• 教程 >
  • 使用 nn.Transformer 和 torchtext 进行语言翻译
快捷方式

使用 nn.Transformer 和 torchtext 进行语言翻译

本教程展示
  • 如何使用 Transformer 从头开始训练翻译模型。

  • 使用 torchtext 库访问 Multi30k 数据集训练德语到英语的翻译模型。

数据来源和处理

torchtext 库 包含用于创建数据集的实用程序,这些数据集可以轻松地迭代,用于创建语言翻译模型。在本例中,我们将展示如何使用 torchtext 的内置数据集,对原始文本句子进行标记,构建词汇表,并将标记数字化为张量。我们将使用 torchtext 库中的 Multi30k 数据集,它会生成一对源语言-目标语言原始句子。

要访问 torchtext 数据集,请按照 https://github.com/pytorch/data 中的说明安装 torchdata。

from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator
from torchtext.datasets import multi30k, Multi30k
from typing import Iterable, List


# We need to modify the URLs for the dataset since the links to the original dataset are broken
# Refer to https://github.com/pytorch/text/issues/1756#issuecomment-1163664163 for more info
multi30k.URL["train"] = "https://raw.githubusercontent.com/neychev/small_DL_repo/master/datasets/Multi30k/training.tar.gz"
multi30k.URL["valid"] = "https://raw.githubusercontent.com/neychev/small_DL_repo/master/datasets/Multi30k/validation.tar.gz"

SRC_LANGUAGE = 'de'
TGT_LANGUAGE = 'en'

# Place-holders
token_transform = {}
vocab_transform = {}

创建源语言和目标语言标记器。请确保安装了依赖项。

pip install -U torchdata
pip install -U spacy
python -m spacy download en_core_web_sm
python -m spacy download de_core_news_sm
token_transform[SRC_LANGUAGE] = get_tokenizer('spacy', language='de_core_news_sm')
token_transform[TGT_LANGUAGE] = get_tokenizer('spacy', language='en_core_web_sm')


# helper function to yield list of tokens
def yield_tokens(data_iter: Iterable, language: str) -> List[str]:
    language_index = {SRC_LANGUAGE: 0, TGT_LANGUAGE: 1}

    for data_sample in data_iter:
        yield token_transform[language](data_sample[language_index[language]])

# Define special symbols and indices
UNK_IDX, PAD_IDX, BOS_IDX, EOS_IDX = 0, 1, 2, 3
# Make sure the tokens are in order of their indices to properly insert them in vocab
special_symbols = ['<unk>', '<pad>', '<bos>', '<eos>']

for ln in [SRC_LANGUAGE, TGT_LANGUAGE]:
    # Training data Iterator
    train_iter = Multi30k(split='train', language_pair=(SRC_LANGUAGE, TGT_LANGUAGE))
    # Create torchtext's Vocab object
    vocab_transform[ln] = build_vocab_from_iterator(yield_tokens(train_iter, ln),
                                                    min_freq=1,
                                                    specials=special_symbols,
                                                    special_first=True)

# Set ``UNK_IDX`` as the default index. This index is returned when the token is not found.
# If not set, it throws ``RuntimeError`` when the queried token is not found in the Vocabulary.
for ln in [SRC_LANGUAGE, TGT_LANGUAGE]:
  vocab_transform[ln].set_default_index(UNK_IDX)

使用 Transformer 的 Seq2Seq 网络

Transformer 是 “Attention is all you need” 论文中提出的一种用于解决机器翻译任务的 Seq2Seq 模型。下面,我们将创建一个使用 Transformer 的 Seq2Seq 网络。该网络包含三个部分。第一部分是嵌入层。该层将输入索引的张量转换为相应的输入嵌入张量。这些嵌入进一步用位置编码进行增强,以向模型提供输入标记的位置信息。第二部分是实际的 Transformer 模型。最后,Transformer 模型的输出将通过线性层,该层会为目标语言中的每个标记提供未标准化的概率。

