注意力机制

#注意力机制
#空间注意力机制
import torch
from torch import nn

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)  # 7,3     3,1
        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)


#通道注意力机制
import torch
from torch import nn

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)


if __name__ == '__main__':
    CA = ChannelAttention(32)
    data_in = torch.randn(8,32,300,300)
    data_out = CA(data_in)
    print(data_in.shape)  # torch.Size([8, 32, 300, 300])
    print(data_out.shape)  # torch.Size([8, 32, 1, 1])


# CBAM注意力机制
import torch
from torch import nn

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)  # 7,3     3,1
        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)
        result = out * self.sa(out)
        return result

# SE注意力机制:
from torch import nn
import torch

class SELayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SELayer, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=False),
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, 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.expand_as(x)
        # return x * y





if __name__ == '__main__':
    print('testing ChannelAttention'.center(100,'-'))
    torch.manual_seed(seed=20200910)
    CA = ChannelAttention(32)
    data_in = torch.randn(8,32,300,300)
    data_out = CA(data_in)
    print(data_in.shape)  # torch.Size([8, 32, 300, 300])
    print(data_out.shape)  # torch.Size([8, 32, 1, 1])

if __name__ == '__main__':
    print('testing SpatialAttention'.center(100,'-'))
    torch.manual_seed(seed=20200910)
    SA = SpatialAttention(7)
    data_in = torch.randn(8,32,300,300)
    data_out = SA(data_in)
    print(data_in.shape)  # torch.Size([8, 32, 300, 300])
    print(data_out.shape)  # torch.Size([8, 1, 300, 300])

if __name__ == '__main__':
    print('testing CBAM'.center(100,'-'))
    torch.manual_seed(seed=20200910)
    cbam = CBAM(32, 16, 7)
    data_in = torch.randn(8,32,300,300)
    data_out = cbam(data_in)
    print(data_in.shape)  # torch.Size([8, 32, 300, 300])
    print(data_out.shape)  # torch.Size([8, 1, 300, 300])

if __name__ == '__main__':
    print('testing seattention'.center(100,'-'))
    torch.manual_seed(seed=20200910)
    data_in = torch.randn(8,32,300,300)
    SE = SELayer(32) 
    data_out = SE(data_in)
    print(data_in.shape)  # torch.Size([8, 32, 300, 300])
    print(data_out.shape)  # torch.Size([8, 32, 300, 300])