self.channel_att = ChannelAttention(512)
        self.spatial_att = SpatialAttention()
        
        # Fully connected layer
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Linear(512, num_classes)
        
    def _make_layer(self, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.in_planes != planes * 4:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_planes, planes * 4, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * 4)
            )
        layers = []
        layers.append(Bottleneck(self.in_planes, planes, stride, downsample))
        self.in_planes = planes * 4
        for _ in range(1, blocks):
            layers.append(Bottleneck(self.in_planes, planes))
        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)
        
        # Apply CBAM attention modules
        x = self.channel_att(x) * x
        x = self.spatial_att(x) * 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