def nmt():
if request.method == 'POST':
text = request.form['sent']
EMBED_SIZE = 256
HIDDEN_SIZE = 512
DROPOUT_RATE = 0.2
BATCH_SIZE = 256
NUM_TRAIN_STEPS = 10
VOCAB = Vocab.load('VOCAB_FILE')
vocab_inp_size = len(VOCAB.src) + 1
vocab_tar_size = len(VOCAB.tgt) + 1
model = NMT(vocab_inp_size, vocab_tar_size, EMBED_SIZE, HIDDEN_SIZE,
BATCH_SIZE)
sample_hidden = model.encoder.initialize_hidden_state()
sample_output, sample_hidden = model.encoder(
tf.random.uniform((BATCH_SIZE, 1)), sample_hidden)
sample_decoder_output, _, _ = model.decoder(
tf.random.uniform((BATCH_SIZE, 1)), sample_hidden, sample_output)
model.load_weights('es_en')
pred = decode_sentence(model, text, VOCAB)
return render_template('home.html', result=pred)
dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)
print("deleting files not required...")
del src_sents, tgt_sents, src_pad, tgt_pad
print("beginning training...")
train(dataset, EMBED_SIZE, HIDDEN_SIZE, DROPOUT_RATE, BATCH_SIZE,
NUM_TRAIN_STEPS, BUFFER_SIZE, steps_per_epoch, vocab_inp_size,
vocab_tar_size, VOCAB)
print("training complete!")
if args['decode']:
print('reading vocabulary file: %s' % args['--vocab'])
VOCAB = Vocab.load(args['--vocab'])
vocab_inp_size = len(VOCAB.src) + 1
vocab_tar_size = len(VOCAB.tgt) + 1
print('restoring pre-trained model')
model = NMT(vocab_inp_size, vocab_tar_size, EMBED_SIZE, HIDDEN_SIZE,
BATCH_SIZE)
sample_hidden = model.encoder.initialize_hidden_state()
sample_output, sample_hidden = model.encoder(
tf.random.uniform((BATCH_SIZE, 1)), sample_hidden)
sample_decoder_output, _, _ = model.decoder(
tf.random.uniform((BATCH_SIZE, 1)), sample_hidden, sample_output)
model.load_weights(args['--model-file'])
print("beginning decoding...")
decode(model, args['--sent-file'], VOCAB, 0)