用torch实现CBAM注意力机制

CBAM（Convolutional Block Attention Module）是一种用于图像分类和目标检测任务的注意力机制模块。下面是使用PyTorch实现CBAM注意力机制的示例代码：

import torch
import torch.nn as nn

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)

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)

class CBAM(nn.Module):
    def __init__(self, in_planes, ratio=16, kernel_size=7):
        super(CBAM, self).__init__()
        self.ca = ChannelAttention(in_planes, ratio)
        self.sa = SpatialAttention(kernel_size)
        
    def forward(self, x):
        out = self.ca(x) * x
        out = self.sa(out) * out
        return out

# 使用示例
model = nn.Sequential(
    nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1),
    CBAM(64),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    # ...
)