在resent50中加se模块

在ResNet50中加入SE模块的方法如下：

1. 定义SE模块的类，该类包含两个部分：squeeze和excitation。其中squeeze是全局平均池化层，excitation是两个全连接层。

import torch.nn as nn

class SEModule(nn.Module):
    def __init__(self, channels, reduction=16):
        super(SEModule, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc1 = nn.Linear(channels, channels // reduction, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.fc2 = nn.Linear(channels // reduction, channels, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        out = self.avg_pool(x)
        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)
        return x * out

2. 在ResNet50的基础上，加入SE模块。将SE模块添加在每个residual block的输出之前。

import torch.nn as nn
import torchvision.models as models

class ResNet50_SE(nn.Module):
    def __init__(self, num_classes=1000):
        super(ResNet50_SE, self).__init__()

        resnet50 = models.resnet50(pretrained=True)

        self.conv1 = resnet50.conv1
        self.bn1 = resnet50.bn1
        self.relu = resnet50.relu
        self.maxpool = resnet50.maxpool

        self.layer1 = resnet50.layer1
        self.layer2 = resnet50.layer2
        self.layer3 = resnet50.layer3
        self.layer4 = resnet50.layer4

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(2048, num_classes)

        self.se1 = SEModule(256)
        self.se2 = SEModule(512)
        self.se3 = SEModule(1024)
        self.se4 = SEModule(2048)

    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.se1(x)
        x = self.layer2(x)
        x = self.se2(x)
        x = self.layer3(x)
        x = self.se3(x)
        x = self.layer4(x)
        x = self.se4(x)

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

        return x

通过以上方法，在ResNet50中加入SE模块，可以提高模型的性能和精度。