def prepare_data(self, train_path, valid_path, test_path):
"""Prepare train/validation/test sets. Create or load vocabularies."""
# Prepare data.
print("Preparing G2P data")
train_gr_ids, train_ph_ids, valid_gr_ids, valid_ph_ids, self.gr_vocab,\
self.ph_vocab, self.test_lines =\
data_utils.prepare_g2p_data(self.model_dir, train_path, valid_path,
test_path)
# Read data into buckets and compute their sizes.
print("Reading development and training data.")
if self.mode == 'g2p':
self.valid_set = self.__put_into_buckets(valid_gr_ids,
valid_ph_ids)
self.train_set = self.__put_into_buckets(train_gr_ids,
train_ph_ids)
self.rev_ph_vocab = dict([(x, y)
for (y, x) in enumerate(self.ph_vocab)])
else:
self.valid_set = self.__put_into_buckets(valid_ph_ids,
valid_gr_ids)
self.train_set = self.__put_into_buckets(train_ph_ids,
train_gr_ids)
self.rev_gr_vocab = dict([(x, y)
for (y, x) in enumerate(self.gr_vocab)])
def prepare_data(self, train_path, valid_path, test_path):
"""Prepare train/validation/test sets. Create or load vocabularies."""
# Prepare data.
print("Preparing G2P data")
train_gr_ids, train_ph_ids, valid_gr_ids, valid_ph_ids, self.gr_vocab,\
self.ph_vocab, self.test_lines =\
data_utils.prepare_g2p_data(self.model_dir, train_path, valid_path,
test_path)
# Read data into buckets and compute their sizes.
print ("Reading development and training data.")
self.valid_set = self.__put_into_buckets(valid_gr_ids, valid_ph_ids)
self.train_set = self.__put_into_buckets(train_gr_ids, train_ph_ids)
self.rev_ph_vocab = dict([(x, y) for (y, x) in enumerate(self.ph_vocab)])
def __train_init(self,
params,
train_path,
valid_path=None,
test_path=None):
"""Create G2P model and initialize or load parameters in session."""
# Preliminary actions before model creation.
# Load model parameters.
if self.model_dir:
data_utils.save_params(params.num_layers, params.size,
self.model_dir)
# Prepare G2P data.
print("Preparing G2P data")
train_gr_ids, train_ph_ids, valid_gr_ids, valid_ph_ids, self.gr_vocab,\
self.ph_vocab, self.test_lines =\
data_utils.prepare_g2p_data(self.model_dir, train_path, valid_path,
test_path)
# Read data into buckets and compute their sizes.
print("Reading development and training data.")
self.valid_set = self.__put_into_buckets(valid_gr_ids, valid_ph_ids)
self.train_set = self.__put_into_buckets(train_gr_ids, train_ph_ids)
self.rev_ph_vocab = dict([(x, y)
for (y, x) in enumerate(self.ph_vocab)])
self.session = tf.Session()
# Create model.
print("Creating %d layers of %d units." %
(params.num_layers, params.size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab),
self._BUCKETS,
params.size,
params.num_layers,
params.max_gradient_norm,
params.batch_size,
params.learning_rate,
params.lr_decay_factor,
forward_only=False)
self.model.saver = tf.train.Saver(tf.all_variables(), max_to_keep=1)
print("Created model with fresh parameters.")
self.session.run(tf.initialize_all_variables())
def __train_init(self, params, train_path, valid_path=None, test_path=None):
"""Create G2P model and initialize or load parameters in session."""
# Preliminary actions before model creation.
# Load model parameters.
if self.model_dir:
data_utils.save_params(params.num_layers,
params.size,
self.model_dir)
# Prepare G2P data.
print("Preparing G2P data")
train_gr_ids, train_ph_ids, valid_gr_ids, valid_ph_ids, self.gr_vocab,\
self.ph_vocab, self.test_lines =\
data_utils.prepare_g2p_data(self.model_dir, train_path, valid_path,
test_path)
# Read data into buckets and compute their sizes.
print ("Reading development and training data.")
self.valid_set = self.__put_into_buckets(valid_gr_ids, valid_ph_ids)
self.train_set = self.__put_into_buckets(train_gr_ids, train_ph_ids)
self.rev_ph_vocab = dict([(x, y) for (y, x) in enumerate(self.ph_vocab)])
self.session = tf.Session()
# Create model.
print("Creating %d layers of %d units." % (params.num_layers, params.size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab), self._BUCKETS,
params.size, params.num_layers,
params.max_gradient_norm,
params.batch_size,
params.learning_rate,
params.lr_decay_factor,
forward_only=False)
self.model.saver = tf.train.Saver(tf.all_variables(), max_to_keep=1)
print("Created model with fresh parameters.")
self.session.run(tf.initialize_all_variables())
