Sequential¶
- class torch.nn.Sequential(*args: Module)[源代码][源代码]¶
- class torch.nn.Sequential(arg: OrderedDict[str, Module])
一个序列容器。
模块将按照它们在构造函数中传入的顺序添加到其中。或者,可以传入模块的
OrderedDict
。Sequential
的forward()
方法接受任何输入,并将其转发到它包含的第一个模块。然后,它为每个后续模块“链接”输出到输入,最终返回最后一个模块的输出。Sequential
相对于手动调用模块序列的价值在于,它允许将整个容器视为单个模块,这样对Sequential
执行转换将应用于它存储的每个模块(这些模块都是Sequential
的注册子模块)。Sequential
和torch.nn.ModuleList
之间有什么区别?ModuleList
正如其名称所示,它是一个用于存储Module
的列表!另一方面,Sequential
中的层以级联方式连接。示例
# 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()) ]))