pytorch（三）：快速法搭建神经网络

传统法搭建神经网络：

import torch
import torch.nn.functional as f


# 传统法搭建神经网络模型
class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)
        
    def forward(self, x):
        x = f.relu(self.hidden(x))
        y = self.predict(x)
        return y 
net1 = Net(1, 10, 1)
print(net1)

传统法搭建神经网络：print(net1)结果为：

Net(
  (hidden): Linear(in_features=1, out_features=10)
  (predict): Linear(in_features=10, out_features=1)
)

快速法搭建神经网络：

import torch
import torch.nn.functional as f


# 快速法搭建神经网络模型
net2 = torch.nn.Sequential(
    torch.nn.Linear(1, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 1),
)
print(net2)

快速法搭建神经网络：print(net2)结果为：

Sequential(
  (0): Linear(in_features=1, out_features=10)
  (1): ReLU()
  (2): Linear(in_features=10, out_features=1)
)

输出结果本质上是一致的