DL|循环神经网络部分

一、序列模型

时间序列
预测方式有自回归模型（与过去所有时间有关）、马尔可夫模型（只与x个过去数据有关）、潜变量模型（h+x->新的h，再循环）。

多层感知机实现马尔可夫模型：

%matplotlib inline
import torch
from torch import nn
from d2l import torch as d2l

T = 1000  # 总共产生1000个点
time = torch.arange(1, T + 1, dtype=torch.float32)
x = torch.sin(0.01 * time) + torch.normal(0, 0.2, (T,))
d2l.plot(time, [x], 'time', 'x', xlim=[1, 1000], figsize=(6, 3))

tau = 4
features = torch.zeros((T - tau, tau))
for i in range(tau):
    features[:, i] = x[i: T - tau + i]
labels = x[tau:].reshape((-1, 1))

batch_size, n_train = 16, 600
# 只有前n_train个样本用于训练
train_iter = d2l.load_array((features[:n_train], labels[:n_train]),
                            batch_size, is_train=True)

# 初始化网络权重的函数
def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.xavier_uniform_(m.weight)

# 一个简单的多层感知机
def get_net():
    net = nn.Sequential(nn.Linear(4, 10),
                        nn.ReLU(),
                        nn.Linear(10, 1))
    net.apply(init_weights)
    return net

# 平方损失。注意：MSELoss计算平方误差时不带系数1/2
loss = nn.MSELoss(reduction='none')

def train(net, train_iter, loss, epochs, lr):
    trainer = torch.optim.Adam(net.parameters(), lr)
    for epoch in range(epochs):
        for X, y in train_iter:
            trainer.zero_grad()
            l = loss(net(X), y)
            l.sum().backward()
            trainer.step()
        print(f'epoch {
      epoch + 1}, '
              f'loss: {
      d2l.evaluate_loss(net, train_iter, loss):f}')

net = get_net()
train(net, train_iter, loss, 5, 0.01)

max_steps = 64

features = torch.zeros((T - tau - max_steps + 1, tau + max_steps))
# 列i（i<tau）是来自x的观测，其时间步从（i+1）到（i+T-tau-max_steps+1）
for i in range(tau):
    features[:, i] = x[i: i + T - tau - max_steps + 1]

# 列i（i>=tau）是来自（i-tau+1）步的预测，其时间步从（i+1）到（i+T-tau-max_steps+1）
for i in range(tau, tau + max_steps):
    features[:, i] = net(features[:, i - tau:i]).reshape(-1)

steps = (1, 4, 16, 64)
d2l.plot([time[tau + i - 1: T - max_steps + i] for i in steps],
         [features[:, (tau + i - 1)].detach().numpy() for i in steps], 'time', 'x',
         legend=[f'{
      i}-step preds' for i in steps], xlim=[5, 1000],
         figsize=(6, 3))

单步预测：例如用已知的x1、x2、x3、x4来预测x5，再用已知的x2、x3、x4、x5来预测x6，由此由已知的x1到x996得到预测的x5到x1000。
多步预测：例如步长为4，用已知的x1、x2、x3、x4来预测x5，再用已知的x2、x3、x4和预测的x5来预测x6。（这里还有一些疑问，看看后面能否解决。）“虽然4步预测看起来仍然不错，但超过这个跨度的任何预测几乎都是无用的。”

二、文本预处理

import collections
import re
from d2l import torch as d2l


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

def read_time_machine():
    """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]

lines = read_time_machine()

def tokenize(lines, token='word'): 
    """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)

tokens = tokenize(lines)

class Vocab:
    """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):
    """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)

vocab = Vocab(tokens)

# for i in [0, 10]:
# print('文本:', tokens[i])
# print('索引:', vocab[tokens[i]])

def load_corpus_time_machine(max_tokens=-1): 
    """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

corpus, vocab = load_corpus_time_machine()
len(corpus), len(vocab)
print(corpus)

