注意
点击 此处 下载完整的示例代码
使用 TorchText 进行语言翻译¶
本教程演示了如何使用 torchtext 预处理来自包含英语和德语句子（一个众所周知的）数据集的数据，并使用它来训练一个带有注意力机制的序列到序列模型，该模型可以将德语句子翻译成英语。
它基于 PyTorch 社区成员 Ben Trevett 的 本教程（经 Ben 许可）。我们通过删除一些旧代码来更新教程。
在本教程结束时，您将能够将句子预处理成用于 NLP 建模的张量，并使用 torch.utils.data.DataLoader 训练和验证模型。
数据处理¶
torchtext 提供了用于创建数据集的实用程序，这些数据集可以轻松地进行迭代以用于创建语言翻译模型。在本例中，我们展示了如何对原始文本句子进行标记化、构建词汇表以及将标记数值化为张量。
注意：本教程中的标记化需要 Spacy。我们使用 Spacy 是因为它为除英语之外的其他语言的标记化提供了强大的支持。torchtext 提供了一个 basic_english 标记器并支持其他英语标记器（例如 Moses），但是对于需要多种语言的语言翻译而言，Spacy 是最佳选择。
要运行本教程，首先使用 pip 或 conda 安装 spacy。接下来，下载英语和德语 Spacy 标记器的原始数据。
python -m spacy download en
python -m spacy download de
import torchtext
import torch
from torchtext.data.utils import get_tokenizer
from collections import Counter
from torchtext.vocab import Vocab
from torchtext.utils import download_from_url, extract_archive
import io
url_base = 'https://raw.githubusercontent.com/multi30k/dataset/master/data/task1/raw/'
train_urls = ('train.de.gz', 'train.en.gz')
val_urls = ('val.de.gz', 'val.en.gz')
test_urls = ('test_2016_flickr.de.gz', 'test_2016_flickr.en.gz')
train_filepaths = [extract_archive(download_from_url(url_base + url))[0] for url in train_urls]
val_filepaths = [extract_archive(download_from_url(url_base + url))[0] for url in val_urls]
test_filepaths = [extract_archive(download_from_url(url_base + url))[0] for url in test_urls]
de_tokenizer = get_tokenizer('spacy', language='de')
en_tokenizer = get_tokenizer('spacy', language='en')
def build_vocab(filepath, tokenizer):
counter = Counter()
with io.open(filepath, encoding="utf8") as f:
for string_ in f:
counter.update(tokenizer(string_))
return Vocab(counter, specials=['<unk>', '<pad>', '<bos>', '<eos>'])
de_vocab = build_vocab(train_filepaths[0], de_tokenizer)
en_vocab = build_vocab(train_filepaths[1], en_tokenizer)
def data_process(filepaths):
raw_de_iter = iter(io.open(filepaths[0], encoding="utf8"))
raw_en_iter = iter(io.open(filepaths[1], encoding="utf8"))
data = []
for (raw_de, raw_en) in zip(raw_de_iter, raw_en_iter):
de_tensor_ = torch.tensor([de_vocab[token] for token in de_tokenizer(raw_de)],
dtype=torch.long)
en_tensor_ = torch.tensor([en_vocab[token] for token in en_tokenizer(raw_en)],
dtype=torch.long)
data.append((de_tensor_, en_tensor_))
return data
train_data = data_process(train_filepaths)
val_data = data_process(val_filepaths)
test_data = data_process(test_filepaths)
DataLoader¶
我们将使用的最后一个 torch 特性是 DataLoader，它易于使用，因为它将数据作为其第一个参数。具体来说，正如文档中所说：DataLoader 组合了一个数据集和一个采样器，并提供了一个对给定数据集进行迭代的迭代器。DataLoader 支持使用单进程或多进程加载的映射风格和可迭代风格的数据集，自定义加载顺序以及可选的自动批处理（整理）和内存固定。
请注意 collate_fn（可选），它将样本列表合并以形成一个 Tensor(s) 的小批量。在从映射风格的数据集中使用批处理加载时使用。
import torch
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
BATCH_SIZE = 128
PAD_IDX = de_vocab['<pad>']
BOS_IDX = de_vocab['<bos>']
EOS_IDX = de_vocab['<eos>']
from torch.nn.utils.rnn import pad_sequence
from torch.utils.data import DataLoader
def generate_batch(data_batch):
de_batch, en_batch = [], []
for (de_item, en_item) in data_batch:
de_batch.append(torch.cat([torch.tensor([BOS_IDX]), de_item, torch.tensor([EOS_IDX])], dim=0))
en_batch.append(torch.cat([torch.tensor([BOS_IDX]), en_item, torch.tensor([EOS_IDX])], dim=0))
de_batch = pad_sequence(de_batch, padding_value=PAD_IDX)
en_batch = pad_sequence(en_batch, padding_value=PAD_IDX)
return de_batch, en_batch
train_iter = DataLoader(train_data, batch_size=BATCH_SIZE,
shuffle=True, collate_fn=generate_batch)
valid_iter = DataLoader(val_data, batch_size=BATCH_SIZE,
shuffle=True, collate_fn=generate_batch)
test_iter = DataLoader(test_data, batch_size=BATCH_SIZE,
shuffle=True, collate_fn=generate_batch)
