pytorch－－－线性回归实现

１．准备数据
２．定义模型
３．定义损失函数
４．定义优化方法
５．训练
超参数初始化
循环传入数据计算损失
梯度回传更新参数
评估训练结果

%matplotlib inline  
#可以直接画图
import random 
import torch
# from d2l import torch as d2l

#prepare the data
def synthetic_data(w, b, num_examples):
  """
  y = XW+b
  """
  x = torch.normal(0,1,(num_examples,len(w)))
  y = torch.matmul(x,w)+b
  y += torch.normal(0, 0.01, y.shape)

  return x, y.reshape((-1, 1))

true_w = torch.tensor([2, -3.4])
true_b = 4.2

features, labels = synthetic_data(true_w, true_b, 1000) 


# data iteration
def data_iter(batch_size, features, labels):
  num_examples = len(features)
  indices = list(range(num_examples))
  random.shuffle(indices)
  for i in range(0, num_examples, batch_size):
    batch_indices = torch.tensor(
        indices[i:min(i+batch_size, num_examples)]#最后一组可能会超过总的数量，所以就选取最后剩下的样本作为最后一组
    )
    yield features[batch_indices], labels[batch_indices]


# model
def linereg(x,w,b):
  return torch.matmul(x,w) + b



# loss 
def mse_loss(y_hat, y):
  return ((y_hat - y)**2) / 2

# sgd
def sgd(params, lr, batch_size):
  with torch.no_grad():
    for param in params:
      # print(id(param))
      #注意这里要原地操作，如果写成param = param -　的形式，param的地址就改变了，就不携带梯度了，所以会报错　AttributeError: 'NoneType' object has no attribute 'zero_'
      #param = param - lr * param.grad / batch_size
      # print(id(param))
      param -= lr * param.grad / batch_size
      param.grad.zero_()


# init the parameters
w = torch.normal(0, 0.01, size=(2, 1), requires_grad=True)
b = torch.zeros(1, requires_grad=True)

# train
num_epochs = 10
lr = 1
net = linereg
loss = mse_loss
batch_size = 10
for epoch in range(num_epochs):
  for x,y in data_iter(batch_size, features, labels):
    train_loss = loss(net(x,w,b), y)
    train_loss.sum().backward()#梯度回传
    # print(w.grad)
    sgd([w,b], lr, batch_size)
  # test
  with torch.no_grad():
    l = loss(net(features, w, b), labels)
    print(f'epoch {epoch+1}, loss{float(l.mean()):f}')


print("b loss", (true_b - b))
print("w_loss", (true_w - w.reshape(true_w.shape)))