三、语言模型

马尔可夫模型与n元语法：

import random
import torch
from d2l import torch as d2l

tokens = d2l.tokenize(d2l.read_time_machine())
# 因为每个文本行不一定是一个句子或一个段落，因此我们把所有文本行拼接到一起
corpus = [token for line in tokens for token in line]
vocab = d2l.Vocab(corpus)
# vocab.token_freqs[:10]

freqs = [freq for token, freq in vocab.token_freqs]
d2l.plot(freqs, xlabel='token: x', ylabel='frequency: n(x)',
         xscale='log', yscale='log')

bigram_tokens = [pair for pair in zip(corpus[:-1], corpus[1:])]
bigram_vocab = d2l.Vocab(bigram_tokens)
bigram_vocab.token_freqs[:10]

trigram_tokens = [triple for triple in zip(
    corpus[:-2], corpus[1:-1], corpus[2:])]
trigram_vocab = d2l.Vocab(trigram_tokens)
trigram_vocab.token_freqs[:10]

bigram_freqs = [freq for token, freq in bigram_vocab.token_freqs]
trigram_freqs = [freq for token, freq in trigram_vocab.token_freqs]
d2l.plot([freqs, bigram_freqs, trigram_freqs], xlabel='token: x',
         ylabel='frequency: n(x)', xscale='log', yscale='log',
         legend=['unigram', 'bigram', 'trigram'])

读取长序列数据：
随机采样：

import random
import torch
from d2l import torch as d2l
import numpy as np

def seq_data_iter_random(corpus, batch_size, num_steps):
    """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 np.array(X), np.array(Y)

my_seq = list(range(35))
for X, Y in seq_data_iter_random(my_seq, batch_size=2, num_steps=5):
    print('X: ', X, '\nY:', Y)

顺序分区：

import random
import torch
from d2l import torch as d2l
import numpy as np

def seq_data_iter_sequential(corpus, batch_size, num_steps):
    """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

my_seq = list(range(35))
for X, Y in seq_data_iter_sequential(my_seq, batch_size=2, num_steps=5):
    print('X: ', X, '\nY:', Y)

四、循环神经网络

从零开始实现：

%matplotlib inline
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)

def get_params(vocab_size, num_hiddens, device):
    num_inputs = num_outputs = vocab_size

    def normal(shape):
        return torch.randn(size=shape, device=device) * 0.01

    # 隐藏层参数
    W_xh = normal((num_inputs, num_hiddens))
    W_hh = normal((num_hiddens, num_hiddens))
    b_h = torch.zeros(num_hiddens, device=device)
    # 输出层参数
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    # 附加梯度
    params = [W_xh, W_hh, b_h, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params

def init_rnn_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device), )

def rnn(inputs, state, params):
    # inputs的形状：(时间步数量，批量大小，词表大小)
    W_xh, W_hh, b_h, W_hq, b_q = params
    H, = state
    outputs = []
    # X的形状：(批量大小，词表大小)
    for X in inputs:
        H = torch.tanh(torch.mm(X, W_xh) + torch.mm(H, W_hh) + b_h)
        Y = torch.mm(H, W_hq) + b_q
        outputs.append(Y)
    return torch.cat(outputs, dim=0), (H,)

class RNNModelScratch:
    """从零开始实现的循环神经网络模型"""
    def __init__(self, vocab_size, num_hiddens, device,
                 get_params, init_state, forward_fn):
        self.vocab_size, self.num_hiddens = vocab_size, num_hiddens
        self.params = get_params(vocab_size, num_hiddens, device)
        self.init_state, self.forward_fn = init_state, forward_fn

    def __call__(self, X, state):
        X = F.one_hot(X.T, self.vocab_size).type(torch.float32)
        return self.forward_fn(X, state, self.params)

    def begin_state(self, batch_size, device):
        return self.init_state(batch_size, self.num_hiddens, device)

num_hiddens = 512
net = RNNModelScratch(len(vocab), num_hiddens, d2l.try_gpu(), get_params,
                      init_rnn_state, rnn)

def predict_ch8(prefix, num_preds, net, vocab, device):
    """在prefix后面生成新字符"""
    state = net.begin_state(batch_size=1, device=device)
    outputs = [vocab[prefix[0]]]
    get_input = lambda: torch.tensor([outputs[-1]], device=device).reshape((1, 1))
    for y in prefix[1:]:  # 预热期
        _, state = net(get_input(), state)
        outputs.append(vocab[y])
    for _ in range(num_preds):  # 预测num_preds步
        y, state = net(get_input(), state)
        outputs.append(int(y.argmax(dim=1).reshape(1)))
    return ''.join([vocab.idx_to_token[i] for i in outputs])

