SENet

1.模块介绍

Sequeeze-and-Excitation bloack (SENet) 并不是一个完整的网络结构，而是一个子模块，可以嵌到其他分类，分割或检测模型中。作者在文中做了将其嵌入到Resnet，VGG，Inception等网络模型当中，发现效果都有了一定的提升。

SENet的核心思想在于通过网络根据loss去学习特征权重，使得不同Channel中有效的feature map权重大，无效或效果小的feature map权重小的方式训练模型达到更好的结果。

2. 各个部分详细介绍

Squeeze:顺着空间维度进行特征压缩，并将每一个feature压缩成一个实数，所以这个实数某种程度上具有全局的感受野，并且输出的维度和输入的特征通道相匹配。
Excitation：基于特征通道之间的相关性，每个通道生成一个权重，用来表示这个通道的重要程度。
Reweight：将Excitation输出的权重看作是每个通道的重要性，然后直接加权（乘）到之前的完整的feature maps上，完成在通道维度上对原始特征的重要性加权标注。

设计细节：

1. Squeeze()中哪种池化方式好：全局平均池化
2. Excitation中reduction® 设置多少好 r = 16
   
3. Excitation中那种激活方式最好？==Sigmoid ==
4. 
   Code:

class SENet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(SENet, 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])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[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, 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))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        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