def main(_):
if not FLAGS.pos_data_path:
raise ValueError("No data files found in 'data_path' folder")
raw_data = reader.load_data(FLAGS.pos_data_path)
# train_data, valid_data, test_data, _ = raw_data
train_word, train_tag, dev_word, dev_tag, test_word, test_tag, vocabulary = raw_data
config = get_config(FLAGS.pos_lang)
eval_config = get_config(FLAGS.pos_lang)
eval_config.batch_size = 1
eval_config.num_steps = 1
with tf.Graph().as_default(), tf.Session() as session:
initializer = tf.random_uniform_initializer(-config.init_scale,
config.init_scale)
with tf.variable_scope(FLAGS.pos_scope_name,
reuse=None,
initializer=initializer):
m = POSTagger(is_training=True, config=config)
with tf.variable_scope(FLAGS.pos_scope_name,
reuse=True,
initializer=initializer):
mvalid = POSTagger(is_training=False, config=config)
mtest = POSTagger(is_training=False, config=eval_config)
# CheckPoint State
ckpt = tf.train.get_checkpoint_state(FLAGS.pos_train_dir)
if ckpt and tf.gfile.Exists(ckpt.model_checkpoint_path):
print("Loading model parameters from %s" %
ckpt.model_checkpoint_path)
m.saver.restore(session, ckpt.model_checkpoint_path)
else:
print("Created model with fresh parameters.")
session.run(tf.initialize_all_variables())
# tf.initialize_all_variables().run()
for i in range(config.max_max_epoch):
lr_decay = config.lr_decay**max(i - config.max_epoch, 0.0)
m.assign_lr(session, config.learning_rate * lr_decay)
print("Epoch: %d Learning rate: %.3f" % (i + 1, session.run(m.lr)))
train_perplexity = run_epoch(session,
m,
train_word,
train_tag,
m.train_op,
verbose=True)
print("Epoch: %d Train Perplexity: %.3f" %
(i + 1, train_perplexity))
valid_perplexity = run_epoch(session, mvalid, dev_word, dev_tag,
tf.no_op())
print("Epoch: %d Valid Perplexity: %.3f" %
(i + 1, valid_perplexity))
test_perplexity = run_epoch(session, mtest, test_word, test_tag,
tf.no_op())
print("Test Perplexity: %.3f" % test_perplexity)
def main(_):
if not FLAGS.pos_data_path:
raise ValueError("No data files found in 'data_path' folder")
# Load Data
raw_data = reader.load_data(FLAGS.pos_data_path)
train_word, train_tag, dev_word, dev_tag, test_word, test_tag, vocab_size = raw_data
# Load Config
config_dict = load_config(FLAGS.pos_model_config_path)
config = get_config(config_dict, FLAGS.pos_lang)
eval_config = get_config(config_dict, FLAGS.pos_lang)
eval_config.batch_size = 1
eval_config.num_steps = 1
# Define Variable Scope
model_var_scope = get_model_var_scope(FLAGS.pos_scope_name, FLAGS.pos_lang)
with tf.Graph().as_default(), tf.Session() as session:
initializer = tf.random_uniform_initializer(-config.init_scale,
config.init_scale)
with tf.variable_scope(model_var_scope,
reuse=False,
initializer=initializer):
m = POSTagger(is_training=True, config=config)
with tf.variable_scope(model_var_scope,
reuse=True,
initializer=initializer):
mvalid = POSTagger(is_training=False, config=config)
mtest = POSTagger(is_training=False, config=eval_config)
# CheckPoint State
ckpt = tf.train.get_checkpoint_state(FLAGS.pos_train_dir)
if ckpt:
print("Loading model parameters from %s" %
ckpt.model_checkpoint_path)
m.saver.restore(session,
tf.train.latest_checkpoint(FLAGS.pos_train_dir))
else:
print("Created model with fresh parameters.")
session.run(tf.global_variables_initializer())
# write the graph out for further use e.g. C++ API call
tf.train.write_graph(session.graph_def,
'./models/',
'pos_graph.pbtxt',
as_text=True) # output is text
for i in range(config.max_max_epoch):
lr_decay = config.lr_decay**max(i - config.max_epoch, 0.0)
m.assign_lr(session, config.learning_rate * lr_decay)
print("Epoch: %d Learning rate: %.3f" % (i + 1, session.run(m.lr)))
train_perplexity = run_epoch(session,
m,
train_word,
train_tag,
m.train_op,
verbose=True)
print("Epoch: %d Train Perplexity: %.3f" %
(i + 1, train_perplexity))
valid_perplexity = run_epoch(session, mvalid, dev_word, dev_tag,
tf.no_op())
print("Epoch: %d Valid Perplexity: %.3f" %
(i + 1, valid_perplexity))
test_perplexity = run_epoch(session, mtest, test_word, test_tag,
tf.no_op())
print("Test Perplexity: %.3f" % test_perplexity)