Pytorch实现线性回归

import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random
#准备数据
x_data = torch.Tensor([[1.0],[2.0],[3.0]])
y_data = torch.Tensor([[2.0],[4.0],[6.0]])

#定义模型
class LinearModel(torch.nn.Module):
    #相当于构造函数
    def __init__(self):
        #调用父类的构造函数
        super(LinearModel,self).__init__()
        self.linear = torch.nn.Linear(1,1)
    #前向的计算
    def forward(self,x):
        y_pred = self.linear(x)
        return y_pred

model = LinearModel()
#定义损失函数和优化器
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
#训练
for epoch in range(1000):
    y_pred = model(x_data)
    loss = criterion(y_pred,y_data)
    print(epoch+1,loss.data)

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

#打印结果
print('w = ',model.linear.weight.item())
print('b = ',model.linear.bias.item())
#测试模型
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred = ',y_test.data)

训练1000次结果：