CBAM注意力机制代码

最新推荐文章于 2024-05-20 20:52:35 发布

微光_

最新推荐文章于 2024-05-20 20:52:35 发布

阅读量507

点赞数

文章标签：深度学习 cnn 神经网络

本文链接：https://blog.csdn.net/hengshui_uzi_/article/details/130203789

版权

文章提供了CBAM（ChannelAttentionandSpatialAttentionModule）注意力机制在PyTorch中的实现代码，包括通道注意力和空间注意力模块，这些模块可以即插即用来增强卷积神经网络的性能。

摘要由CSDN通过智能技术生成

前言

CBAM注意力机制代码，即插即用，之前看的一个博主的，但是后来找不到了，在这里分享一下

代码

1.引入库

代码如下（示例）：

import torch
import torch.nn as nn
import math

2.读入数据

代码如下（示例）：

class Se_block(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, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y

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 ChannelAttention1(nn.Module):
    def __init__(self,channel,ratio=16):
        super(ChannelAttention1, self).__init__()
        self.avgpool=nn.AdaptiveAvgPool2d(1)
        self.maxpool=nn.AdaptiveMaxPool2d(1)

        self.fc=nn.Sequential(
            nn.Linear(channel,channel/ratio,bias=False),
            nn.ReLU(),
            nn.Linear(channel/ratio,channel,bias=False)
        )
        self.sigmiod=nn.Sigmoid()

    def forward(self,x):'''


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)

---