Station B Liu Erden linear regression pytoch

---

Series articles ：

---

---

Linear regression Pytorch

import matplotlib.pyplot as plt
import  torch
x_data = torch.Tensor([[1.0, 2.0, 3.0]])
y_data = torch.Tensor([[2.0, 4.0, 6.0]])

class LinearModel(torch.nn.Module):
    #  Member method __init__  And  forward  Must be realized 
    def __init__(self):
        super(LinearModel, self).__init__()
        # 1,1, For weight weight And offset b Of size
        self.linear = torch.nn.Linear(3, 1)

    def forward(self, x):
        y_pred = self.linear(x)
        return  y_pred

model = LinearModel()
#  Loss function calculation one batch All in loss The average of 
criterion =  torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.0005)
loss_list = []
epoch_list = []
for epoch in range(200):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())
    loss_list.append(loss.item())
    epoch_list.append(epoch)
    #  The gradient will be backward Hourly accumulation , So in backward Must be reset before 
    optimizer.zero_grad()
    loss.backward()
    # update
    optimizer.step()

plt.plot(epoch_list, loss_list)
plt.xlabel("epoch")
plt.ylabel("loss")
plt.show()