pytorch代码实现模型加CBAM注意力模块

CBAM（Convolutional Block Attention Module）是一种用于卷积神经网络的注意力模块，可以增强模型的表达能力和准确性。下面是一个使用PyTorch实现的CBAM模块的示例代码：

import torch
import torch.nn as nn
import torch.nn.functional as F

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 = x * self.ca(x)
        return out * self.sa(out)

上述代码中，定义了一个CBAM类，包括了ChannelAttention模块和SpatialAttention模块。其中，ChannelAttention模块用于提取通道信息，SpatialAttention模块用于提取空间信息。在CBAM模块的forward()函数中，先使用ChannelAttention模块提取通道信息，然后再使用SpatialAttention模块提取空间信息。最后将两种信息结合起来得到最终输出。

使用该CBAM模块时，只需在需要使用注意力机制的卷积层后面添加一个CBAM实例即可。例如：

class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1)
        self.cbam1 = CBAM(64)
        self.conv2 = nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1)
        self.cbam2 = CBAM(128)

    def forward(self, x):
        x = self.conv1(x)
        x = self.cbam1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = self.cbam2(x)
        x = F.relu(x)
        return x