PyTorch实现一维线性回归模型

import numpy as np
import torch
import matplotlib.pyplot as plt
from torch import nn
from torch.nn import Linear
from torch.autograd import Variable

x_train = np.array([[3.3],[4.4],[5.5],[6.71],[6.93],[4.168],
                   [9.779],[6.182],[7.59],[2.167],[7.042],
                   [10.791],[5.313],[7.997],[3.11]],dtype=np.float32)

y_train = np.array([[1.7],[2.76],[2.09],[3.19],[1.694],[1.573],
                   [3.336],[2.596],[2.53],[1.221],[2.827],
                   [3.465],[1.65],[2.904],[1.31]],dtype=np.float32)

#将numpy.array转换成Tensor
x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)
 
#初始化模型
#model = nn.Linear(1,1)也可以
class LinearRegression(nn.Module):
    def __init__(self):
        super(LinearRegression, self).__init__()
        self.linear = Linear(1, 1)
    
    def forward(self, x) :
        out = self.linear(x)
        return out

model = LinearRegression()
    
print(list(model.parameters())) 

#定义损失和优化函数
criterion = nn.MSELoss()
optimizer =torch.optim.SGD(model.parameters(),lr = 1e-3)

#训练模型
num_epochs = 1000
for epoch in range(num_epochs):
    inputs = Variable(x_train)
    target = Variable(y_train)
    #forward
    out = model(inputs)
    loss = criterion(out,target)
    #backward
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
    if(epoch + 1) % 20 == 0:
        print('Epoch[{}/{}],loss:{:.6f}'.format(epoch+1,num_epochs,loss.item()))
        
#预测结果
model.eval() #将模型变成测试模式
predict = model(Variable(x_train))
predict = predict.data.numpy()
plt.plot(x_train.numpy(),y_train.numpy(),'ro',label='Orignal Data')
plt.plot(x_train.numpy(),predict,label='Fitting Line')
plt.show()