RNN的从零开始-使用梯度下降优化网络

在D2L的官方教程中如下代码会报错

import math
import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l

batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)

报错内容如下：

AttributeError                            Traceback (most recent call last)
Cell In[59], line 9
      6 from d2l import torch as d2l
      8 batch_size, num_steps = 32, 35
----> 9 train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)

AttributeError: module 'd2l.torch' has no attribute 'load_data_time_machine'

对其原因分析为d2l.torch包里面没有load_data_time_machine这个函数，解决办法也很简单。

1.退回0.17.5版本(不推荐)

2.自己手动构造load_data_time_machine这个函数

在8.2部分，已经有如何处理文本数据了，这里就不赘述了。

现在来说后半部分（末尾有该部分完整代码！！！！）

8.4.4 读取长序列数据

构建随机采样函数

def seq_data_iter_random(corpus, batch_size, num_steps):  #@save
    """使用随机抽样生成一个小批量子序列"""
    # 从随机偏移量开始对序列进行分区，随机范围包括num_steps-1
    corpus = corpus[random.randint(0, num_steps - 1):]
    # 减去1，是因为我们需要考虑标签
    num_subseqs = (len(corpus) - 1) // num_steps
    # 长度为num_steps的子序列的起始索引
    initial_indices = list(range(0, num_subseqs * num_steps, num_steps))
    # 在随机抽样的迭代过程中，
    # 来自两个相邻的、随机的、小批量中的子序列不一定在原始序列上相邻
    random.shuffle(initial_indices)

    def data(pos):
        # 返回从pos位置开始的长度为num_steps的序列
        return corpus[pos: pos + num_steps]

    num_batches = num_subseqs // batch_size
    for i in range(0, batch_size * num_batches, batch_size):
        # 在这里，initial_indices包含子序列的随机起始索引
        initial_indices_per_batch = initial_indices[i: i + batch_size]
        X = [data(j) for j in initial_indices_per_batch]
        Y = [data(j + 1) for j in initial_indices_per_batch]
        yield torch.tensor(X), torch.tensor(Y)

构建顺序分区函数

def seq_data_iter_sequential(corpus, batch_size, num_steps):  #@save
    """使用顺序分区生成一个小批量子序列"""
    # 从随机偏移量开始划分序列
    offset = random.randint(0, num_steps)
    num_tokens = ((len(corpus) - offset - 1) // batch_size) * batch_size
    Xs = torch.tensor(corpus[offset: offset + num_tokens])
    Ys = torch.tensor(corpus[offset + 1: offset + 1 + num_tokens])
    Xs, Ys = Xs.reshape(batch_size, -1), Ys.reshape(batch_size, -1)
    num_batches = Xs.shape[1] // num_steps
    for i in range(0, num_steps * num_batches, num_steps):
        X = Xs[:, i: i + num_steps]
        Y = Ys[:, i: i + num_steps]
        yield X, Y

将上面的两个采样函数包装到一个类中

class SeqDataLoader:  #@save
    """加载序列数据的迭代器"""

    def __init__(self, batch_size, num_steps, use_random_iter, max_tokens):
        if use_random_iter:
            self.data_iter_fn = d2l.seq_data_iter_random
        else:
            self.data_iter_fn = seq_data_iter_sequential
        self.corpus, self.vocab = load_corpus_time_machine(max_tokens)
        self.batch_size, self.num_steps = batch_size, num_steps

    def __iter__(self):
        return self.data_iter_fn(self.corpus, self.batch_size, self.num_steps)

定义函数load_data_time_machine

def load_data_time_machine(batch_size, num_steps,  #@save
                           use_random_iter=False, max_tokens=10000):
    """返回时光机器数据集的迭代器和词表"""
    data_iter = SeqDataLoader(
        batch_size, num_steps, use_random_iter, max_tokens)
    return data_iter, data_iter.vocab

修改8.5函数

batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)
修改为
batch_size, num_steps = 32, 35
train_iter, vocab = load_data_time_machine(batch_size, num_steps)

到此为止完成第二种手动构造load_data_time_machine这个函数

剩下代码可重8.5部分自行复制

最终结果如图：

(完整代码仅仅包含报错部分的完整代码，无法理解请重新阅读)

附完整代码：

import random
import torch
import collections
from d2l import torch as d2l
import math
import re
from torch import nn
from torch.nn import functional as F

d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
                                '090b5e7e70c295757f55df93cb0a180b9691891a')


def read_time_machine():  #@save
    """将时间机器数据集加载到文本行的列表中"""
    with open(d2l.download('time_machine'), 'r') as f:
        lines = f.readlines()
    return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]


def tokenize(lines, token='word'):  #@save
    """将文本行拆分为单词或字符词元"""
    if token == 'word':
        return [line.split() for line in lines]
    elif token == 'char':
        return [list(line) for line in lines]
    else:
        print('错误：未知词元类型：' + token)


class Vocab:  #@save
    """文本词表"""

