pytorch:回归

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

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)

#plt.scatter(x.data.numpy(),y.data.numpy())

class Net(torch.nn.Module):
    def __init__(self,n_feature,n_hidden,n_output):
        super(Net,self).__init__()#此为官方步骤
        self.hidden = torch.nn.Linear(n_feature,n_hidden)
        self.predict = torch.nn.Linear(n_hidden,n_output)
        pass
    def forward(self,x):#前向传播
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x


net = Net(1,10,1)#输入1个特征，隐藏层神经元10个，输出1个
print(net)

plt.ion()
plt.show()

optimizer = torch.optim.SGD(net.parameters(),lr=0.5)#优化参数,SGD为优化器
loss_func = torch.nn.MSELoss()#损失函数为均方差，处理回归问题

for t in range(100):  # 训练100次
    prediction = net(x)

    loss = loss_func(prediction, y)  # 预测值与真实值的误差，预测值一定写在前面

    optimizer.zero_grad()  # 求导前先将导数归零
    loss.backward()
    optimizer.step()

    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.item(), fontdict={'size': 20, 'color': 'red'})
        plt.pause(0.1)
plt.ioff()
plt.show()

视频链接：传送门
结果图：