yolo_attention.py

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import torch
import torch.nn as nn
import math


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


# Channel Attention Mechanism
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)

        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)


# Spatial attention mechanism
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)


# CBAM注意力机制
class CBAM(nn.Module):
    def __init__(self, channel, ratio=8, kernel_size=7):
        super(CBAM, 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


# ECANet
class ECA(nn.Module):
    def __init__(self, channel, b=1, gamma=2, kernel_size=3):
        super(ECA, self).__init__()
        # https://github.com/BangguWu/ECANet/issues/24#issuecomment-664926242
        # The adaptive kernel is not easy to implement, so it is fixed 'kernel_size=3'
        # The kernel size cannot be confirmed correctly due to the input channel, which may cause errors
        # kernel_size = int(abs((math.log(channel, 2) + b) / gamma))
        # kernel_size = kernel_size if kernel_size % 2 else kernel_size + 1

        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv = nn.Conv1d(1, 1, kernel_size=kernel_size, padding=(kernel_size - 1) // 2, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # Feature of global spatial information
        y = self.avg_pool(x)
        # Two different branches of ECA module
        y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)
        # Multi-scale information fusion
        y = self.sigmoid(y)
        return x * y.expand_as(x)