ECA-Net eca注意力机制应用于ResNet (附代码)

论文地址：https://arxiv.org/abs/1910.03151代码地址： https://github.com/BangguWu/ECANetECA-Net是一种深度卷积神经网络，它使用了一种称为“有效通道注意度”的注意力机制，以提高网络的性能。ECA-Net的主要贡献是提出了一种高效的通道注意力模块，可以在不增加计算成本的情况下提高网络的性能。该模块可以被集成到现有的卷积神经网络中，

无妄无望

1577人浏览 · 2023-10-23 16:11:46

无妄无望 · 2023-10-23 16:11:46 发布

论文地址：https://arxiv.org/abs/1910.03151

代码地址： https://github.com/BangguWu/ECANet

1.是什么？

ECA-Net是一种深度卷积神经网络，它使用了一种称为“有效通道注意度”的注意力机制，以提高网络的性能。ECA-Net的主要贡献是提出了一种高效的通道注意力模块，可以在不增加计算成本的情况下提高网络的性能。该模块可以被集成到现有的卷积神经网络中，以提高它们的性能。ECA-Net已经在多个计算机视觉任务中取得了优异的表现，例如图像分类、目标检测和语义分割等。

2.为什么？

ECA-Net的作者认为：SE-Net对通道注意力机制的预测带来了副作用，捕获所有通道的依赖关系是低效并且是不必要的。在ECA-Net的论文中，作者认为：卷积具有良好的跨通道信息获取能力。

ECA模块的思想是非常简单的，它去除了原来SE模块中的全连接层，直接在全局平均池化之后的特征上通过一个1D卷积进行学习。既然用到了1D卷积，那么1D卷积的卷积核大小的选择就变得非常重要了，了解过卷积原理的同学很快就可以明白，1D卷积的卷积核大小会影响注意力机制每个权重的计算要考虑的通道数量，用更专业的名词就是跨通道交互的覆盖率。

3.怎么样？

3.1 网络结构

特点：
（1）通过大小为 k 的快速一维卷积实现，其中核大小k表示 局部跨通道交互 的覆盖范围，即有多少领域参与了一个通道的注意预测；
（2）为了避免通过交叉验证手动调整 k，开发了一种 自适应方法 确定 k，其中跨通道交互的覆盖范围 (即核大小k) 与通道维度成比例；

3.2 框图

3.3 代码实现

eca_module.py

import torch
from torch import nn
from torch.nn.parameter import Parameter
 
class eca_layer(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(eca_layer, 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)

eca_resnet.py

import torch.nn as nn
import math
# import torch.utils.model_zoo as model_zoo
from eca_module import eca_layer
 
 
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)
 
 
class ECABasicBlock(nn.Module):
    expansion = 1
 
    def __init__(self, inplanes, planes, stride=1, downsample=None, k_size=3):
        super(ECABasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes, 1)
        self.bn2 = nn.BatchNorm2d(planes)
        self.eca = eca_layer(planes, k_size)
        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.eca(out)
 
        if self.downsample is not None:
            residual = self.downsample(x)
 
        out += residual
        out = self.relu(out)
 
        return out
 
 
class ECABottleneck(nn.Module):
    expansion = 4
 
    def __init__(self, inplanes, planes, stride=1, downsample=None, k_size=3):
        super(ECABottleneck, 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)
        self.eca = eca_layer(planes * 4, k_size)
        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)
        out = self.eca(out)
 
        if self.downsample is not None:
            residual = self.downsample(x)
 
        out += residual
        out = self.relu(out)
 
        return out
 
 
class ResNet(nn.Module):
 
    def __init__(self, block, layers, num_classes=1000, k_size=[3, 3, 3, 3]):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0], int(k_size[0]))
        self.layer2 = self._make_layer(block, 128, layers[1], int(k_size[1]), stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], int(k_size[2]), stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], int(k_size[3]), stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)
 
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
 
    def _make_layer(self, block, planes, blocks, k_size, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )
 
        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample, k_size))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, k_size=k_size))
 
        return nn.Sequential(*layers)
 
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)
 
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
 
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
 
        return x
 
 
def eca_resnet18(k_size=[3, 3, 3, 3], num_classes=1_000, pretrained=False):
    """Constructs a ResNet-18 model.
    Args:
        k_size: Adaptive selection of kernel size
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        num_classes:The classes of classification
    """
    model = ResNet(ECABasicBlock, [2, 2, 2, 2], num_classes=num_classes, k_size=k_size)
    model.avgpool = nn.AdaptiveAvgPool2d(1)
    return model
 
 
def eca_resnet34(k_size=[3, 3, 3, 3], num_classes=1_000, pretrained=False):
    """Constructs a ResNet-34 model.
    Args:
        k_size: Adaptive selection of kernel size
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        num_classes:The classes of classification
    """
    model = ResNet(ECABasicBlock, [3, 4, 6, 3], num_classes=num_classes, k_size=k_size)
    model.avgpool = nn.AdaptiveAvgPool2d(1)
    return model
 
 
def eca_resnet50(k_size=[3, 3, 3, 3], num_classes=1000, pretrained=False):
    """Constructs a ResNet-50 model.
    Args:
        k_size: Adaptive selection of kernel size
        num_classes:The classes of classification
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    print("Constructing eca_resnet50......")
    model = ResNet(ECABottleneck, [3, 4, 6, 3], num_classes=num_classes, k_size=k_size)
    model.avgpool = nn.AdaptiveAvgPool2d(1)
    return model
 
 
def eca_resnet101(k_size=[3, 3, 3, 3], num_classes=1_000, pretrained=False):
    """Constructs a ResNet-101 model.
    Args:
        k_size: Adaptive selection of kernel size
        num_classes:The classes of classification
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(ECABottleneck, [3, 4, 23, 3], num_classes=num_classes, k_size=k_size)
    model.avgpool = nn.AdaptiveAvgPool2d(1)
    return model
 
 
def eca_resnet152(k_size=[3, 3, 3, 3], num_classes=1_000, pretrained=False):
    """Constructs a ResNet-152 model.
    Args:
        k_size: Adaptive selection of kernel size
        num_classes:The classes of classification
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(ECABottleneck, [3, 8, 36, 3], num_classes=num_classes, k_size=k_size)
    model.avgpool = nn.AdaptiveAvgPool2d(1)
    return model

参考：

【pytorch】ECA-NET注意力机制应用于ResNet的代码实现