动手学深度学习PyTorch（二）：线性回归

%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

## 1.生成数据集

num_inputs = 2
num_examples = 1000
true_w = [2,-3.4]
true_b = 4.2
features = torch.randn(num_examples,num_inputs,dtype=torch.float32)
labels = true_w[0] * features[:,0] + true_w[1]*features[:,1] + true_b
labels += torch.tensor(np.random.normal(0,0.01,size=labels.size()),dtype=torch.float32)

def use_svg_display():
    # 用矢量图显示
    display.set_matplotlib_formats('svg')
    
def set_figsize(figsize=(8,6)):
    use_svg_display()
    # 设置图的尺寸
    plt.rcParams['figure.figsize'] = figsize

set_figsize()
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1)   

## 2.读取数据
def data_iter(batch_size,features,labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    random.shuffle(indices) # 样本的读取顺序是随机的
    for i in range(0,num_examples,batch_size):
        j = torch.LongTensor(indices[i:min(i+batch_size,num_examples)])
        yield features.index_select(0,j),labels.index_select(0,j)

# 3.初始化模型参数
w = torch.tensor(np.random.normal(0,0.01,(num_inputs,1)),dtype=torch.float32)
b = torch.zeros(1,dtype=torch.float32)
w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

# 4.定义模型
def linreg(X,w,b):
    return torch.mm(X,w) + b

# 5.定义损失函数
def squared_loss(y_hat,y):
    return (y_hat - y.view(y_hat.size())) ** 2 / 2

# 6.定义优化算法
def sgd(params,lr,batch_size):
    for param in params:
        param.data -= lr * param.grad / batch_size

# 7.模型训练
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):  # 训练模型一共需要num_epochs个迭代周期
    # 在每一个迭代周期中，会使用训练数据集中所有样本一次（假设样本数能够被批量大小整除）。X
    # 和y分别是小批量样本的特征和标签
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y).sum()  # l是有关小批量X和y的损失
        l.backward()  # 小批量的损失对模型参数求梯度
        sgd([w, b], lr, batch_size)  # 使用小批量随机梯度下降迭代模型参数
        
        # 不要忘了梯度清零
        w.grad.data.zero_()
        b.grad.data.zero_()
    train_l = loss(net(features, w, b), labels)
    print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))

>> epoch 1, loss 0.034886
>> epoch 2, loss 0.000138
>> epoch 3, loss 0.000053

print(true_w, '\n', w)
print(true_b, '\n', b)

>> [2, -3.4] 
>> tensor([[ 1.9999],
        [-3.3999]], requires_grad=True)
>> 4.2 
>> tensor([4.1994], requires_grad=True)

简洁实现

from torch.nn import init
import torch.optim as optim
import torch.utils.data as Data

num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)

batch_size = 10
# 将训练数据的特征和标签组合
dataset = Data.TensorDataset(features, labels)
# 随机读取小批量
data_iter = Data.DataLoader(dataset, batch_size, shuffle=True)

class LinearNet(nn.Module):
    def __init__(self, n_feature):
        super(LinearNet, self).__init__()
        self.linear = nn.Linear(n_feature, 1)
    # forward 定义前向传播
    def forward(self, x):
        y = self.linear(x)
        return y

init.normal_(net[0].weight, mean=0, std=0.01)
init.constant_(net[0].bias, val=0)  

loss = nn.MSELoss()

optimizer = optim.SGD(net.parameters(), lr=0.03)

num_epochs = 3
for epoch in range(1, num_epochs + 1):
    for X, y in data_iter:
        output = net(X)
        l = loss(output, y.view(-1, 1))
        optimizer.zero_grad() # 梯度清零，等价于net.zero_grad()
        l.backward()
        optimizer.step()
    print('epoch %d, loss: %f' % (epoch, l.item()))