线性回归 - 代码 (使用深度学习框架实现)

使用深度学习框架去实现线性回归

(我没理解明白, 但先把代码整理一下笔记... 仍需继续学习)

import torch
from torch.utils import data
from torch import nn

# 自创数据集
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) # add noise
  return x, y.reshape((-1, 1))

# 构造真的w和b
true_w = torch.tensor([2, -3.4])
true_b = 4.2

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

# 构造PyTorch数据迭代器
def load_array(data_arrays, batch_size, is_train=True): # data_arrays即(features, labels)的list
  dataset = data.TensorDataset(*data_arrays)
  dataloader = data.DataLoader(dataset, batch_size, shuffle=is_train) # 每次shuffle样本出来
  return dataloader

batch_size = 10
data_iter = load_array((features, la