定义我们的 nn.Module 和 Optimizer¶
从 torchtext 的角度来看，这几乎就是全部了：在构建了数据集并定义了迭代器之后，本教程的其余部分只是将我们的模型定义为一个 nn.Module，以及一个 Optimizer，然后对其进行训练。
具体来说，我们的模型遵循 此处 描述的架构（您可以在 此处 找到一个注释得更多版本）。
注意：此模型只是一个可用于语言翻译的示例模型；我们选择它是因为它是该任务的标准模型，而不是因为它是在翻译中建议使用的模型。您可能已经知道，最先进的模型目前基于 Transformer；您可以在 此处 查看 PyTorch 实现 Transformer 层的能力；并且特别是，下面模型中使用的“注意力”与 Transformer 模型中存在的多头自注意力不同。
import random
from typing import Tuple
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch import Tensor
class Encoder(nn.Module):
def __init__(self,
input_dim: int,
emb_dim: int,
enc_hid_dim: int,
dec_hid_dim: int,
dropout: float):
super().__init__()
self.input_dim = input_dim
self.emb_dim = emb_dim
self.enc_hid_dim = enc_hid_dim
self.dec_hid_dim = dec_hid_dim
self.dropout = dropout
self.embedding = nn.Embedding(input_dim, emb_dim)
self.rnn = nn.GRU(emb_dim, enc_hid_dim, bidirectional = True)
self.fc = nn.Linear(enc_hid_dim * 2, dec_hid_dim)
self.dropout = nn.Dropout(dropout)
def forward(self,
src: Tensor) -> Tuple[Tensor]:
embedded = self.dropout(self.embedding(src))
outputs, hidden = self.rnn(embedded)
hidden = torch.tanh(self.fc(torch.cat((hidden[-2,:,:], hidden[-1,:,:]), dim = 1)))
return outputs, hidden
class Attention(nn.Module):
def __init__(self,
enc_hid_dim: int,
dec_hid_dim: int,
attn_dim: int):
super().__init__()
self.enc_hid_dim = enc_hid_dim
self.dec_hid_dim = dec_hid_dim
self.attn_in = (enc_hid_dim * 2) + dec_hid_dim
self.attn = nn.Linear(self.attn_in, attn_dim)
def forward(self,
decoder_hidden: Tensor,
encoder_outputs: Tensor) -> Tensor:
src_len = encoder_outputs.shape[0]
repeated_decoder_hidden = decoder_hidden.unsqueeze(1).repeat(1, src_len, 1)
encoder_outputs = encoder_outputs.permute(1, 0, 2)
energy = torch.tanh(self.attn(torch.cat((
repeated_decoder_hidden,
encoder_outputs),
dim = 2)))
attention = torch.sum(energy, dim=2)
return F.softmax(attention, dim=1)
class Decoder(nn.Module):
def __init__(self,
output_dim: int,
emb_dim: int,
enc_hid_dim: int,
dec_hid_dim: int,
dropout: int,
attention: nn.Module):
super().__init__()
self.emb_dim = emb_dim
self.enc_hid_dim = enc_hid_dim
self.dec_hid_dim = dec_hid_dim
self.output_dim = output_dim
self.dropout = dropout
self.attention = attention
self.embedding = nn.Embedding(output_dim, emb_dim)
self.rnn = nn.GRU((enc_hid_dim * 2) + emb_dim, dec_hid_dim)
self.out = nn.Linear(self.attention.attn_in + emb_dim, output_dim)
self.dropout = nn.Dropout(dropout)
def _weighted_encoder_rep(self,
decoder_hidden: Tensor,
encoder_outputs: Tensor) -> Tensor:
a = self.attention(decoder_hidden, encoder_outputs)
a = a.unsqueeze(1)
encoder_outputs = encoder_outputs.permute(1, 0, 2)
weighted_encoder_rep = torch.bmm(a, encoder_outputs)
weighted_encoder_rep = weighted_encoder_rep.permute(1, 0, 2)
return weighted_encoder_rep
def forward(self,
input: Tensor,
decoder_hidden: Tensor,
encoder_outputs: Tensor) -> Tuple[Tensor]:
input = input.unsqueeze(0)
embedded = self.dropout(self.embedding(input))
weighted_encoder_rep = self._weighted_encoder_rep(decoder_hidden,
encoder_outputs)
rnn_input = torch.cat((embedded, weighted_encoder_rep), dim = 2)
output, decoder_hidden = self.rnn(rnn_input, decoder_hidden.unsqueeze(0))
embedded = embedded.squeeze(0)
output = output.squeeze(0)
weighted_encoder_rep = weighted_encoder_rep.squeeze(0)
output = self.out(torch.cat((output,
weighted_encoder_rep,
embedded), dim = 1))
return output, decoder_hidden.squeeze(0)
class Seq2Seq(nn.Module):
def __init__(self,
encoder: nn.Module,
decoder: nn.Module,
device: torch.device):
super().__init__()
self.encoder = encoder
self.decoder = decoder
self.device = device
def forward(self,
