def decode():
# Prepare NLC data.
global reverse_vocab, vocab, lm
if FLAGS.lmfile is not None:
print("Loading Language model from %s" % FLAGS.lmfile)
# lm = kenlm.LanguageModel(FLAGS.lmfile)
lm = kenlm.Model(FLAGS.lmfile)
else:
print('No lmfile, better to add kenlm arpa data file')
print("Preparing NLC data in %s" % FLAGS.data_dir)
x_train, y_train, x_dev, y_dev, vocab_path = prepare_nlc_data(
FLAGS.data_dir, FLAGS.max_vocab_size, tokenizer=get_tokenizer())
vocab, reverse_vocab = initialize_vocabulary(vocab_path)
vocab_size = len(vocab)
print("Vocabulary size: %d" % vocab_size)
with tf.Session() as sess:
print("Creating %d layers of %d units." % (FLAGS.num_layers, FLAGS.size))
model = create_model(sess, vocab_size, False)
while True:
sent = input("Enter a sentence: ")
output_sent = fix_sent(model, sess, sent)
print("Candidate: ", output_sent)
def decode():
# Prepare NLC data.
global reverse_vocab, vocab, lm
if FLAGS.lmfile is not None:
print("Loading Language model from %s" % FLAGS.lmfile)
lm = kenlm.Model(FLAGS.lmfile)
else:
print('No lmfile, better to add kenlm arpa data file')
print("Preparing NLC data in %s" % FLAGS.data_dir)
x_train, y_train, x_dev, y_dev, vocab_path = prepare_nlc_data(
FLAGS.data_dir, FLAGS.max_vocab_size, tokenizer=get_tokenizer())
vocab, reverse_vocab = initialize_vocabulary(vocab_path)
vocab_size = len(vocab)
print("Vocabulary size: %d" % vocab_size)
with tf.Session() as sess:
print("Creating %d layers of %d units." % (FLAGS.num_layers, FLAGS.size))
model = create_model(sess, vocab_size, False)
while True:
sent = input("Enter a sentence: ")
output_sent = fix_sent(model, sess, sent)
print("Candidate: ", output_sent)
def tokenize(sent, vocab, depth=FLAGS.num_layers):
align = pow(2, depth - 1)
token_ids = sentence_to_token_ids(sent, vocab, get_tokenizer())
ones = [1] * len(token_ids)
pad = (align - len(token_ids)) % align
token_ids += [PAD_ID] * pad
ones += [0] * pad
source = np.array(token_ids).reshape([-1, 1])
mask = np.array(ones).reshape([-1, 1])
return source, mask
def tokenize(sent, vocab, depth=FLAGS.num_layers):
align = pow(2, depth - 1)
token_ids = sentence_to_token_ids(sent, vocab, get_tokenizer())
ones = [1] * len(token_ids)
pad = (align - len(token_ids)) % align
token_ids += [PAD_ID] * pad
ones += [0] * pad
source = np.array(token_ids).reshape([-1, 1])
mask = np.array(ones).reshape([-1, 1])
return source, mask
def setup_batch_decode(sess):
# decode for dev-sets, in batches
global reverse_vocab, vocab, lm
if FLAGS.lmfile is not None:
print("Loading Language model from %s" % FLAGS.lmfile)
lm = kenlm.LanguageModel(FLAGS.lmfile)
print("Preparing NLC data in %s" % FLAGS.data_dir)
x_train, y_train, x_dev, y_dev, vocab_path = prepare_nlc_data(
FLAGS.data_dir, FLAGS.max_vocab_size,
tokenizer=get_tokenizer()) # , other_dev_path="/deep/group/nlp_data/nlc_data/ourdev/bpe")
vocab, reverse_vocab = initialize_vocabulary(vocab_path, bpe=(FLAGS.tokenizer.lower() == "bpe"))
vocab_size = len(vocab)
print("Vocabulary size: %d" % vocab_size)
print("Creating %d layers of %d units." % (FLAGS.num_layers, FLAGS.size))
model = create_model(sess, vocab_size, False)
return model, x_dev, y_dev
def setup_batch_decode(sess):
# decode for dev-sets, in batches
global reverse_vocab, vocab, lm
if FLAGS.lmfile is not None:
print("Loading Language model from %s" % FLAGS.lmfile)
lm = kenlm.LanguageModel(FLAGS.lmfile)
print("Preparing NLC data in %s" % FLAGS.data_dir)
x_train, y_train, x_dev, y_dev, vocab_path = prepare_nlc_data(
FLAGS.data_dir, FLAGS.max_vocab_size,
tokenizer=get_tokenizer()) # , other_dev_path="/deep/group/nlp_data/nlc_data/ourdev/bpe")
vocab, reverse_vocab = initialize_vocabulary(vocab_path, bpe=(FLAGS.tokenizer.lower() == "bpe"))
vocab_size = len(vocab)
print("Vocabulary size: %d" % vocab_size)
print("Creating %d layers of %d units." % (FLAGS.num_layers, FLAGS.size))
model = create_model(sess, vocab_size, False)
return model, x_dev, y_dev
def train():
"""Train a translation model using NLC data."""