predict_ch8('time traveller ', 10, net, vocab, d2l.try_gpu())

def grad_clipping(net, theta):
    """裁剪梯度"""
    if isinstance(net, nn.Module):
        params = [p for p in net.parameters() if p.requires_grad]
    else:
        params = net.params
    norm = torch.sqrt(sum(torch.sum((p.grad ** 2)) for p in params))
    if norm > theta:
        for param in params:
            param.grad[:] *= theta / norm

def train_epoch_ch8(net, train_iter, loss, updater, device, use_random_iter):
    """训练网络一个迭代周期（定义见第8章）"""
    state, timer = None, d2l.Timer()
    metric = d2l.Accumulator(2)  # 训练损失之和,词元数量
    for X, Y in train_iter:
        if state is None or use_random_iter:
            # 在第一次迭代或使用随机抽样时初始化state
            state = net.begin_state(batch_size=X.shape[0], device=device)
        else:
            if isinstance(net, nn.Module) and not isinstance(state, tuple):
                # state对于nn.GRU是个张量
                state.detach_()
            else:
                # state对于nn.LSTM或对于我们从零开始实现的模型是个张量
                for s in state:
                    s.detach_()
        y = Y.T.reshape(-1)
        X, y = X.to(device), y.to(device)
        y_hat, state = net(X, state)
        l = loss(y_hat, y.long()).mean()
        if isinstance(updater, torch.optim.Optimizer):
            updater.zero_grad()
            l.backward()
            grad_clipping(net, 1)
            updater.step()
        else:
            l.backward()
            grad_clipping(net, 1)
            # 因为已经调用了mean函数
            updater(batch_size=1)
        metric.add(l * y.numel(), y.numel())
    return math.exp(metric[0] / metric[1]), metric[1] / timer.stop()

def train_ch8(net, train_iter, vocab, lr, num_epochs, device,
              use_random_iter=False):
    """训练模型（定义见第8章）"""
    loss = nn.CrossEntropyLoss()
    animator = d2l.Animator(xlabel='epoch', ylabel='perplexity',
                            legend=['train'], xlim=[10, num_epochs])
    # 初始化
    if isinstance(net, nn.Module):
        updater = torch.optim.SGD(net.parameters(), lr)
    else:
        updater = lambda batch_size: d2l.sgd(net.params, lr, batch_size)
    predict = lambda prefix: predict_ch8(prefix, 50, net, vocab, device)
    # 训练和预测
    for epoch in range(num_epochs):
        ppl, speed = train_epoch_ch8(
            net, train_iter, loss, updater, device, use_random_iter)
        if (epoch + 1) % 10 == 0:
            print(predict('time traveller'))
            animator.add(epoch + 1, [ppl])
    print(f'困惑度 {
      ppl:.1f}, {
      speed:.1f} 词元/秒 {
      str(device)}')
    print(predict('time traveller'))
    print(predict('traveller'))

num_epochs, lr = 500, 1
train_ch8(net, train_iter, vocab, lr, num_epochs, d2l.try_gpu())

net = RNNModelScratch(len(vocab), num_hiddens, d2l.try_gpu(), get_params,
                      init_rnn_state, rnn)
train_ch8(net, train_iter, vocab, lr, num_epochs, d2l.try_gpu(),
          use_random_iter=True)

（文字和第二个图是使用随机抽样方法的结果，第一个图是使用顺序分区方法的结果）
简洁实现：

%matplotlib inline
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)

num_hiddens, device = 256, d2l.try_gpu()
num_epochs, lr = 500, 1

rnn_layer = nn.RNN(len(vocab), num_hiddens)
net = d2l.RNNModel(rnn_layer, vocab_size=len(vocab))
net = net.to(device)
d2l.train_ch8(net, train_iter, vocab, lr, num_epochs, device, use_random_iter=True)

五、门控循环单元（GRU）

从零开始实现：

import torch
from torch import nn
from d2l import torch as d2l

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

def get_params(vocab_size, num_hiddens, device):
    num_inputs = num_outputs = vocab_size

    def normal(shape):
        return torch.randn(size=shape, device=device)*0.01

    def three():
        return (normal((num_inputs, num_hiddens)),
                normal((num_hiddens, num_hiddens)),
                torch.zeros(num_hiddens, device=device))

