models/cbam.py

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.fc = nn.Sequential(
            nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False),
            nn.ReLU(),
            nn.Conv2d(in_planes // ratio, in_planes, 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
        return self.sigmoid(out)


class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        padding = kernel_size // 2
        self.conv = 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.conv(x)
        return self.sigmoid(x)


class CBAM(nn.Module):
    def __init__(self, in_planes, ratio=16, kernel_size=7):
        super(CBAM, self).__init__()
        self.channel_attention = ChannelAttention(in_planes, ratio)
        self.spatial_attention = SpatialAttention(kernel_size)

    def forward(self, x):
        x = x * self.channel_attention(x)
        x = x * self.spatial_attention(x)
        return x