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_build_dataset(self):
tf.reset_default_graph()
with tf.Session() as sess:
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
dataset = model.build_dataset(["the brown lazy fox", "the red quick fox"], self.batch_size,
self.max_input_seq_length, ENGLISH_CHAR_MAP)
iterator = dataset.make_initializable_iterator()
sess.run(iterator.initializer)
iterator_get_next_op = iterator.get_next()
input_dataset, input_length_dataset, label_dataset = sess.run(iterator_get_next_op)
# Rebuild the expected result for comparison
expected_result = []
one_hot = dataprocessor.DataProcessor.get_str_to_one_hot_encoded(ENGLISH_CHAR_MAP, "the brown lazy fox")
expected_result.append(one_hot)
one_hot = dataprocessor.DataProcessor.get_str_to_one_hot_encoded(ENGLISH_CHAR_MAP, "the red quick fox")
# Append the padding
one_hot.append(np.zeros(len(ENGLISH_CHAR_MAP)))
expected_result.append(one_hot)
# Check values
np.testing.assert_array_equal(input_dataset, expected_result)
np.testing.assert_array_equal(input_length_dataset, [18, 17])
np.testing.assert_array_equal(label_dataset[0],
[[0, 0], [0, 1], [0, 2], [0, 3], [0, 4], [0, 5], [0, 6], [0, 7],
[0, 8], [0, 9], [0, 10], [0, 11], [0, 12], [0, 13], [0, 14], [0, 15],
[1, 0], [1, 1], [1, 2], [1, 3], [1, 4], [1, 5], [1, 6], [1, 7],
[1, 8], [1, 9], [1, 10], [1, 11], [1, 12], [1, 13], [1, 14]
])
np.testing.assert_array_equal(label_dataset[1],
[33, 30, 53, 43, 40, 48, 39, 63, 26, 51, 50, 57, 40, 49, 79, 79,
33, 30, 69, 30, 29, 68, 46, 34, 28, 36, 57, 40, 49, 79, 79])
np.testing.assert_array_equal(label_dataset[2], [2, 1800])
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)
def test_build_dataset(self):
tf.reset_default_graph()
with tf.Session() as sess:
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
dataset = model.build_dataset(
["the brown lazy fox", "the red quick fox"], self.batch_size,
self.max_input_seq_length, ENGLISH_CHAR_MAP)
iterator = dataset.make_initializable_iterator()
sess.run(iterator.initializer)
iterator_get_next_op = iterator.get_next()
input_dataset, input_length_dataset, label_dataset = sess.run(
iterator_get_next_op)
# Rebuild the expected result for comparison
expected_result = []
one_hot = dataprocessor.DataProcessor.get_str_to_one_hot_encoded(
ENGLISH_CHAR_MAP, "the brown lazy fox")
expected_result.append(one_hot)
one_hot = dataprocessor.DataProcessor.get_str_to_one_hot_encoded(
ENGLISH_CHAR_MAP, "the red quick fox")
# Append the padding
one_hot.append(np.zeros(len(ENGLISH_CHAR_MAP)))
expected_result.append(one_hot)
# Check values
np.testing.assert_array_equal(input_dataset, expected_result)
np.testing.assert_array_equal(input_length_dataset, [18, 17])
np.testing.assert_array_equal(
label_dataset[0],
[[0, 0], [0, 1], [0, 2], [0, 3], [0, 4], [0, 5], [0, 6],
[0, 7], [0, 8], [0, 9], [0, 10], [0, 11], [0, 12], [0, 13],
[0, 14], [0, 15], [1, 0], [1, 1], [1, 2], [1, 3], [1, 4],
[1, 5], [1, 6], [1, 7], [1, 8], [1, 9], [1, 10], [1, 11],
[1, 12], [1, 13], [1, 14]])
np.testing.assert_array_equal(label_dataset[1], [
33, 30, 53, 43, 40, 48, 39, 63, 26, 51, 50, 57, 40, 49, 79, 79,
33, 30, 69, 30, 29, 68, 46, 34, 28, 36, 57, 40, 49, 79, 79
])
np.testing.assert_array_equal(label_dataset[2], [2, 1800])