SENet构建识别图片模型代码

SENet是一种用于图像分类的深度学习模型，它在卷积神经网络中引入了一种新的机制，即“Squeeze-and-Excitation”（简称SE）模块，可以自适应地调整特征图的通道权重，从而增强模型的表征能力。下面是SENet的代码实现（以PyTorch为例）：

import torch
import torch.nn as nn

class SEModule(nn.Module):
    def __init__(self, channels, reduction):
        super(SEModule, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc1 = nn.Conv2d(channels, channels // reduction, kernel_size=1, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.fc2 = nn.Conv2d(channels // reduction, channels, kernel_size=1, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c, 1, 1)
        y = self.fc1(y)
        y = self.relu(y)
        y = self.fc2(y)
        y = self.sigmoid(y)
        return x * y

class SEBasicBlock(nn.Module):
    def __init__(self, inplanes, planes, reduction=16, stride=1, downsample=None):
        super(SEBasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.se_module = SEModule(planes, reduction)
        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.se_module(out)

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

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

        return out

class SENet(nn.Module):
    def __init__(self, block, layers, num_classes=1000, reduction=16):
        super(SENet, self).__init__()
        self.inplanes = 64
        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], reduction)
        self.layer2 = self._make_layer(block, 128, layers[1], reduction, stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], reduction, stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], reduction, stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(self, block, planes, blocks, reduction, 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, reduction, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, reduction))

        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

以上代码实现了SENet的SE模块和SEBasicBlock模块，以及整个SENet模型。其中，SEModule模块是SENet中的核心部分，用于自适应地调整特征图的通道权重；SEBasicBlock模块则是SENet的基本组成单元，由卷积层、BN层、ReLU层、SE模块和残差连接组成；SENet模型则是由多个SEBasicBlock模块组成的深度卷积神经网络。