    def __init__(self, tokens=None, min_freq=0, reserved_tokens=None):
        if tokens is None:
            tokens = []
        if reserved_tokens is None:
            reserved_tokens = []
        # 按出现频率排序
        counter = count_corpus(tokens)
        self._token_freqs = sorted(counter.items(), key=lambda x: x[1],
                                   reverse=True)
        # 未知词元的索引为0
        self.idx_to_token = ['<unk>'] + reserved_tokens
        self.token_to_idx = {token: idx
                             for idx, token in enumerate(self.idx_to_token)}
        for token, freq in self._token_freqs:
            if freq < min_freq:
                break
            if token not in self.token_to_idx:
                self.idx_to_token.append(token)
                self.token_to_idx[token] = len(self.idx_to_token) - 1

    def __len__(self):
        return len(self.idx_to_token)

    def __getitem__(self, tokens):
        if not isinstance(tokens, (list, tuple)):
            return self.token_to_idx.get(tokens, self.unk)
        return [self.__getitem__(token) for token in tokens]

    def to_tokens(self, indices):
        if not isinstance(indices, (list, tuple)):
            return self.idx_to_token[indices]
        return [self.idx_to_token[index] for index in indices]

    @property
    def unk(self):  # 未知词元的索引为0
        return 0

    @property
    def token_freqs(self):
        return self._token_freqs


def count_corpus(tokens):  #@save
    """统计词元的频率"""
    # 这里的tokens是1D列表或2D列表
    if len(tokens) == 0 or isinstance(tokens[0], list):
        # 将词元列表展平成一个列表
        tokens = [token for line in tokens for token in line]
    return collections.Counter(tokens)


def load_corpus_time_machine(max_tokens=-1):  #@save
    """返回时光机器数据集的词元索引列表和词表"""
    lines = read_time_machine()
    tokens = tokenize(lines, 'char')
    vocab = Vocab(tokens)
    # 因为时光机器数据集中的每个文本行不一定是一个句子或一个段落，
    # 所以将所有文本行展平到一个列表中
    corpus = [vocab[token] for line in tokens for token in line]
    if max_tokens > 0:
        corpus = corpus[:max_tokens]
    return corpus, vocab


def seq_data_iter_random(corpus, batch_size, num_steps):  #@save
    """使用随机抽样生成一个小批量子序列"""
    # 从随机偏移量开始对序列进行分区，随机范围包括num_steps-1
    corpus = corpus[random.randint(0, num_steps - 1):]
    # 减去1，是因为我们需要考虑标签
    num_subseqs = (len(corpus) - 1) // num_steps
    # 长度为num_steps的子序列的起始索引
    initial_indices = list(range(0, num_subseqs * num_steps, num_steps))
    # 在随机抽样的迭代过程中，
    # 来自两个相邻的、随机的、小批量中的子序列不一定在原始序列上相邻
    random.shuffle(initial_indices)

    def data(pos):
        # 返回从pos位置开始的长度为num_steps的序列
        return corpus[pos: pos + num_steps]

    num_batches = num_subseqs // batch_size
    for i in range(0, batch_size * num_batches, batch_size):
        # 在这里，initial_indices包含子序列的随机起始索引
        initial_indices_per_batch = initial_indices[i: i + batch_size]
        X = [data(j) for j in initial_indices_per_batch]
        Y = [data(j + 1) for j in initial_indices_per_batch]
        yield torch.tensor(X), torch.tensor(Y)


def seq_data_iter_sequential(corpus, batch_size, num_steps):  #@save
    """使用顺序分区生成一个小批量子序列"""
    # 从随机偏移量开始划分序列
    offset = random.randint(0, num_steps)
    num_tokens = ((len(corpus) - offset - 1) // batch_size) * batch_size
    Xs = torch.tensor(corpus[offset: offset + num_tokens])
    Ys = torch.tensor(corpus[offset + 1: offset + 1 + num_tokens])
    Xs, Ys = Xs.reshape(batch_size, -1), Ys.reshape(batch_size, -1)
    num_batches = Xs.shape[1] // num_steps
    for i in range(0, num_steps * num_batches, num_steps):
        X = Xs[:, i: i + num_steps]
        Y = Ys[:, i: i + num_steps]
        yield X, Y


class SeqDataLoader:  #@save
    """加载序列数据的迭代器"""

    def __init__(self, batch_size, num_steps, use_random_iter, max_tokens):
        if use_random_iter:
            self.data_iter_fn = d2l.seq_data_iter_random
        else:
            self.data_iter_fn = seq_data_iter_sequential
        self.corpus, self.vocab = load_corpus_time_machine(max_tokens)
        self.batch_size, self.num_steps = batch_size, num_steps

    def __iter__(self):
        return self.data_iter_fn(self.corpus, self.batch_size, self.num_steps)


def load_data_time_machine(batch_size, num_steps,  #@save
                           use_random_iter=False, max_tokens=10000):
    """返回时光机器数据集的迭代器和词表"""
    data_iter = SeqDataLoader(
        batch_size, num_steps, use_random_iter, max_tokens)
    return data_iter, data_iter.vocab


batch_size, num_steps = 32, 35
train_iter, vocab = load_data_time_machine(batch_size, num_steps)