10-Sequential的使用

SEQUENTIAL

• CLASStorch.nn.Sequential(*args: Module)[SOURCE]

• CLASStorch.nn.Sequential(arg: OrderedDict[str, Module])

A sequential container. Modules will be added to it in the order they are passed in the constructor. Alternatively, an OrderedDict of modules can be passed in. The forward() method of Sequential accepts any input and forwards it to the first module it contains. It then “chains” outputs to inputs sequentially for each subsequent module, finally returning the output of the last module.

The value a Sequential provides over manually calling a sequence of modules is that it allows treating the whole container as a single module, such that performing a transformation on the Sequential applies to each of the modules it stores (which are each a registered submodule of the Sequential).

What’s the difference between a Sequential and a torch.nn.ModuleList? A ModuleList is exactly what it sounds like–a list for storing Module s! On the other hand, the layers in a Sequential are connected in a cascading way.

Example:

# 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())
        ]))

CIFAR10 model structure

示例

import torch
from torch import nn
from torch.nn import Sequential
from torch.utils.tensorboard import SummaryWriter
​
​
class XiaoMo(nn.Module):
    def __init__(self):
        super(XiaoMo, self).__init__()
​
        # 注意此处在dilation=1的情况下，padding和stride是未知参数
        # 因为H_out和W_out是相当于已知的，而卷积之后的相关参数有明确的数学公式计算
        # 按道理来说，严格依照公式来计算的话，方程有很多组解
        # 但是因为padding不宜太大的原因，stride尽量从1开始向上枚举，以此推得padding的值
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2)
        self.maxpool1 = nn.MaxPool2d(kernel_size=2)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2)
        self.maxpool2 = nn.MaxPool2d(kernel_size=2)
        self.conv3 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2)
        self.maxpool3 = nn.MaxPool2d(2)
        self.flatten = nn.Flatten()  # 展平后长度= channel*H*W
        self.linear1 = nn.Linear(in_features=64 * 4 * 4, out_features=64)
        self.linear2 = nn.Linear(in_features=64, out_features=10)  # 此处的10意味着数据将分类成10个类别
​
        self.model1 = Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64 * 4 * 4, 64),
            nn.Linear(64, 10)
        )
​
    def forward(self, x):
        # x = self.conv1(x)
        # x = self.maxpool1(x)
        # x = self.conv2(x)
        # x = self.maxpool2(x)
        # x = self.conv3(x)
        # x = self.maxpool3(x)
        # x = self.flatten(x)
        # x = self.linear1(x)
        # x = self.linear2(x)
​
        x = self.model1(x)
​
        return x
​
xiaomo = XiaoMo()
print(xiaomo)
​
# 检测手写网络的正确性
# 未报错则大概率是没有问题的
input = torch.ones((64, 3, 32, 32))
output = xiaomo(input)
print(output.shape)  # torch.Size([64, 10])
​
writer = SummaryWriter("logs")
writer.add_graph(xiaomo,  input)  # 计算图
writer.close()

tensorboard中的演示