from torch import Tensor
import torch
import torch.nn as nn
from torch.nn import Transformer
import math
DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# helper Module that adds positional encoding to the token embedding to introduce a notion of word order.
class PositionalEncoding(nn.Module):
    def __init__(self,
                 emb_size: int,
                 dropout: float,
                 maxlen: int = 5000):
        super(PositionalEncoding, self).__init__()
        den = torch.exp(- torch.arange(0, emb_size, 2)* math.log(10000) / emb_size)
        pos = torch.arange(0, maxlen).reshape(maxlen, 1)
        pos_embedding = torch.zeros((maxlen, emb_size))
        pos_embedding[:, 0::2] = torch.sin(pos * den)
        pos_embedding[:, 1::2] = torch.cos(pos * den)
        pos_embedding = pos_embedding.unsqueeze(-2)

        self.dropout = nn.Dropout(dropout)
        self.register_buffer('pos_embedding', pos_embedding)

    def forward(self, token_embedding: Tensor):
        return self.dropout(token_embedding + self.pos_embedding[:token_embedding.size(0), :])

# helper Module to convert tensor of input indices into corresponding tensor of token embeddings
class TokenEmbedding(nn.Module):
    def __init__(self, vocab_size: int, emb_size):
        super(TokenEmbedding, self).__init__()
        self.embedding = nn.Embedding(vocab_size, emb_size)
        self.emb_size = emb_size

    def forward(self, tokens: Tensor):
        return self.embedding(tokens.long()) * math.sqrt(self.emb_size)

# Seq2Seq Network
class Seq2SeqTransformer(nn.Module):
    def __init__(self,
                 num_encoder_layers: int,
                 num_decoder_layers: int,
                 emb_size: int,
                 nhead: int,
                 src_vocab_size: int,
                 tgt_vocab_size: int,
                 dim_feedforward: int = 512,
                 dropout: float = 0.1):
        super(Seq2SeqTransformer, self).__init__()
        self.transformer = Transformer(d_model=emb_size,
                                       nhead=nhead,
                                       num_encoder_layers=num_encoder_layers,
                                       num_decoder_layers=num_decoder_layers,
                                       dim_feedforward=dim_feedforward,
                                       dropout=dropout)
        self.generator = nn.Linear(emb_size, tgt_vocab_size)
        self.src_tok_emb = TokenEmbedding(src_vocab_size, emb_size)
        self.tgt_tok_emb = TokenEmbedding(tgt_vocab_size, emb_size)
        self.positional_encoding = PositionalEncoding(
            emb_size, dropout=dropout)

    def forward(self,
                src: Tensor,
                trg: Tensor,
                src_mask: Tensor,
                tgt_mask: Tensor,
                src_padding_mask: Tensor,
                tgt_padding_mask: Tensor,
                memory_key_padding_mask: Tensor):
        src_emb = self.positional_encoding(self.src_tok_emb(src))
        tgt_emb = self.positional_encoding(self.tgt_tok_emb(trg))
        outs = self.transformer(src_emb, tgt_emb, src_mask, tgt_mask, None,
                                src_padding_mask, tgt_padding_mask, memory_key_padding_mask)
        return self.generator(outs)

    def encode(self, src: Tensor, src_mask: Tensor):
        return self.transformer.encoder(self.positional_encoding(
                            self.src_tok_emb(src)), src_mask)

    def decode(self, tgt: Tensor, memory: Tensor, tgt_mask: Tensor):
        return self.transformer.decoder(self.positional_encoding(
                          self.tgt_tok_emb(tgt)), memory,
                          tgt_mask)

