注意力机制（Attention Mechanism）源于对人类视觉的研究。在认知科学中，由于信息处理的瓶颈，人类会选择性地关注所有信息的一部分，同时忽略其他可见的信息。上述机制通常被称为注意力机制。人类视网膜不同的部位具有不同程度的信息处理能力，即敏锐度（Acuity），只有视网膜中央凹部位具有最强的敏锐度。为了合理利用有限的视觉信息处理资源，人类需要选择视觉区域中的特定部分，然后集中关注它。例如，人们在阅读时，通常只有少量要被读取的词会被关注和处理。综上，注意力机制主要有两个方面：决定需要关注输入的哪部分；分配有限的信息处理资源给重要的部分。来至某度百科。

attention在视觉任务中有很多应用场景，每年顶会也有很多关于attention的paper。记录一下往backbone里加attention，不喜勿喷。以resnet为例，其他backbone也可以借鉴一下怎么添加attention。废话少说，直接上代码

import torch.nn as nn
import math

import torch

#3x3卷积会改变feature map 大小（当stride不等于1时），反之
def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)

#conv1x1只改变了输出的通道数
def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution """
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride,
                      bias=False)



class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        #第一个conv3x3的stride是可变的，当取2的时候，会导致特征图的size变成二分之一
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        #第二个conv3x3的stride=1,只可以改变通道数，不会改变特征图的大小。
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

        if planes == 64:
            self.globalAvgPool = nn.AvgPool2d(56, stride=1)
        elif planes == 128:
            self.globalAvgPool = nn.AvgPool2d(28, stride=1)
        elif planes == 256:
            self.globalAvgPool = nn.AvgPool2d(14, stride=1)
        elif planes == 512:
            self.globalAvgPool = nn.AvgPool2d(7, stride=1)
        self.fc1 = nn.Linear(in_features=planes, out_features=round(planes / 16))
        self.fc2 = nn.Linear(in_features=round(planes / 16), out_features=planes)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        original_out = out
        out = self.globalAvgPool(out)
        out = out.view(out.size(0), -1)
        out = self.fc1(out)
        out = self.relu(out)
        out = self.fc2(out)
        out = self.sigmoid(out)
        out = out.view(out.size(0), out.size(1), 1, 1)
        out = out * original_out

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        if planes == 64:
            self.globalAvgPool = nn.AvgPool2d(56, stride=1)
        elif planes == 128:
            self.globalAvgPool = nn.AvgPool2d(28, stride=1)
        elif planes == 256:
            self.globalAvgPool = nn.AvgPool2d(14, stride=1)
        elif planes == 512:
            self.globalAvgPool = nn.AvgPool2d(7, stride=1)
        self.fc1 = nn.Linear(in_features=planes * 4, out_features=round(planes / 4))
        self.fc2 = nn.Linear(in_features=round(planes / 4), out_features=planes * 4)
        self.sigmoid = nn.Sigmoid()
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        original_out = out
        out = self.globalAvgPool(out)
        out = out.view(out.size(0), -1)
        out = self.fc1(out)
        out = self.relu(out)
        out = self.fc2(out)
        out = self.sigmoid(out)
        out = out.view(out.size(0),out.size(1),1,1)
        out = out * original_out

        out += residual
        out = self.relu(out)

        return out
# 通道注意力机制
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 // 16, 1, bias=False)
        self.relu1 = nn.ReLU()
        self.fc2 = nn.Conv2d(in_planes // 16, 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)


# 空间注意力机制
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 ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
                 groups=1, width_per_group=64, replace_stride_with_dilation=None,
                 norm_layer=None):
        super(ResNet, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer

        self.inplanes = 64
        self.dilation = 1
        if replace_stride_with_dilation is None:
            # each element in the tuple indicates if we should replace
            # the 2x2 stride with a dilated convolution instead
            replace_stride_with_dilation = [False, False, False]
        if len(replace_stride_with_dilation) != 3:
            raise ValueError("replace_stride_with_dilation should be None "
                             "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
        self.groups = groups
        self.base_width = width_per_group
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = norm_layer(self.inplanes)
        self.relu = nn.ReLU(inplace=True)

        # 网络的第一层加入注意力机制
        self.ca = ChannelAttention(self.inplanes)
        self.sa = SpatialAttention()

        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
                                       dilate=replace_stride_with_dilation[0])
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
                                       dilate=replace_stride_with_dilation[1])
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
                                       dilate=replace_stride_with_dilation[2])
        # 网络的卷积层的最后一层加入注意力机制
        self.ca1 = ChannelAttention(self.inplanes)
        self.sa1 = SpatialAttention()

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)
#每个layer的生成函数_make_layer
    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        if dilate:
            self.dilation *= stride
            stride = 1
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                norm_layer(planes * block.expansion),
            )

        layers = []
        #参数block传入:BasicBlock还是BottleNeck作为基本模块
        layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
                            self.base_width, previous_dilation, norm_layer))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            #layer中剩余的block
            layers.append(block(self.inplanes, planes, groups=self.groups,
                                base_width=self.base_width, dilation=self.dilation,
                                norm_layer=norm_layer))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)

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

        x = self.maxpool(x)
#layer1-layer4又由若干层基本的block（BasicBlock或者BottleNeck）构成，其中block参决定是BasicBlock还是BottleNeck. layers是一个四维的列表，每个元素分别决定这四层分别包含多少个基本block
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.ca1(x) * x
        x = self.sa1(x) * x

        x = self.avgpool(x)
        x = x.reshape(x.size(0), -1)
        x = self.fc(x)

        return x