def build_language_training_rnn(sess, hyper_params, prog_params, train_set, test_set):
model = LanguageModel(hyper_params["num_layers"], hyper_params["hidden_size"], hyper_params["batch_size"],
hyper_params["max_input_seq_length"], hyper_params["max_target_seq_length"],
hyper_params["char_map_length"])
# Create a Dataset from the train_set and the test_set
train_dataset = model.build_dataset(train_set, hyper_params["batch_size"], hyper_params["max_input_seq_length"],
hyper_params["char_map"])
v_iterator = None
if test_set is []:
t_iterator = model.add_dataset_input(train_dataset)
sess.run(t_iterator.initializer)
else:
test_dataset = model.build_dataset(test_set, hyper_params["batch_size"], hyper_params["max_input_seq_length"],
hyper_params["char_map"])
# Build the input stream from the different datasets
t_iterator, v_iterator = model.add_datasets_input(train_dataset, test_dataset)
sess.run(t_iterator.initializer)
sess.run(v_iterator.initializer)
# Create the model
model.create_training_rnn(hyper_params["dropout_input_keep_prob"], hyper_params["dropout_output_keep_prob"],
hyper_params["grad_clip"], hyper_params["learning_rate"],
hyper_params["lr_decay_factor"], use_iterator=True)
model.add_tensorboard(sess, hyper_params["tensorboard_dir"], prog_params["tb_name"], prog_params["timeline"])
model.initialize(sess)
model.restore(sess, hyper_params["checkpoint_dir"] + "/language/")
# Override the learning rate if given on the command line
if prog_params["learn_rate"] is not None:
model.set_learning_rate(sess, prog_params["learn_rate"])
return model, t_iterator, v_iterator
def build_language_training_rnn(sess, hyper_params, prog_params, train_set, test_set):
model = LanguageModel(hyper_params["num_layers"], hyper_params["hidden_size"], hyper_params["batch_size"],
hyper_params["max_input_seq_length"], hyper_params["max_target_seq_length"],
hyper_params["char_map_length"])
# Create a Dataset from the train_set and the test_set
train_dataset = model.build_dataset(train_set, hyper_params["batch_size"], hyper_params["max_input_seq_length"],
hyper_params["char_map"])
v_iterator = None
if test_set is []:
t_iterator = model.add_dataset_input(train_dataset)
sess.run(t_iterator.initializer)
else:
test_dataset = model.build_dataset(test_set, hyper_params["batch_size"], hyper_params["max_input_seq_length"],
hyper_params["char_map"])
# Build the input stream from the different datasets
t_iterator, v_iterator = model.add_datasets_input(train_dataset, test_dataset)
sess.run(t_iterator.initializer)
sess.run(v_iterator.initializer)
# Create the model
model.create_training_rnn(hyper_params["dropout_input_keep_prob"], hyper_params["dropout_output_keep_prob"],
hyper_params["grad_clip"], hyper_params["learning_rate"],
hyper_params["lr_decay_factor"], use_iterator=True)
model.add_tensorboard(sess, hyper_params["tensorboard_dir"], prog_params["tb_name"], prog_params["timeline"])
model.initialize(sess)
model.restore(sess, hyper_params["checkpoint_dir"] + "/language/")
# Override the learning rate if given on the command line
if prog_params["learn_rate"] is not None:
model.set_learning_rate(sess, prog_params["learn_rate"])
return model, t_iterator, v_iterator
def test_create_training_rnn(self):
tf.reset_default_graph()
with tf.Session():
model = LanguageModel(self.num_layers, self.hidden_size, self.batch_size, self.max_input_seq_length,
self.max_target_seq_length, self.input_dim)
model.create_training_rnn(self.input_keep_prob, self.output_keep_prob, self.grad_clip,
self.learning_rate, self.lr_decay_factor)
def test_create_training_rnn(self):
tf.reset_default_graph()
with tf.Session():
model = LanguageModel(self.num_layers, self.hidden_size,
self.batch_size, self.max_input_seq_length,
self.max_target_seq_length, self.input_dim)
model.create_training_rnn(self.input_keep_prob,
self.output_keep_prob, self.grad_clip,
self.learning_rate, self.lr_decay_factor)
def test_create_training_rnn_with_iterators(self):
tf.reset_default_graph()
with tf.Session():
model = LanguageModel(self.num_layers, self.hidden_size, self.batch_size, self.max_input_seq_length,
self.max_target_seq_length, self.input_dim)
# Create a Dataset from the train_set and the test_set
train_dataset = model.build_dataset(["the brown lazy fox", "the red quick fox"], self.batch_size,
self.max_input_seq_length, ENGLISH_CHAR_MAP)
model.add_dataset_input(train_dataset)
model.create_training_rnn(self.input_keep_prob, self.output_keep_prob, self.grad_clip,
self.learning_rate, self.lr_decay_factor, use_iterator=True)
def test_create_training_rnn_with_iterators(self):
tf.reset_default_graph()
with tf.Session():
model = LanguageModel(self.num_layers, self.hidden_size,
self.batch_size, self.max_input_seq_length,
self.max_target_seq_length, self.input_dim)
# Create a Dataset from the train_set and the test_set
train_dataset = model.build_dataset(
["the brown lazy fox", "the red quick fox"], self.batch_size,
self.max_input_seq_length, ENGLISH_CHAR_MAP)
model.add_dataset_input(train_dataset)
model.create_training_rnn(self.input_keep_prob,
self.output_keep_prob,
self.grad_clip,
self.learning_rate,
self.lr_decay_factor,
use_iterator=True)