PyTorch学習-単純回帰実装

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


x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  #     
y = x.pow(2) + 0.2 * torch.rand(x.size())
x, y = Variable(x), Variable(y)  #   Variable            
# 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)  #            
        self.predict = torch.nn.Linear(n_hidden, n_output)  #            

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


model = Net(n_feature=1, n_hidden=10, n_output=1)  #      
loss_func = torch.nn.MSELoss()  #       
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)  #       

plt.ion()
for t in range(1000):  #   1000 
    prediction = model(x)   # input x and predict based on x
    loss = loss_func(prediction, y)  # X   (x1, x2,...)，    (y1, y2,...)
    optimizer.zero_grad()  #      0
    loss.backward()  #         
    optimizer.step()  # apply gradients

    if t % 5 == 0:
        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()