    W_xz, W_hz, b_z = three()  # 更新门参数
    W_xr, W_hr, b_r = three()  # 重置门参数
    W_xh, W_hh, b_h = three()  # 候选隐状态参数
    # 输出层参数
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    # 附加梯度
    params = [W_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params

def init_gru_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device), )

def gru(inputs, state, params):
    W_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q = params
    H, = state
    outputs = []
    for X in inputs:
        Z = torch.sigmoid((X @ W_xz) + (H @ W_hz) + b_z)
        R = torch.sigmoid((X @ W_xr) + (H @ W_hr) + b_r)
        H_tilda = torch.tanh((X @ W_xh) + ((R * H) @ W_hh) + b_h)
        H = Z * H + (1 - Z) * H_tilda
        Y = H @ W_hq + b_q
        outputs.append(Y)
    return torch.cat(outputs, dim=0), (H,)

vocab_size, num_hiddens, device = len(vocab), 256, d2l.try_gpu()
num_epochs, lr = 500, 1
model = d2l.RNNModelScratch(vocab_size, num_hiddens, device, get_params,
                            init_gru_state, gru)
d2l.train_ch8(model, train_iter, vocab, lr, num_epochs, device)

简洁实现：

import torch
from torch import nn
from d2l import torch as d2l

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

vocab_size, num_hiddens, device = len(vocab), 256, d2l.try_gpu()
num_epochs, lr = 500, 1

num_inputs = vocab_size
gru_layer = nn.GRU(num_inputs, num_hiddens)
model = d2l.RNNModel(gru_layer, len(vocab))
model = model.to(device)
d2l.train_ch8(model, train_iter, vocab, lr, num_epochs, device)

六、长短期记忆网络（LSTM）

从零开始实现：

import torch
from torch import nn
from d2l import torch as d2l

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

def get_lstm_params(vocab_size, num_hiddens, device):
    num_inputs = num_outputs = vocab_size

    def normal(shape):
        return torch.randn(size=shape, device=device)*0.01

    def three():
        return (normal((num_inputs, num_hiddens)),
                normal((num_hiddens, num_hiddens)),
                torch.zeros(num_hiddens, device=device))

    W_xi, W_hi, b_i = three()  # 输入门参数
    W_xf, W_hf, b_f = three()  # 遗忘门参数
    W_xo, W_ho, b_o = three()  # 输出门参数
    W_xc, W_hc, b_c = three()  # 候选记忆元参数
    # 输出层参数
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    # 附加梯度
    params = [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc,
              b_c, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params

def init_lstm_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device),
            torch.zeros((batch_size, num_hiddens), device=device))
    
def lstm(inputs, state, params):
    [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc, b_c,
     W_hq, b_q] = params
    (H, C) = state
    outputs = []
    for X in inputs:
        I = torch.sigmoid((X @ W_xi) + (H @ W_hi) + b_i)
        F = torch.sigmoid((X @ W_xf) + (H @ W_hf) + b_f)
        O = torch.sigmoid((X @ W_xo) + (H @ W_ho) + b_o)
        C_tilda = torch.tanh((X @ W_xc) + (H @ W_hc) + b_c)
        C = F * C + I * C_tilda
        H = O * torch.tanh(C)
        Y = (H @ W_hq) + b_q
        outputs.append(Y)
    return torch.cat(outputs, dim=0), (H, C)

vocab_size, num_hiddens, device = len(vocab), 256, d2l.try_gpu()
num_epochs, lr = 500, 1
model = d2l.RNNModelScratch(vocab_size, num_hiddens, device, get_lstm_params,
                            init_lstm_state, lstm)
d2l.train_ch8(model, train_iter, vocab, lr, num_epochs, device)

简洁实现：

import torch
from torch import nn
from d2l import torch as d2l

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

vocab_size, num_hiddens, device = len(vocab), 256, d2l.try_gpu()
num_epochs, lr = 500, 1

num_inputs = vocab_size
lstm_layer = nn.LSTM(num_inputs, num_hiddens)
model = d2l.RNNModel(lstm_layer, vocab_size)
model = model.to(device)
d2l.train_ch8(model, train_iter, vocab, lr, num_epochs, device)