教程Python代碼如下：

import torch

x = torch.tensor(1.0)

y = torch.tensor(2.0)

w = torch.tensor(1.0,requires_grad=True)

#前向傳播，forward pass and compute the loss

y_hat = w * x

loss = (y_hat - y)**2

print(loss)

#反向傳播，backward pass

loss.backward()

print(w.grad)

### update weights

### next forward and backward pass