容器（Containter）

• 在Pytorch中提供的模型容器中，有三个常用的模型容器，nn.Sequential、nn.ModuleList、nn.ModuleDict
• 

1、nn.Sequential

• nn.Sequential是nn.Module的容器，用于按顺序包装一组网络层。
• 例如对LeNet网络的构建：

class LeNetSequential(nn.Module):
    def __init__(self, classes):
        super(LeNetSequential, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 6, 5),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(6, 16, 5),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2),)

        self.classifier = nn.Sequential(
            nn.Linear(16*5*5, 120),
            nn.ReLU(),
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84, classes),)

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size()[0], -1)
        x = self.classifier(x)
        return x

2、nn.ModuleList

• nn.ModuleList是nn.Module的模块，用于包装一组网络层，以迭代的方式调用网络层
• 
• 以迭代的方法构建一个深度为20的全连接网络

class ModuleList(nn.Module):
    def __init__(self):
        super(ModuleList, self).__init__()
        self.linears = nn.ModuleList([nn.Linear(10, 10) for i in range(20)])

    def forward(self, x):
        for i, linear in enumerate(self.linears):
            x = linear(x)
        return x

3、nn.ModuleDict

• nn.ModuleDict是nn.Module的容器，用于包装一组网络层，以索引的方式调用网络层
• 

class ModuleDict(nn.Module):
    def __init__(self):
        super(ModuleDict, self).__init__()
        self.choices = nn.ModuleDict({
            'conv': nn.Conv2d(10, 10, 3),
            'pool': nn.MaxPool2d(3)
        })

        self.activations = nn.ModuleDict({
            'relu': nn.ReLU(),
            'prelu': nn.PReLU()
        })

    def forward(self, x, choice, act):
        x = self.choices[choice](x)
        x = self.activations[act](x)
        return x


net = ModuleDict()

fake_img = torch.randn((4, 10, 32, 32))

output = net(fake_img, 'conv', 'relu')

print(output)

4、容器总结

5、Alex网络实例

class AlexNet(nn.Module):

    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x