pytorch 学习笔记 part 5 语言模型

语言模型数据集采样方法

读取数据集

这里采用的是周杰伦的歌词作为样本

with open(r'D:\project\language_model\jaychou9972\jaychou_lyrics.txt',encoding='utf-8') as f:
    corpus_chars = f.read()
print(len(corpus_chars))
print(corpus_chars[: 40])
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[: 10000]

建立字符索引

idx_to_char = list(set(corpus_chars)) # 去重，得到索引到字符的映射
char_to_idx = {char: i for i, char in enumerate(idx_to_char)} # 字符到索引的映射
vocab_size = len(char_to_idx)
print(vocab_size)

corpus_indices = [char_to_idx[char] for char in corpus_chars]  # 将每个字符转化为索引，得到一个索引的序列
sample = corpus_indices[: 20]
print('chars:', ''.join([idx_to_char[idx] for idx in sample]))
print('indices:', sample)

定义函数load_data_jay_lyrics，在后续章节中直接调用。

def load_data_jay_lyrics():
    with open(r'D:\project\language_model\jaychou9972\jaychou_lyrics.txt',encoding='utf-8') as f:
        corpus_chars = f.read()
    corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
    corpus_chars = corpus_chars[0:10000]
    idx_to_char = list(set(corpus_chars))
    char_to_idx = dict([(char, i) for i, char in enumerate(idx_to_char)])
    vocab_size = len(char_to_idx)
    corpus_indices = [char_to_idx[char] for char in corpus_chars]
    return corpus_indices, char_to_idx, idx_to_char, vocab_size

1.随机采样

下面的代码每次从数据里随机采样一个小批量。其中批量大小batch_size是每个小批量的样本数，num_steps是每个样本所包含的时间步数。 在随机采样中，每个样本是原始序列上任意截取的一段序列，相邻的两个随机小批量在原始序列上的位置不一定相毗邻。

import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):# 序列，批量大小，时间步数，控制最后返回的批量放在什么设备上
    # 减1是因为对于长度为n的序列，X最多只有包含其中的前n - 1个字符
    num_examples = (len(corpus_indices) - 1) // num_steps  # 下取整，得到不重叠情况下的样本个数
    example_indices = [i * num_steps for i in range(num_examples)]  # 每个样本的第一个字符在corpus_indices中的下标
    random.shuffle(example_indices)

    def _data(i):
        # 返回从i开始的长为num_steps的序列
        return corpus_indices[i: i + num_steps]
    if device is None:
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    
    for i in range(0, num_examples, batch_size):
        # 每次选出batch_size个随机样本
        batch_indices = example_indices[i: i + batch_size]  # 当前batch的各个样本的首字符的下标
        X = [_data(j) for j in batch_indices]
        Y = [_data(j + 1) for j in batch_indices]
        yield torch.tensor(X, device=device), torch.tensor(Y, device=device)

my_seq = list(range(30))
for X, Y in data_iter_random(my_seq, batch_size=2, num_steps=6):
    print('X: ', X, '\nY:', Y, '\n')

2.相邻采样

在相邻采样中，相邻的两个随机小批量在原始序列上的位置相毗邻。

def data_iter_consecutive(corpus_indices, batch_size, num_steps, device=None):
    if device is None:
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    corpus_len = len(corpus_indices) // batch_size * batch_size  # 保留下来的序列的长度
    corpus_indices = corpus_indices[: corpus_len]  # 仅保留前corpus_len个字符
    indices = torch.tensor(corpus_indices, device=device)
    indices = indices.view(batch_size, -1)  # resize成(batch_size, )
    batch_num = (indices.shape[1] - 1) // num_steps
    for i in range(batch_num):
        i = i * num_steps
        X = indices[:, i: i + num_steps]
        Y = indices[:, i + 1: i + num_steps + 1]
        yield X, Y

for X, Y in data_iter_consecutive(my_seq, batch_size=2, num_steps=6):
    print('X: ', X, '\nY:', Y, '\n')