# Prepare NLC data.
logging.info("Preparing NLC data in %s" % FLAGS.data_dir)
x_train, y_train, x_dev, y_dev, vocab_path = prepare_nlc_data(
FLAGS.data_dir, FLAGS.max_vocab_size, tokenizer=get_tokenizer())
vocab, _ = initialize_vocabulary(vocab_path)
vocab_size = len(vocab)
logging.info("Vocabulary size: %d" % vocab_size)
if not os.path.exists(FLAGS.train_dir):
os.makedirs(FLAGS.train_dir)
file_handler = logging.FileHandler("{0}/log.txt".format(FLAGS.train_dir))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with tf.Session() as sess:
logging.info("Creating %d layers of %d units." %
(FLAGS.num_layers, FLAGS.size))
model = create_model(sess, vocab_size, False)
logging.info('Initial validation cost: %f' %
validate(model, sess, x_dev, y_dev))
epoch = 0
previous_losses = []
exp_cost = None
exp_length = None
exp_norm = None
total_iters = 0
start_time = time.time()
while FLAGS.epochs == 0 or epoch < FLAGS.epochs:
epoch += 1
current_step = 0
# Train
epoch_tic = time.time()
for source_tokens, source_mask, target_tokens, target_mask in pair_iter(
x_train, y_train, FLAGS.batch_size, FLAGS.num_layers):
# Get a batch and make a step.
grad_norm, cost, param_norm = model.train(
sess, source_tokens, source_mask, target_tokens,
target_mask)
total_iters += np.sum(target_mask)
tps = total_iters / (time.time() - start_time)
current_step += 1
lengths = np.sum(target_mask, axis=0)
mean_length = np.mean(lengths)
std_length = np.std(lengths)
if not exp_cost:
exp_cost = cost
exp_length = mean_length
exp_norm = grad_norm
else:
exp_cost = 0.99 * exp_cost + 0.01 * cost
exp_length = 0.99 * exp_length + 0.01 * mean_length
exp_norm = 0.99 * exp_norm + 0.01 * grad_norm
cost = cost / mean_length
if current_step % FLAGS.print_every == 0:
logging.info(
'epoch %d, iter %d, cost %f, exp_cost %f, grad norm %f, param norm %f, tps %f, '
'length mean/std %f/%f' %
(epoch, current_step, cost, exp_cost / exp_length,
grad_norm, param_norm, tps, mean_length, std_length))
epoch_toc = time.time()
# Checkpoint
checkpoint_path = os.path.join(FLAGS.train_dir, "best.ckpt")
# Validate
valid_cost = validate(model, sess, x_dev, y_dev)
logging.info("Epoch %d Validation cost: %f time: %f" %
(epoch, valid_cost, epoch_toc - epoch_tic))
if len(previous_losses) > 2 and valid_cost > previous_losses[-1]:
logging.info("Annealing learning rate by %f" %
FLAGS.learning_rate_decay_factor)
sess.run(model.learning_rate_decay_op)
model.saver.restore(sess, checkpoint_path)
else:
previous_losses.append(valid_cost)
model.saver.save(sess, checkpoint_path)
sys.stdout.flush()
def train():
"""Train a translation model using NLC data."""
# Prepare NLC data.
logging.info("Preparing NLC data in %s" % FLAGS.data_dir)
x_train, y_train, x_dev, y_dev, vocab_path = prepare_nlc_data(
FLAGS.data_dir, FLAGS.max_vocab_size, tokenizer=get_tokenizer())
vocab, _ = initialize_vocabulary(vocab_path)
vocab_size = len(vocab)
logging.info("Vocabulary size: %d" % vocab_size)
if not os.path.exists(FLAGS.train_dir):
os.makedirs(FLAGS.train_dir)
file_handler = logging.FileHandler("{0}/log.txt".format(FLAGS.train_dir))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.train_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
logging.info("Creating %d layers of %d units." % (FLAGS.num_layers, FLAGS.size))
model = create_model(sess, vocab_size, False)
logging.info('Initial validation cost: %f' % validate(model, sess, x_dev, y_dev))
epoch = 0
previous_losses = []
exp_cost = None
exp_length = None
exp_norm = None
total_iters = 0
start_time = time.time()
while FLAGS.epochs == 0 or epoch < FLAGS.epochs:
epoch += 1
current_step = 0
# Train
epoch_tic = time.time()
for source_tokens, source_mask, target_tokens, target_mask in pair_iter(x_train, y_train, FLAGS.batch_size,
FLAGS.num_layers):
# Get a batch and make a step.
grad_norm, cost, param_norm = model.train(sess, source_tokens, source_mask, target_tokens, target_mask)
total_iters += np.sum(target_mask)
tps = total_iters / (time.time() - start_time)
current_step += 1
lengths = np.sum(target_mask, axis=0)
mean_length = np.mean(lengths)
std_length = np.std(lengths)
if not exp_cost:
exp_cost = cost
exp_length = mean_length
exp_norm = grad_norm
else:
exp_cost = 0.99 * exp_cost + 0.01 * cost
exp_length = 0.99 * exp_length + 0.01 * mean_length
exp_norm = 0.99 * exp_norm + 0.01 * grad_norm
cost = cost / mean_length
if current_step % FLAGS.print_every == 0:
logging.info(
'epoch %d, iter %d, cost %f, exp_cost %f, grad norm %f, param norm %f, tps %f, '
'length mean/std %f/%f' %
(epoch, current_step, cost, exp_cost / exp_length, grad_norm, param_norm, tps, mean_length,
std_length))
epoch_toc = time.time()
# Checkpoint
checkpoint_path = os.path.join(FLAGS.train_dir, "best.ckpt")
# Validate
valid_cost = validate(model, sess, x_dev, y_dev)
logging.info("Epoch %d Validation cost: %f time: %f" % (epoch, valid_cost, epoch_toc - epoch_tic))
if len(previous_losses) > 2 and valid_cost > previous_losses[-1]:
logging.info("Annealing learning rate by %f" % FLAGS.learning_rate_decay_factor)
sess.run(model.learning_rate_decay_op)
model.saver.restore(sess, checkpoint_path)
else:
previous_losses.append(valid_cost)
model.saver.save(sess, checkpoint_path)
sys.stdout.flush()