注意力机制模块

1.SENet

SENet为通道注意力机制模块

实现方式：

1.首先对输入进来的特征层进行一个全局池化，将【b,c,h,w】 ->  【b,c,1,1】

2.对全局池化后的特征条进行两次全连接操作，第一次全连接操作生成一个较为短的特征条，之后用一个非线性的ReLU激活函数进行处理，第二次全连接层使特征长条恢复到输入的channel数，之后用Sigmoid激活函数让每个特征通道的权值固定在0-1之间

3.用获取的特征长条特征权值与原输入特征层进行乘积运算

 

代码参考

import torch
import torch.nn as nn
import math

class SEblock(nn.Module):
    def __init__(self, channel, ratio=16):
        super(SE_block, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
                nn.Linear(channel, channel // ratio, bias=False),
                nn.ReLU(inplace=True),
                nn.Linear(channel // ratio, channel, bias=False),
                nn.Sigmoid()
        )

    def forward(self, x):
        b, c, h, w = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y

SENet模块应用

 注：用两个Fully Connected层的优点

增加非线性，更好的拟合通道复杂的相关性

2.CBAM

CBAM将空间注意力与通道注意力进行结合。

 注：

空间注意力是在channel维度进行max与mean，通道注意力是在w,h维度上进行全局池化与平均

空间：【b,c,w,h】-> 【b,1,w,h】

通道：【b,c,w,h】->【b,c,1,1】

代码参考：

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=8):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)

        # 利用1x1卷积代替全连接
        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_block(nn.Module):
    def __init__(self, channel, ratio=8, kernel_size=7):
        super(cbam_block, self).__init__()
        self.channelattention = ChannelAttention(channel, ratio=ratio)
        self.spatialattention = SpatialAttention(kernel_size=kernel_size)

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

代码参考来自于https://blog.csdn.net/weixin_44791964/article/details/121371986