注意力机制结构在resnet中的应用方式

最新推荐文章于 2024-05-20 20:52:35 发布

枫呱呱

最新推荐文章于 2024-05-20 20:52:35 发布

阅读量8.6k

点赞数 10

分类专栏：注意力机制深度学习 pytorch 文章标签： pytorch 深度学习神经网络

本文链接：https://blog.csdn.net/qq_35275007/article/details/119252191

版权

深度学习同时被 3 个专栏收录

10 篇文章 4 订阅

订阅专栏

pytorch

3 篇文章 0 订阅

订阅专栏

注意力机制

2 篇文章 2 订阅

订阅专栏

import torch
import torch.nn as nn



#__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
#           'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
#           'wide_resnet50_2', 'wide_resnet101_2']
#
#
#model_urls = {
#    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
#    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
#    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
#    'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
#    'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
#    'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
#    'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
#    'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
#    'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
#}


'''****************CF的注意力机制结构---SimAM--无参数结构*******************'''
class simam_module(torch.nn.Module):
    def __init__(self, channels = None, e_lambda = 1e-4):
        super(simam_module, self).__init__()

        self.activaton = nn.Sigmoid()
        self.e_lambda = e_lambda

    def __repr__(self):
        s = self.__class__.__name__ + '('
        s += ('lambda=%f)' % self.e_lambda)
        return s

    @staticmethod
    def get_module_name():
        return "simam"

    def forward(self, x):

        b, c, h, w = x.size()
        
        n = w * h - 1

        x_minus_mu_square = (x - x.mean(dim=[2,3], keepdim=True)).pow(2)
        y = x_minus_mu_square / (4 * (x_minus_mu_square.sum(dim=[2,3], keepdim=True) / n + self.e_lambda)) + 0.5

        return x * self.activaton(y)


'''****************CF的注意力机制结构---SE******************* '''
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)


'''****************CF的注意力机制结构---CA******************* '''
class h_sigmoid(nn.Module):
    def __init__(self, inplace=True):
        super(h_sigmoid, self).__init__()
        self.relu = nn.ReLU6(inplace=inplace)

    def forward(self, x):
        return self.relu(x + 3) / 6

class h_swish(nn.Module):
    def __init__(self, inplace=True):
        super(h_swish, self).__init__()
        self.sigmoid = h_sigmoid(inplace=inplace)

    def forward(self, x):
        return x * self.sigmoid(x)

class CoordAtt(nn.Module):
    def __init__(self, inp, oup, reduction=32):
        super(CoordAtt, self).__init__()
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        self.pool_w = nn.AdaptiveAvgPool2d((1, None))

        mip = max(8, inp // reduction)

        self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(mip)
        self.act = h_swish()
        
        self.conv_h = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
        self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
        

    def forward(self, x):
        identity = x
        
        n,c,h,w = x.size()
        x_h = self.pool_h(x)
        x_w = self.pool_w(x).permute(0, 1, 3, 2)

        y = torch.cat([x_h, x_w], dim=2)
        y = self.conv1(y)
        y = self.bn1(y)
        y = self.act(y) 
        
        x_h, x_w = torch.split(y, [h, w], dim=2)
        x_w = x_w.permute(0, 1, 3, 2)

        a_h = self.conv_h(x_h).sigmoid()
        a_w = self.conv_w(x_w).sigmoid()

        out = identity * a_w * a_h

        return out
'''*******************************************************************************'''



def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=dilation, groups=groups, bias=False, dilation=dilation)


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, groups=1,
                 base_width=64, dilation=1, norm_layer=None, attention_module=None):
        super(BasicBlock, self).__init__()
        self.attention_module = attention_module
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride
        self.se = SELayer(planes, 16)
        self.ca = CoordAtt(planes,planes)
        self.simam = simam_module(planes)
        
        if attention_module == "simam":
            self.conv2 = nn.Sequential(
                    self.conv2,
                    self.simam
                    )
        elif attention_module == "se":
            self.bn2 = nn.Sequential(
                    self.bn2, 
                    self.se
                    )
        elif attention_module == "ca":
            self.bn2 = nn.Sequential(
                    self.bn2, 
                    self.ca
                    )        
        
    def forward(self, x):
        identity = x

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

        out = self.conv2(out)
#        if self.attention_module == "simam":
#            out = self.simam(out)
        out = self.bn2(out)
        
        if self.downsample is not None:
            identity = self.downsample(x)

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

        return out


class Bottleneck(nn.Module):
    # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
    # while original implementation places the stride at the first 1x1 convolution(self.conv1)
    # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
    # This variant is also known as ResNet V1.5 and improves accuracy according to
    # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.

    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None, attention_module=None):
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.)) * groups
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride
        self.se = SELayer(planes, 16)
        self.ca = CoordAtt(planes,planes)
        self.simam = simam_module(planes)
        
        if attention_module == "simam":
            self.conv2 = nn.Sequential(
                    self.conv2,
                    self.simam
                    )
        elif attention_module == "se":
            self.bn3 = nn.Sequential(
                    self.bn3, 
                    self.se
                    )
        elif attention_module == "ca":
            self.bn3 = nn.Sequential(
                    self.bn3, 
                    self.ca
                    )  

    def forward(self, x):
        identity = 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:
            identity = self.downsample(x)

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

        return out

这里可以注意到三个注意力机制结构，均由三个类构成，直接嵌入到BasicBlock 或者 Bottleneck中，不同的是：“simam”是加到 conv2 后面，而 “se” 和 “ca” 是加到 bn2 或 bn3 后面

枫呱呱

关注

10
点赞
踩
116

收藏

觉得还不错? 一键收藏
打赏
11
评论
注意力机制结构在resnet中的应用方式

import torchimport torch.nn as nn#__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',# 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',# 'wide_resnet50_2', 'wide_resnet101_2']###model_urls = {# 'resne.
复制链接

扫一扫