动手深度学习（李沐）笔记

 #1. 导入相关模块

    
 !pip install d2l
    
 !pip install matplotlib_inline
    
 %matplotlib inline
    
 import random
    
 import torch
    
 from d2l import torch as d2l
    
  
    
 # 2. 生成数据集
    
 '''X为（x11,x12）,y为y1'''
    
 def synthetic_data(w,b,num_examples):
    
     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)) #保证y为一列
    
 true_w = torch.tensor([2,-3.4])
    
 true_b = 4.2
    
 features,labels = synthetic_data(true_w,true_b,1000)
    
  
    
 print('features:',features[0],'\nlabels:',labels[0])
    
  
    
 d2l.set_figsize()
    
 d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
    
  
    
 # 3. 读取数据集
    
 def data_iter(batch_size, features, labels):
    
     num_examples = len(features)
    
     indices = list(range(num_examples))
    
     # 这些样本是随机读取的，没有特定的顺序
    
     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
    
  
    
 # 4. 初始化模型参数
    
 w = torch.normal(0,0.01,size=(2,1),requires_grad=True)
    
 b = torch.zeros(1,requires_grad=True)
    
  
    
 # 5. 定义线性回归模型
    
 def linreg(X,w,b):
    
     return torch.matmul(X,w)+b
    
  
    
 # 6. 定义损失函数
    
 def squared_loss(y_hat,y,batch_size):
    
     return (y_hat-y.reshape(y_hat.shape))**2/(2*batch_size)
    
  
    
 # 7. 小批量梯度下降优化算法
    
 def sgd(params,lr):
    
     with torch.no_grad():
    
     for param in params:
    
         param -= lr*param.grad
    
         param.grad.zero_()
    
 # 8.训练
    
 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,batch_size)
    
     l.sum().backward()
    
     sgd([w,b],lr)
    
     with torch.no_grad():
    
     train_l = loss(net(features,w,b),labels,batch_size)
    
     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}')
    
    
    
    
    AI写代码

 # 1.导入包

    
 import numpy as np
    
 import torch
    
 from torch.utils import data
    
 from d2l import torch as d2l
    
  
    
 # 2. 生成数据集
    
 '''X为（x11,x12）,y为y1'''
    
 def synthetic_data(w,b,num_examples):
    
     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)) #保证y为一列
    
 true_w = torch.tensor([2, -3.4])
    
 true_b = 4.2
    
 features, labels = d2l.synthetic_data(true_w, true_b, 1000)
    
  
    
 # 3. 读取数据集
    
 def load_array(data_arrays, batch_size, is_train=True): 
    
     """构造一个PyTorch数据迭代器，
    
     is_train表示是否希望数据迭代器对象在每个迭代周期内打乱数据"""
    
     dataset = data.TensorDataset(*data_arrays)
    
     return data.DataLoader(dataset, batch_size, shuffle=is_train)
    
  
    
 batch_size = 10
    
 data_iter = load_array((features, labels), batch_size)
    
 next(iter(data_iter))
    
  
    
 # 4. 定义模型
    
 # nn是神经网络的缩写
    
 from torch import nn
    
  
    
 net = nn.Sequential(nn.Linear(2, 1))
    
  
    
 # 5. 初始化模型参数
    
 net[0].weight.data.normal_(0, 0.01)
    
 net[0].bias.data.fill_(0)
    
  
    
 # 6. 定义损失函数
    
 loss = nn.MSELoss()
    
  
    
 # 7. 定义优化算法
    
 trainer = torch.optim.SGD(net.parameters(), lr=0.03)
    
  
    
 # 8. 训练
    
 num_epochs = 3
    
 for epoch in range(num_epochs):
    
     for X, y in data_iter:
    
     l = loss(net(X) ,y)
    
     trainer.zero_grad()
    
     l.backward()
    
     trainer.step()
    
     l = loss(net(features), labels)
    
     print(f'epoch {epoch + 1}, loss {l:f}')
    
  
    
 w = net[0].weight.data
    
 print('w的估计误差：', true_w - w.reshape(true_w.shape))
    
 b = net[0].bias.data
    
 print('b的估计误差：', true_b - b)
    
    
    
    
    AI写代码