import torch
import torch.nn.functional as F # 主要实现激活函数
import matplotlib.pyplot as plt # 绘图的工具
from torch.autograd import Variable

# 生成伪数据
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim = 1)
y = x.pow(2) + 0.2 * torch.rand(x.size())

# 变为Variable
x, y = Variable(x), Variable(y)

# 绘制数据图像
plt.scatter(x.data.numpy(), y.data.numpy())
plt.show()

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) # hidden layer
  self.predict = torch.nn.Linear(n_hidden, n_output) # output layer

 def forward(self, x):
  x = F.relu(self.hidden(x))  # activation function for hidden layer
  x = self.predict(x)    # linear output
  return x

net = Net(n_feature=1, n_hidden=10, n_output=1)  # define the network
print(net) # net architecture

Net (
 (hidden): Linear (1 -> 10)
 (predict): Linear (10 -> 1)
)

# 训练100次
for t in range(100):
 prediction = net(x)  # input x and predict based on x

 loss = loss_func(prediction, y)  # 一定要是输出在前，标签在后 (1. nn output, 2. target)

 optimizer.zero_grad() # clear gradients for next train
 loss.backward()   # backpropagation, compute gradients
 optimizer.step()  # apply gradients

plt.ion() # something about plotting

for t in range(100):
 ...

 if t % 5 == 0:
  # plot and show learning process
  plt.cla()
  plt.scatter(x.data.numpy(), y.data.numpy())
  plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
  plt.text(0.5, 0, 'Loss=%.4f' % loss.data[0], fontdict={'size': 20, 'color': 'red'})
  plt.pause(0.1)

plt.ioff()
plt.show()