PyTorch nn.Sequential Explained

In PyTorch, nn.Sequential is a container used to build neural network models. It allows you to combine multiple layers in sequential order to construct a deep neural network.

The usage of nn.Sequential is as follows:

import torch.nn as nn

model = nn.Sequential(
    nn.Linear(input_size, hidden_size),  # 添加输入层
    nn.ReLU(),                           # 添加激活函数
    nn.Linear(hidden_size, output_size),  # 添加输出层
    nn.Sigmoid()                         # 添加激活函数
)

In the example above, nn.Sequential added four layers in order: a linear layer, a ReLU activation function, another linear layer, and a Sigmoid activation function. These layers will be applied to the input data in the order they were added to produce the final output.

One can use this nn.Sequential model by invoking model(x), where x represents the input data. The model will sequentially pass the input data through each added layer and generate the final output.