print_loss_total += loss
plot_loss_total += loss
if iter % print_every == 0:
print_loss_avg = print_loss_total / print_every
print_loss_total = 0
print('%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_every
plot_losses.append(plot_loss_avg)
plot_loss_total = 0
showPlot(plot_losses)
plt.savefig('base-lstm-loss')
torch.save(encoder.state_dict(), 'encoder.pth')
torch.save(decoder.state_dict(), 'decoder.pth')
if __name__ == "__main__":
hidden_size = 256
n_iters = 910000
teacher_forcing_ratio = 0.5
input_lang, output_lang, pairs = loader.prepareData('eng', 'fra', True)
encoder = seq2seq.Encoder(input_lang.n_words, hidden_size).to(device)
decoder = seq2seq.Decoder(hidden_size, output_lang.n_words).to(device)
trainiters(encoder, decoder, n_iters)
translate(pair, output_sentence)
ref = pair[1].split()
hyp = output_words
scores.append(sentence_bleu([ref], hyp, smoothing_function = cc.method3) * 100.)
print("BLEU: {:.4}".format(sum(scores)/len(test_pairs)))
if __name__ == "__main__":
"""
Evaluation is mostly the same as training,
but there are no targets so we simply feed the decoder's predictions back to itself for each step.
Every time it predict a word, we add it to the output string
and if it predicts the EOS token we step there.
"""
config = argparser()
input_lang, output_lang, pairs = loader.prepareData(config.srcLang, config.tgtLang, True)
encoder = seq2seq.LSTMEncoder(input_size = input_lang.n_words, embedding_size \
= config.embedding_size, hidden_size = config.hidden_size).to(device)
decoder = seq2seq.LSTMDecoder(output_size = output_lang.n_words, embedding_size \
= config.embedding_size, hidden_size = config.hidden_size).to(device)
encoder.load_state_dict(torch.load(config.encoder))
encoder.eval()
decoder.load_state_dict(torch.load(config.decoder))
decoder.eval()
evaluateiters(pairs, encoder, decoder)
