通道注意力+像素注意力 pytorch实现

Squeeze-and-Excitation Networks

import torch
from torch import nn


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)

if __name__ == "__main__":
    model =  SELayer(64)
    B,C,H ,W = 2,64,4,4
    x = torch.randn(B,C,H,W)
    res = model(x)

import torch
from torch import nn


class ECALayer(nn.Module):
    """Constructs a ECA module.
    Args:
        channel: Number of channels of the input feature map
        k_size: Adaptive selection of kernel size
    """
    def __init__(self, channel, k_size=3):
        super(ECALayer, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # feature descriptor on the 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)

if __name__ == "__main__":
    model =  ECALayer(64)
    B,C,H ,W = 2,64,4,4
    x = torch.randn(B,C,H,W)
    res = model(x)

• 全局池化的实现：将nn.AdaptiveAvgPool2d()的参数值设置为1，即输出1×1大小的数值

https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool2d.html?highlight=adaptiveavgpool2d#torch.nn.AdaptiveAvgPool2d
# target output size of 5x7
m = nn.AdaptiveAvgPool2d((5,7))
input = torch.randn(1, 64, 8, 9)
output = m(input)
# target output size of 7x7 (square)
m = nn.AdaptiveAvgPool2d(7)
input = torch.randn(1, 64, 10, 9)
output = m(input)
# target output size of 10x7
m = nn.AdaptiveAvgPool2d((None, 7))
input = torch.randn(1, 64, 10, 9)
output = m(input)

CBAM

https://github.com/luuuyi/CBAM.PyTorch/blob/master/model/resnet_cbam.py
out = self.ca(out) * out
out = self.sa(out) * out

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 // 16, 1, bias=False),
                               nn.ReLU(),
                               nn.Conv2d(in_planes // 16, 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__()

        self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=kernel_size//2, 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)

参考与更多

CBAM

Squeeze-and-Excitation Networks

从pytorch代码讲讲通道注意力SENet和ECANet