在训练过程中,我们需要一个后续词掩码,以防止模型在进行预测时查看未来的词。我们还需要掩码来隐藏源和目标填充标记。下面,让我们定义一个函数来处理这两者。

def generate_square_subsequent_mask(sz):
    mask = (torch.triu(torch.ones((sz, sz), device=DEVICE)) == 1).transpose(0, 1)
    mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
    return mask


def create_mask(src, tgt):
    src_seq_len = src.shape[0]
    tgt_seq_len = tgt.shape[0]

    tgt_mask = generate_square_subsequent_mask(tgt_seq_len)
    src_mask = torch.zeros((src_seq_len, src_seq_len),device=DEVICE).type(torch.bool)

    src_padding_mask = (src == PAD_IDX).transpose(0, 1)
    tgt_padding_mask = (tgt == PAD_IDX).transpose(0, 1)
    return src_mask, tgt_mask, src_padding_mask, tgt_padding_mask

现在让我们定义模型的参数并实例化它。下面,我们还定义了我们的损失函数,即交叉熵损失,以及用于训练的优化器。

torch.manual_seed(0)

SRC_VOCAB_SIZE = len(vocab_transform[SRC_LANGUAGE])
TGT_VOCAB_SIZE = len(vocab_transform[TGT_LANGUAGE])
EMB_SIZE = 512
NHEAD = 8
FFN_HID_DIM = 512
BATCH_SIZE = 128
NUM_ENCODER_LAYERS = 3
NUM_DECODER_LAYERS = 3

transformer = Seq2SeqTransformer(NUM_ENCODER_LAYERS, NUM_DECODER_LAYERS, EMB_SIZE,
                                 NHEAD, SRC_VOCAB_SIZE, TGT_VOCAB_SIZE, FFN_HID_DIM)

for p in transformer.parameters():
    if p.dim() > 1:
        nn.init.xavier_uniform_(p)

transformer = transformer.to(DEVICE)

loss_fn = torch.nn.CrossEntropyLoss(ignore_index=PAD_IDX)

optimizer = torch.optim.Adam(transformer.parameters(), lr=0.0001, betas=(0.9, 0.98), eps=1e-9)

整理

Data Sourcing and Processing 部分所示,我们的数据迭代器会生成一对原始字符串。我们需要将这些字符串对转换为可以由我们之前定义的 Seq2Seq 网络处理的批处理张量。下面我们定义整理函数,该函数将一批原始字符串转换为可以直接输入到模型的批处理张量。

from torch.nn.utils.rnn import pad_sequence

# helper function to club together sequential operations
def sequential_transforms(*transforms):
    def func(txt_input):
        for transform in transforms:
            txt_input = transform(txt_input)
        return txt_input
    return func

# function to add BOS/EOS and create tensor for input sequence indices
def tensor_transform(token_ids: List[int]):
    return torch.cat((torch.tensor([BOS_IDX]),
                      torch.tensor(token_ids),
                      torch.tensor([EOS_IDX])))

# ``src`` and ``tgt`` language text transforms to convert raw strings into tensors indices
text_transform = {}
for ln in [SRC_LANGUAGE, TGT_LANGUAGE]:
    text_transform[ln] = sequential_transforms(token_transform[ln], #Tokenization
                                               vocab_transform[ln], #Numericalization
                                               tensor_transform) # Add BOS/EOS and create tensor


# function to collate data samples into batch tensors
def collate_fn(batch):
    src_batch, tgt_batch = [], []
    for src_sample, tgt_sample in batch:
        src_batch.append(text_transform[SRC_LANGUAGE](src_sample.rstrip("\n")))
        tgt_batch.append(text_transform[TGT_LANGUAGE](tgt_sample.rstrip("\n")))

    src_batch = pad_sequence(src_batch, padding_value=PAD_IDX)
    tgt_batch = pad_sequence(tgt_batch, padding_value=PAD_IDX)
    return src_batch, tgt_batch

