接上面两篇（通道注意力、空间注意力）

CBAM 是通道注意力机制和空间注意力机制的结合。它先通过通道注意力模块关注不同通道的重要性，对特征图的通道进行加权；然后再通过空间注意力模块关注特征图中不同空间位置的重要性，对通道加权后的特征图在空间维度上进行加权，从而实现对特征图的更精细调整。

import torch
import torch.nn as nn

# 通道注意力模块
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)
        self.sigmoid = nn.Sigmoid()

    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 self.sigmoid(out)

# 空间注意力模块
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)
        self.sigmoid = nn.Sigmoid()

    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 self.sigmoid(x)

# CBAM模块
class CBAM(nn.Module):
    def __init__(self, in_planes):
        super(CBAM, self).__init__()
        self.ca = ChannelAttention(in_planes)
        self.sa = SpatialAttention()

    def forward(self, x):
        x = self.ca(x) * x
        x = self.sa(x) * x
        return x