模块拼接|即插即用模块|CBAM|注意力机制

CBAM（ Convolutional Block Attention Module ）是一种轻量级注意力模块的提出于2018年，它可以在空间维度和通道维度上进行Attention操作。论文在Resnet和MobileNet上加入CBAM模块进行对比，并针对两个注意力模块应用的先后进行实验，同时进行CAM可视化，可以看到Attention更关注目标物体。

论文地址：MCANet: Medical Image Segmentation with Multi-Scale Cross-Axis Attention

代码地址：GitHub - haoshao-nku/medical_seg

import numpy as np
import torch
from torch import nn
from torch.nn import init


class ChannelAttention(nn.Module):
    """
    CBAM混合注意力机制的通道注意力
    """

    def __init__(self, in_channels, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)

        self.fc = nn.Sequential(
            # 利用1x1卷积代替全连接，避免输入必须尺度固定的问题，并减小计算量
            nn.Conv2d(in_channels, in_channels // ratio, 1, bias=False),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels // ratio, in_channels, 1, bias=False)
        )

        self.sigmoid = nn.Sigmoid()

   def forward(self, x):
       avg_out = self.fc(self.avg_pool(x))
       max_out = self.fc(self.max_pool(x))
       out = avg_out + max_out
       out = self.sigmoid(out)
       return out * x


class SpatialAttention(nn.Module):
    """
    CBAM混合注意力机制的空间注意力
    """

    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)
        out = torch.cat([avg_out, max_out], dim=1)
        out = self.sigmoid(self.conv1(out))
        return out * x


class CBAM(nn.Module):
    """
    CBAM混合注意力机制
    """

    def __init__(self, in_channels, ratio=16, kernel_size=3):
        super(CBAM, self).__init__()
        self.channelattention = ChannelAttention(in_channels, ratio=ratio)
        self.spatialattention = SpatialAttention(kernel_size=kernel_size)

    def forward(self, x):
        x = self.channelattention(x)
        x = self.spatialattention(x)
        return x