Pytorch教程[04]torch.nn---Containers

一、模型创建步骤

二、构建模型两要素

三、torch.nn模块

nn.Module
• parameters : 存储管理nn.Parameter类
• modules : 存储管理nn.Module类
• buffers：存储管理缓冲属性，如BN层中的running_mean
• ***_hooks：存储管理钩子函数

self._parameters = OrderedDict()
self._buffers = OrderedDict()
self._backward_hooks = OrderedDict()
self._forward_hooks = OrderedDict()
self._forward_pre_hooks = OrderedDict()
self._state_dict_hooks = OrderedDict()
self._load_state_dict_pre_hooks = OrderedDict()
self._modules = OrderedDict()

例：

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

四、模型容器——Containers

4.1 nn.Sequential

nn.Sequential 是 nn.module的容器，用于按顺序包装一组网络层
• 顺序性：各网络层之间严格按照顺序构建
• 自带forward()：自带的forward里，通过for循环依次执行前向传播运算

# Using Sequential to create a small model. When `model` is run,
# input will first be passed to `Conv2d(1,20,5)`. The output of
# `Conv2d(1,20,5)` will be used as the input to the first
# `ReLU`; the output of the first `ReLU` will become the input
# for `Conv2d(20,64,5)`. Finally, the output of
# `Conv2d(20,64,5)` will be used as input to the second `ReLU`
model = nn.Sequential(
          nn.Conv2d(1,20,5),
          nn.ReLU(),
          nn.Conv2d(20,64,5),
          nn.ReLU()
        )

# Using Sequential with OrderedDict. This is functionally the
# same as the above code
model = nn.Sequential(OrderedDict([
          ('conv1', nn.Conv2d(1,20,5)),
          ('relu1', nn.ReLU()),
          ('conv2', nn.Conv2d(20,64,5)),
          ('relu2', nn.ReLU())
        ]))

4.2 nn.ModuleList

nn.ModuleList是 nn.module的容器，用于包装一组网络层，以迭代方式调用网络层主要方法：
• append()：在ModuleList后面添加网络层
• extend()：拼接两个ModuleList
• insert()：指定在ModuleList中位置插入网络层

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

    def forward(self, x):
        # ModuleList can act as an iterable, or be indexed using ints
        for i, l in enumerate(self.linears):
            x = self.linears[i // 2](x) + l(x)
        return x

4.3 nn.ModuleDict

nn.ModuleDict是 nn.module的容器，用于包装一组网络层，以索引方式调用网络层主要方法：
• clear()：清空ModuleDict
• items()：返回可迭代的键值对(key-value pairs)
• keys()：返回字典的键(key)
• values()：返回字典的值(value)
• pop()：返回一对键值，并从字典中删除

class MyModule(nn.Module):
    def __init__(self):
        super(MyModule, self).__init__()
        self.choices = nn.ModuleDict({
                'conv': nn.Conv2d(10, 10, 3),
                'pool': nn.MaxPool2d(3)
        })
        self.activations = nn.ModuleDict([
                ['lrelu', nn.LeakyReLU()],
                ['prelu', nn.PReLU()]
        ])

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

4.4 容器总结

• nn.Sequential：顺序性，各网络层之间严格按顺序执行，常用于block构建
• nn.ModuleList：迭代性，常用于大量重复网构建，通过for循环实现重复构建
• nn.ModuleDict：索引性，常用于可选择的网络层