기초부터 시작하는 NLP: Sequence to Sequence 네트워크와 Attention을 이용한 번역¶

class EncoderRNN(nn.Module):
    def __init__(self, input_size, hidden_size, dropout_p=0.1):
        super(EncoderRNN, self).__init__()
        self.hidden_size = hidden_size

        self.embedding = nn.Embedding(input_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size, batch_first=True)
        self.dropout = nn.Dropout(dropout_p)

    def forward(self, input):
        embedded = self.dropout(self.embedding(input))
        output, hidden = self.gru(embedded)
        return output, hidden

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)

def get_dataloader(batch_size):
    input_lang, output_lang, pairs = prepareData('eng', 'fra', True)

    n = len(pairs)
    input_ids = np.zeros((n, MAX_LENGTH), dtype=np.int32)
    target_ids = np.zeros((n, MAX_LENGTH), dtype=np.int32)

    for idx, (inp, tgt) in enumerate(pairs):
        inp_ids = indexesFromSentence(input_lang, inp)
        tgt_ids = indexesFromSentence(output_lang, tgt)
        inp_ids.append(EOS_token)
        tgt_ids.append(EOS_token)
        input_ids[idx, :len(inp_ids)] = inp_ids
        target_ids[idx, :len(tgt_ids)] = tgt_ids

    train_data = TensorDataset(torch.LongTensor(input_ids).to(device),
                               torch.LongTensor(target_ids).to(device))

    train_sampler = RandomSampler(train_data)
    train_dataloader = DataLoader(train_data, sampler=train_sampler, batch_size=batch_size)
    return input_lang, output_lang, train_dataloader

def train_epoch(dataloader, encoder, decoder, encoder_optimizer,
          decoder_optimizer, criterion):

    total_loss = 0
    for data in dataloader:
        input_tensor, target_tensor = data

        encoder_optimizer.zero_grad()
        decoder_optimizer.zero_grad()

        encoder_outputs, encoder_hidden = encoder(input_tensor)
        decoder_outputs, _, _ = decoder(encoder_outputs, encoder_hidden, target_tensor)

        loss = criterion(
            decoder_outputs.view(-1, decoder_outputs.size(-1)),
            target_tensor.view(-1)
        )
        loss.backward()

        encoder_optimizer.step()
        decoder_optimizer.step()

        total_loss += loss.item()

    return total_loss / len(dataloader)

import time
import math

def asMinutes(s):
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)

def timeSince(since, percent):
    now = time.time()
    s = now - since
    es = s / (percent)
    rs = es - s
    return '%s (- %s)' % (asMinutes(s), asMinutes(rs))

def train(train_dataloader, encoder, decoder, n_epochs, learning_rate=0.001,
               print_every=100, plot_every=100):
    start = time.time()
    plot_losses = []
    print_loss_total = 0  # Reset every print_every
    plot_loss_total = 0  # Reset every plot_every

    encoder_optimizer = optim.Adam(encoder.parameters(), lr=learning_rate)
    decoder_optimizer = optim.Adam(decoder.parameters(), lr=learning_rate)
    criterion = nn.NLLLoss()

    for epoch in range(1, n_epochs + 1):
        loss = train_epoch(train_dataloader, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion)
        print_loss_total += loss
        plot_loss_total += loss

        if epoch % print_every == 0:
            print_loss_avg = print_loss_total / print_every
            print_loss_total = 0
            print('%s (%d %d%%) %.4f' % (timeSince(start, epoch / n_epochs),
                                        epoch, epoch / n_epochs * 100, print_loss_avg))

        if epoch % plot_every == 0:
            plot_loss_avg = plot_loss_total / plot_every
            plot_losses.append(plot_loss_avg)
            plot_loss_total = 0

    showPlot(plot_losses)

import matplotlib.pyplot as plt
plt.switch_backend('agg')
import matplotlib.ticker as ticker
import numpy as np

def showPlot(points):
    plt.figure()
    fig, ax = plt.subplots()
    # 주기적인 간격으로 이 locator가 tick을 설정
    loc = ticker.MultipleLocator(base=0.2)
    ax.yaxis.set_major_locator(loc)
    plt.plot(points)

def showAttention(input_sentence, output_words, attentions):
    fig = plt.figure()
    ax = fig.add_subplot(111)
    cax = ax.matshow(attentions.cpu().numpy(), cmap='bone')
    fig.colorbar(cax)

    # 축 설정
    ax.set_xticklabels([''] + input_sentence.split(' ') +
                       ['<EOS>'], rotation=90)
    ax.set_yticklabels([''] + output_words)

    # 매 틱마다 라벨 보여주기
    ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
    ax.yaxis.set_major_locator(ticker.MultipleLocator(1))

    plt.show()


def evaluateAndShowAttention(input_sentence):
    output_words, attentions = evaluate(encoder, decoder, input_sentence, input_lang, output_lang)
    print('input =', input_sentence)
    print('output =', ' '.join(output_words))
    showAttention(input_sentence, output_words, attentions[0, :len(output_words), :])


evaluateAndShowAttention('il n est pas aussi grand que son pere')

evaluateAndShowAttention('je suis trop fatigue pour conduire')

evaluateAndShowAttention('je suis desole si c est une question idiote')

evaluateAndShowAttention('je suis reellement fiere de vous')