N7翻译实战

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊# 前言## 前言
本周完成项目实战用于训练一个简单的序列到序列（seq2seq）模型以实现英语到法语的翻译。数据预处理、模型构建、训练以及可视化损失的过程。

环境设置

首先，导入必要的库并设置设备：

from __future__ import unicode_literals, print_function, division
from io import open
import unicodedata
import string
import re
import randomimport torch
import torch.nn as nn
from torch import optim
import torch.nn.functional as Fdevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

数据预处理

定义数据处理的辅助类和函数：

SOS_token = 0
EOS_token = 1class Lang:def __init__(self, name):self.name = nameself.word2index = {}self.word2count = {}self.index2word = {0: "SOS", 1: "EOS"}self.n_words = 2def addSentence(self, sentence):for word in sentence.split(' '):self.addWord(word)def addWord(self, word):if word not in self.word2index:self.word2index[word] = self.n_wordsself.word2count[word] = 1self.index2word[self.n_words] = wordself.n_words += 1else:self.word2count[word] += 1def unicodeToAscii(s):return ''.join(c for c in unicodedata.normalize('NFD', s)if unicodedata.category(c) != 'Mn')def normalizeString(s):s = unicodeToAscii(s.lower().strip())s = re.sub(r"([.!?])", r" \1", s)s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)return sdef readLangs(lang1, lang2, reverse=False):print("Reading lines...")lines = open('%s-%s.txt' % (lang1, lang2), encoding='utf-8').read().strip().split('\n')pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]if reverse:pairs = [list(reversed(p)) for p in pairs]input_lang = Lang(lang2)output_lang = Lang(lang1)else:input_lang = Lang(lang1)output_lang = Lang(lang2)return input_lang, output_lang, pairsMAX_LENGTH = 10eng_prefixes = ("i am ", "i m ","he is", "he s ","she is", "she s ","you are", "you re ","we are", "we re ","they are", "they re "
)def filterPair(p):return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH and p[1].startswith(eng_prefixes)def filterPairs(pairs):return [pair for pair in pairs if filterPair(pair)]def prepareData(lang1, lang2, reverse=False):input_lang, output_lang, pairs = readLangs(lang1, lang2, reverse)print("Read %s sentence pairs" % len(pairs))pairs = filterPairs(pairs[:])print("Trimmed to %s sentence pairs" % len(pairs))print("Counting words...")for pair in pairs:input_lang.addSentence(pair[0])output_lang.addSentence(pair[1])print("Counted words:")print(input_lang.name, input_lang.n_words)print(output_lang.name, output_lang.n_words)return input_lang, output_lang, pairsinput_lang, output_lang, pairs = prepareData('eng', 'fra', True)
print(random.choice(pairs))

模型构建

构建编码器和解码器模型：

class EncoderRNN(nn.Module):def __init__(self, input_size, hidden_size):super(EncoderRNN, self).__init__()self.hidden_size = hidden_sizeself.embedding = nn.Embedding(input_size, hidden_size)self.gru = nn.GRU(hidden_size, hidden_size)def forward(self, input, hidden):embedded = self.embedding(input).view(1, 1, -1)output = embeddedoutput, hidden = self.gru(output, hidden)return output, hiddendef initHidden(self):return torch.zeros(1, 1, self.hidden_size, device=device)class DecoderRNN(nn.Module):def __init__(self, hidden_size, output_size):super(DecoderRNN, self).__init__()self.hidden_size = hidden_sizeself.embedding = nn.Embedding(output_size, hidden_size)self.gru = nn.GRU(hidden_size, hidden_size)self.out = nn.Linear(hidden_size, output_size)self.softmax = nn.LogSoftmax(dim=1)def forward(self, input, hidden):output = self.embedding(input).view(1, 1, -1)output = F.relu(output)output, hidden = self.gru(output, hidden)output = self.softmax(self.out(output[0]))return output, hiddendef initHidden(self):return torch.zeros(1, 1, self.hidden_size, device=device)

