本篇博客主要介绍如何在PyTorch中更加快速便捷地搭建神经网络。

示例代码：

import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt

# 生成假数据
n_data = torch.ones(100, 2)
x0 = torch.normal(2*n_data, 1)      # class0 x data (tensor), shape=(100, 2)
y0 = torch.zeros(100)               # class0 y data (tensor), shape=(100, 1)
x1 = torch.normal(-2*n_data, 1)     # class1 x data (tensor), shape=(100, 2)
y1 = torch.ones(100)                # class1 y data (tensor), shape=(100, 1)
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # shape (200, 2) FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # shape (200,) LongTensor = 64-bit integer

# 将Tensor转换为torch
x, y = Variable(x), Variable(y)

# 打印数据散点图
# plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0, cmap='RdYlGn')
# plt.show()


# method 1
class Net(torch.nn.Module):
    # 初始化
    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)

    # 前向传递
    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x


net = Net(2, 10, 2)
# 输出定义的网络的结构
print(net)

# method2
net2 = torch.nn.Sequential(
    torch.nn.Linear(2, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 2),

)

print(net2)

运行结果：

Net (
  (hidden): Linear (2 -> 10)
  (predict): Linear (10 -> 2)
)
Sequential (
  (0): Linear (2 -> 10)
  (1): ReLU ()
  (2): Linear (10 -> 2)
)

其中，相比于Method1，Method2的搭建方法更为快速便捷，且具有与Method1相同的功能。