%matplotlib inline
import random
import torch
from d2l import torch as d2l
def synthetic_data(w,b,num_examples):
"""生成 y=Xw+b+噪声。"""
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)
print('features:',features[0],'\nabel',labels[0])
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
1) torch.normal(0,1,(num_examples,len(w)))
:该函数原型为:normal(mean, std, *, generator=None, out=None)
,该函数返回从单独的正态分布中提取的随机数的张量,该正态分布的均值是mean,标准差是std。
2)torch.matmul
是tensor的乘法,输入可以是高维的。
3)d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
:画散点图,1是散点的大小
def data_iter(batch_size,featrues,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)])
yield features[batch_indices],labels[batch_indices]
batch_size=10
for X,y in data_iter(batch_size,features,labels):
print(X,'\n',y)
break
代码分析
1)range(num)
返回一个[0,num)的列表,然而在python3中返回的不再是一个list而是一个range对象,list(range(num_examples))
返回一个list。
```python
w=torch.normal(0,0.01,size=(2,1),requires_grad=True)
b=torch.zeros(1,requires_grad=True)
def linreg(X,w,b):
"""线性回归模型"""
return torch.matmul(X,w)+b
#定义损失函数
def squared_loss(y_hat,y):
"""均方损失"""
return (y_hat-y.reshape(y_hat.shape))**2/2
#定义优化算法
def sgd(params,lr,batch_size):
"""小批量随机梯度下降"""
with torch.no_grad():
for param in params:
param-=lr*param.grad/batch_size
param.grad.zero_()
#训练过程
lr=0.03
num_epochs=3
net=linreg
loss=squared_loss
for epoch in range(num_epochs):
for X,y in data_iter(batch_size,features,labels):
l=loss(net(X,w,b),y)
l.sum().backward()
sgd([w,b],lr,batch_size)
with torch.no_grad():
train_l=loss(net(features,w,b),labels)
print(f'epoch{epoch+1},loss{float(train_l.mean()):f}')
print(f'w的估计误差:{true_w-w.reshape(true_w.shape)}')
print(f'b的估计误差:{true_b-b}')