数据转换

将文本转化为张量：

def indexesFromSentence(lang, sentence):return [lang.word2index[word] for word in sentence.split(' ')]def tensorFromSentence(lang, sentence):indexes = indexesFromSentence(lang, sentence)indexes.append(EOS_token)return torch.tensor(indexes, dtype=torch.long, device=device).view(-1, 1)def tensorsFromPair(pair):input_tensor = tensorFromSentence(input_lang, pair[0])target_tensor = tensorFromSentence(output_lang, pair[1])return (input_tensor, target_tensor)

训练过程

定义训练函数：

teacher_forcing_ratio = 0.5def train(input_tensor, target_tensor, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion, max_length=MAX_LENGTH):encoder_hidden = encoder.initHidden()encoder_optimizer.zero_grad()decoder_optimizer.zero_grad()input_length = input_tensor.size(0)target_length = target_tensor.size(0)encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)loss = 0for ei in range(input_length):encoder_output, encoder_hidden = encoder(input_tensor[ei], encoder_hidden)encoder_outputs[ei] = encoder_output[0, 0]decoder_input = torch.tensor([[SOS_token]], device=device)decoder_hidden = encoder_hiddenuse_teacher_forcing = True if random.random() < teacher_forcing_ratio else Falseif use_teacher_forcing:for di in range(target_length):decoder_output, decoder_hidden = decoder(decoder_input, decoder_hidden)loss += criterion(decoder_output, target_tensor[di])decoder_input = target_tensor[di]else:for di in range(target_length):decoder_output, decoder_hidden = decoder(decoder_input, decoder_hidden)topv, topi = decoder_output.topk(1)decoder_input = topi.squeeze().detach()loss += criterion(decoder_output, target_tensor[di])if decoder_input.item() == EOS_token:breakloss.backward()encoder_optimizer.step()decoder_optimizer.step()return loss.item() / target_length

训练模型

定义训练迭代：

import time
import mathdef asMinutes(s):m = math.floor(s / 60)s -= m * 60return '%dm %ds' % (m, s)def timeSince(since, percent):now = time.time()s = now - sincees = s / (percent)rs = es - sreturn '%s (- %s)' % (asMinutes(s), asMinutes(rs))def trainIters(encoder, decoder, n_iters, print_every=1000, plot_every=100, learning_rate=0.01):start = time.time()plot_losses = []print_loss_total = 0plot_loss_total = 0encoder_optimizer = optim.SGD(encoder.parameters(), lr=learning_rate)decoder_optimizer = optim.SGD(decoder.parameters(), lr=learning_rate)training_pairs = [tensorsFromPair(random.choice(pairs)) for i in range(n_iters)]criterion = nn.NLLLoss()for iter in range(1, n_iters + 1):training_pair = training_pairs[iter - 1]input_tensor = training_pair[0]target_tensor = training_pair[1]loss = train(input_tensor, target_tensor, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion)print_loss_total += lossplot_loss_total += lossif iter % print_every == 0:print_loss_avg = print_loss_total / print_everyprint_loss_total = 0print('%s (%d %d%%) %.4f' % (timeSince(start, iter / n_iters), iter, iter / n_iters * 100, print_loss_avg))if iter % plot_every == 0:plot_loss_avg = plot_loss_total / plot_everyplot_losses.append(plot_loss_avg)plot_loss_total = 0return plot_losses

训练和可视化

初始化模型并开始训练：

hidden_size = 256
encoder1 = EncoderRNN(input_lang.n_words, hidden_size).to(device)
attn_decoder1 = DecoderRNN(hidden_size, output_lang.n_words).to(device)plot_losses = trainIters(encoder1, attn_decoder1, 100000, print_every=5000)import matplotlib.pyplot as plt
import warningswarnings.filterwarnings("ignore")
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['figure.dpi'] = 100epochs_range = range(len(plot_losses))plt.figure(figsize=(8, 3))
plt.subplot(1, 1, 1)
plt.plot(epochs_range, plot_losses, label='Training Loss')
plt.legend(loc='upper right')
plt.title('Training Loss')
plt.show()