4-线性回归

python中*运算符的使用
用于将可迭代对象（如列表或元组）的元素解压缩为单独的参数

当我们从Dataloader取出来的时候，又会将压缩为的单独参数分开

import torch
from torch.utils import data

# 准备数据
true_w = torch.tensor([2, -3.4])
true_b = 4.2

def synthetic_data(w, b, num_examples):
    x = torch.normal(0, 1, size=(num_examples, 2))
    y = torch.matmul(x, w) + b
    y += torch.normal(0, 1, size = y.shape)
    return x, y.reshape((-1, 1))

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

# 获取数据
def load_data(data_arrays, batch_size, is_train = True):
    dataset = data.TensorDataset(*data_arrays) # 使用data.TensorDataset函数将输入的data_arrays中的张量组合成一个数据集
    return data.DataLoader(dataset, batch_size, shuffle=is_train) # 使用data.DataLoader函数将数据集包装成一个数据加载器

data_iter = load_data((features, labels), 10)

# 构造模型
net = torch.nn.Sequential(torch.nn.Linear(2, 1)) # 输入特征形状  输出特征形状
net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)

# 定义损失函数和优化器
loss = torch.nn.MSELoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)

# 训练
epochs = 10
for epoch in range(epochs):
    for X, Y in data_iter:
        l = loss(net(X), Y)
        optimizer.zero_grad()

        l.backward()
        optimizer.step()

    l = loss(net(features), labels)
    print('epoch:{},  loss:{}'.format(epoch+1, l.item()))