SONG Shengjie
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
import collections
import re
d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
'090b5e7e70c295757f55df93cb0a180b9691891a')
# 定义读取时间机器数据集的函数
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]
# 定义将文本行拆分为单词或字符词元的函数
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)
# 定义文本词表类
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
# 定义统计词元频率的函数
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)
# 定义返回时光机器数据集的词元索引列表和词表的函数
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
# 定义使用随机抽样生成一个小批量子序列的函数
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 torch.tensor(X), torch.tensor(Y)
# 定义使用顺序分区生成一个小批量子序列的函数
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
# 定义加载序列数据的迭代器类
class SeqDataLoader:
"""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 = 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)
# 定义返回时光机器数据集的迭代器和词表的函数
def load_data_time_machine(batch_size, num_steps, 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
# 测试代码
batch_size, num_steps = 32, 35
train_iter, vocab = load_data_time_machine(batch_size, num_steps)
batch_size, num_steps = 32, 35
train_iter, vocab = load_data_time_machine(batch_size, num_steps)
## 独热编码
F.one_hot(torch.tensor([0, 2]), len(vocab))
X = torch.arange(10).reshape((2, 5))
F.one_hot(X.T, 28).shape
torch.Size([5, 2, 28])
# 初始化模型参数
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
# RNN
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):
# 初始化模型基础参数
self.vocab_size = vocab_size # 词汇表大小，决定输入维度
self.num_hiddens = num_hiddens # 隐藏层单元数，控制模型复杂度
self.device = device # 计算设备（CPU/GPU）
# 获取模型参数（权重矩阵和偏置向量）
# get_params 函数应返回包含W_xh, W_hh, b_h, W_hq, b_q参数的字典
self.params = get_params(vocab_size, num_hiddens, device)
# 初始化隐藏状态的函数（通常返回全零张量）
self.init_state = init_state
# 前向传播计算函数，定义RNN单元的计算逻辑
self.forward_fn = forward_fn
def __call__(self, X, state):
# 将输入序列X转换为one-hot编码格式
# X形状：(时间步数, 批量大小) -> 转置为(批量大小, 时间步数)
# one_hot后形状：(批量大小, 时间步数, 词汇表大小)
X = F.one_hot(X.T, self.vocab_size).type(torch.float32)
# 执行前向传播，返回输出和新的隐藏状态
# 参数说明：
# X - 输入序列的one-hot表示
# state - 初始隐藏状态
# params - 模型参数字典
return self.forward_fn(X, state, self.params)
def begin_state(self, batch_size, device):
# 生成初始隐藏状态（通常为全零张量）
# 形状：(批量大小, 隐藏单元数)
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)
state = net.begin_state(X.shape[0], d2l.try_gpu())
Y, new_state = net(X.to(d2l.try_gpu()), state)
Y.shape, len(new_state), new_state[0].shape
(torch.Size([10, 28]), 1, torch.Size([2, 512]))
# 预测
def predict_ch8(prefix, num_preds, net, vocab, device): #@save
"""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())
'time traveller bgiljqvajq'
# 裁剪梯度
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
# 训练
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'))
import random
num_epochs, lr = 500, 1
train_ch8(net, train_iter, vocab, lr, num_epochs, d2l.try_gpu())
困惑度 1.0, 17524.7 词元/秒 cpu
time traveller for so it will be convenient to speak of himwas e
traveller with a slight accession ofcheerfulness really thi
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)
困惑度 1.4, 18196.8 词元/秒 cpu
time travellerit s against reason said filbywhan at siroove a ou
travellerit s against reason said filbywhan at siroove a ou
#简洁版
class RNNModel(nn.Module):
"""循环神经网络模型"""
def __init__(self, rnn_layer, vocab_size, **kwargs):
super(RNNModel, self).__init__(**kwargs)
self.rnn = rnn_layer
self.vocab_size = vocab_size
self.num_hiddens = self.rnn.hidden_size
# 如果RNN是双向的（之后将介绍），num_directions应该是2，否则应该是1
if not self.rnn.bidirectional:
self.num_directions = 1
self.linear = nn.Linear(self.num_hiddens, self.vocab_size)
else:
self.num_directions = 2
self.linear = nn.Linear(self.num_hiddens * 2, self.vocab_size)
def forward(self, inputs, state):
X = F.one_hot(inputs.T.long(), self.vocab_size)
X = X.to(torch.float32)
Y, state = self.rnn(X, state)
# 全连接层首先将Y的形状改为(时间步数*批量大小,隐藏单元数)
# 它的输出形状是(时间步数*批量大小,词表大小)。
output = self.linear(Y.reshape((-1, Y.shape[-1])))
return output, state
def begin_state(self, device, batch_size=1):
if not isinstance(self.rnn, nn.LSTM):
# nn.GRU以张量作为隐状态
return torch.zeros((self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens),
device=device)
else:
# nn.LSTM以元组作为隐状态
return (torch.zeros((
self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens), device=device),
torch.zeros((
self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens), device=device))