让我们定义一个训练和评估循环,该循环将在每个 epoch 调用。

from torch.utils.data import DataLoader

def train_epoch(model, optimizer):
    model.train()
    losses = 0
    train_iter = Multi30k(split='train', language_pair=(SRC_LANGUAGE, TGT_LANGUAGE))
    train_dataloader = DataLoader(train_iter, batch_size=BATCH_SIZE, collate_fn=collate_fn)

    for src, tgt in train_dataloader:
        src = src.to(DEVICE)
        tgt = tgt.to(DEVICE)

        tgt_input = tgt[:-1, :]

        src_mask, tgt_mask, src_padding_mask, tgt_padding_mask = create_mask(src, tgt_input)

        logits = model(src, tgt_input, src_mask, tgt_mask,src_padding_mask, tgt_padding_mask, src_padding_mask)

        optimizer.zero_grad()

        tgt_out = tgt[1:, :]
        loss = loss_fn(logits.reshape(-1, logits.shape[-1]), tgt_out.reshape(-1))
        loss.backward()

        optimizer.step()
        losses += loss.item()

    return losses / len(list(train_dataloader))


def evaluate(model):
    model.eval()
    losses = 0

    val_iter = Multi30k(split='valid', language_pair=(SRC_LANGUAGE, TGT_LANGUAGE))
    val_dataloader = DataLoader(val_iter, batch_size=BATCH_SIZE, collate_fn=collate_fn)

    for src, tgt in val_dataloader:
        src = src.to(DEVICE)
        tgt = tgt.to(DEVICE)

        tgt_input = tgt[:-1, :]

        src_mask, tgt_mask, src_padding_mask, tgt_padding_mask = create_mask(src, tgt_input)

        logits = model(src, tgt_input, src_mask, tgt_mask,src_padding_mask, tgt_padding_mask, src_padding_mask)

        tgt_out = tgt[1:, :]
        loss = loss_fn(logits.reshape(-1, logits.shape[-1]), tgt_out.reshape(-1))
        losses += loss.item()

    return losses / len(list(val_dataloader))

现在我们拥有了训练模型的所有成分。让我们开始吧!

from timeit import default_timer as timer
NUM_EPOCHS = 18

for epoch in range(1, NUM_EPOCHS+1):
    start_time = timer()
    train_loss = train_epoch(transformer, optimizer)
    end_time = timer()
    val_loss = evaluate(transformer)
    print((f"Epoch: {epoch}, Train loss: {train_loss:.3f}, Val loss: {val_loss:.3f}, "f"Epoch time = {(end_time - start_time):.3f}s"))


# function to generate output sequence using greedy algorithm
def greedy_decode(model, src, src_mask, max_len, start_symbol):
    src = src.to(DEVICE)
    src_mask = src_mask.to(DEVICE)

    memory = model.encode(src, src_mask)
    ys = torch.ones(1, 1).fill_(start_symbol).type(torch.long).to(DEVICE)
    for i in range(max_len-1):
        memory = memory.to(DEVICE)
        tgt_mask = (generate_square_subsequent_mask(ys.size(0))
                    .type(torch.bool)).to(DEVICE)
        out = model.decode(ys, memory, tgt_mask)
        out = out.transpose(0, 1)
        prob = model.generator(out[:, -1])
        _, next_word = torch.max(prob, dim=1)
        next_word = next_word.item()

        ys = torch.cat([ys,
                        torch.ones(1, 1).type_as(src.data).fill_(next_word)], dim=0)
        if next_word == EOS_IDX:
            break
    return ys


# actual function to translate input sentence into target language
def translate(model: torch.nn.Module, src_sentence: str):
    model.eval()
    src = text_transform[SRC_LANGUAGE](src_sentence).view(-1, 1)
    num_tokens = src.shape[0]
    src_mask = (torch.zeros(num_tokens, num_tokens)).type(torch.bool)
    tgt_tokens = greedy_decode(
        model,  src, src_mask, max_len=num_tokens + 5, start_symbol=BOS_IDX).flatten()
    return " ".join(vocab_transform[TGT_LANGUAGE].lookup_tokens(list(tgt_tokens.cpu().numpy()))).replace("<bos>", "").replace("<eos>", "")
print(translate(transformer, "Eine Gruppe von Menschen steht vor einem Iglu ."))

文档

访问 PyTorch 的全面开发人员文档

查看文档

教程

获取针对初学者和高级开发人员的深入教程

查看教程

资源

查找开发资源并获得答案

查看资源