批数据训练

为应对大数据和内存限制，我们常采用批训练的方式以提高训练效率

1. 数据准备

import torch
import torch.utils.data as Data

torch.manual_seed(1)    # reproducible

BATCH_SIZE = 5
# BATCH_SIZE = 8

x = torch.linspace(1, 10, 10)       # this is x data (torch tensor)
y = torch.linspace(10, 1, 10)       # this is y data (torch tensor)

2.数据装载与分批次

torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # mini batch size
    shuffle=True,               # random shuffle for training
    num_workers=2,              # subprocesses for loading data
)

注：

1. Data.TensorDataset()：包装数据和目标张量的数据集，通过沿着第一个维度索引两个张量来恢复每个样本。
2. batch_size： mini batch size
3. shuffle: random shuffle for training
4. num_workers=2：subprocesses for loading data，数据有x，y两类
5. Data.DataLoader(): 数据加载器, 用以组合数据集和采样器，并在数据集上提供单进程或多进程迭代器。

3. 批训练

def show_batch():
    for epoch in range(3):   # train entire dataset 3 times
        for step, (batch_x, batch_y) in enumerate(loader):  # for each training step
            # train your data...
            print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
                  batch_x.numpy(), '| batch y: ', batch_y.numpy())


if __name__ == '__main__':
    show_batch()

注：

1. epoch：表示所有数据的训练次数
2. batch：每一批次装载
3. 补充：zip()函数，将zip(x，y)装载为元组，以成对提取数据