src: Tensor,
trg: Tensor,
teacher_forcing_ratio: float = 0.5) -> Tensor:
batch_size = src.shape[1]
max_len = trg.shape[0]
trg_vocab_size = self.decoder.output_dim
outputs = torch.zeros(max_len, batch_size, trg_vocab_size).to(self.device)
encoder_outputs, hidden = self.encoder(src)
# first input to the decoder is the <sos> token
output = trg[0,:]
for t in range(1, max_len):
output, hidden = self.decoder(output, hidden, encoder_outputs)
outputs[t] = output
teacher_force = random.random() < teacher_forcing_ratio
top1 = output.max(1)[1]
output = (trg[t] if teacher_force else top1)
return outputs
INPUT_DIM = len(de_vocab)
OUTPUT_DIM = len(en_vocab)
# ENC_EMB_DIM = 256
# DEC_EMB_DIM = 256
# ENC_HID_DIM = 512
# DEC_HID_DIM = 512
# ATTN_DIM = 64
# ENC_DROPOUT = 0.5
# DEC_DROPOUT = 0.5
ENC_EMB_DIM = 32
DEC_EMB_DIM = 32
ENC_HID_DIM = 64
DEC_HID_DIM = 64
ATTN_DIM = 8
ENC_DROPOUT = 0.5
DEC_DROPOUT = 0.5
enc = Encoder(INPUT_DIM, ENC_EMB_DIM, ENC_HID_DIM, DEC_HID_DIM, ENC_DROPOUT)
attn = Attention(ENC_HID_DIM, DEC_HID_DIM, ATTN_DIM)
dec = Decoder(OUTPUT_DIM, DEC_EMB_DIM, ENC_HID_DIM, DEC_HID_DIM, DEC_DROPOUT, attn)
model = Seq2Seq(enc, dec, device).to(device)
def init_weights(m: nn.Module):
for name, param in m.named_parameters():
if 'weight' in name:
nn.init.normal_(param.data, mean=0, std=0.01)
else:
nn.init.constant_(param.data, 0)
model.apply(init_weights)
optimizer = optim.Adam(model.parameters())
def count_parameters(model: nn.Module):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
print(f'The model has {count_parameters(model):,} trainable parameters')
注意：特别是在对语言翻译模型的性能进行评分时，我们必须告诉 nn.CrossEntropyLoss 函数忽略目标只是填充的索引。
PAD_IDX = en_vocab.stoi['<pad>']
criterion = nn.CrossEntropyLoss(ignore_index=PAD_IDX)
最后，我们可以训练和评估此模型。
import math
import time
def train(model: nn.Module,
iterator: torch.utils.data.DataLoader,
optimizer: optim.Optimizer,
criterion: nn.Module,
clip: float):
model.train()
epoch_loss = 0
for _, (src, trg) in enumerate(iterator):
src, trg = src.to(device), trg.to(device)
optimizer.zero_grad()
output = model(src, trg)
output = output[1:].view(-1, output.shape[-1])
trg = trg[1:].view(-1)
loss = criterion(output, trg)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), clip)
optimizer.step()
epoch_loss += loss.item()
return epoch_loss / len(iterator)
def evaluate(model: nn.Module,
iterator: torch.utils.data.DataLoader,
criterion: nn.Module):
model.eval()
epoch_loss = 0
with torch.no_grad():
for _, (src, trg) in enumerate(iterator):
src, trg = src.to(device), trg.to(device)
output = model(src, trg, 0) #turn off teacher forcing
output = output[1:].view(-1, output.shape[-1])
trg = trg[1:].view(-1)
loss = criterion(output, trg)
epoch_loss += loss.item()
return epoch_loss / len(iterator)
def epoch_time(start_time: int,
end_time: int):
elapsed_time = end_time - start_time
elapsed_mins = int(elapsed_time / 60)
elapsed_secs = int(elapsed_time - (elapsed_mins * 60))
return elapsed_mins, elapsed_secs
N_EPOCHS = 10
CLIP = 1
best_valid_loss = float('inf')
for epoch in range(N_EPOCHS):
start_time = time.time()
train_loss = train(model, train_iter, optimizer, criterion, CLIP)
valid_loss = evaluate(model, valid_iter, criterion)
end_time = time.time()
epoch_mins, epoch_secs = epoch_time(start_time, end_time)
print(f'Epoch: {epoch+1:02} | Time: {epoch_mins}m {epoch_secs}s')
print(f'\tTrain Loss: {train_loss:.3f} | Train PPL: {math.exp(train_loss):7.3f}')
print(f'\t Val. Loss: {valid_loss:.3f} | Val. PPL: {math.exp(valid_loss):7.3f}')
test_loss = evaluate(model, test_iter, criterion)
print(f'| Test Loss: {test_loss:.3f} | Test PPL: {math.exp(test_loss):7.3f} |')
