def func(save_dir=r'../outputs',
vocab=r'../outputs/vocabulary.txt',
train=r'../outputs/train-data.npz',
valid=r'../outputs/valid-data.npz',
bidirectional=1,
batch_size=32,
num_epochs=1,
learning_rate=0.001,
dropout_keep=1.0,
interval=1000,
lstm_units=500,
embedding_size=100,
in_embeddings=None,
in_train_embeddings=False):
logging.basicConfig(level=logging.INFO)
sess = tf.Session()
wd = utils.WordDictionary(vocab)
embeddings = load_or_create_embeddings(in_embeddings, wd.vocabulary_size,
embedding_size)
logging.info('Reading training data')
train_data = utils.load_binary_data(train)
logging.info('Reading validation data')
valid_data = utils.load_binary_data(valid)
logging.info('Creating model')
train_embeddings = in_train_embeddings if in_embeddings else True
model = seq.seq2seqModel(lstm_units,
embeddings,
wd.eos_index,
train_embeddings=train_embeddings,
bidirectional=bidirectional,
condition=True)
sess.run(tf.global_variables_initializer())
show_parameter_count(model.get_trainable_variables())
logging.info('Initialized the model and all variables. Starting training.')
model.train(sess,
save_dir,
train_data,
valid_data,
batch_size,
num_epochs,
learning_rate,
dropout_keep,
5.0,
report_interval=interval)
pass
default=2)
parser.add_argument('--embeddings',
help='Numpy embeddings file. If not supplied, '
'random embeddings are generated.')
parser.add_argument('data', help='data directory name')
args = parser.parse_args()
logging.basicConfig(level=logging.INFO)
path = args.data + '/vocabulary.txt'
wd = utils.WordDictionary(path)
embeddings = load_or_create_embeddings(args.embeddings, wd.vocabulary_size,
args.embedding_size)
logging.info('Reading training data')
path = args.data + '/train-data.npz'
train_data = utils.load_binary_data(path)
logging.info('Reading validation data')
path = args.data + '/valid-data.npz'
valid_data = utils.load_binary_data(path)
logging.info('Creating model')
model = autoencoder.TextAutoencoder(args.lstm_units, embeddings,
wd.eos_index, args.num_gpus)
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
config.gpu_options.allocator_type = 'BFC'
sess = tf.InteractiveSession(graph=model.g, config=config)
sess.run(tf.global_variables_initializer())
model.g.finalize()
show_parameter_count(model.get_trainable_variables())
logging.info('Initialized the model and all variables. Starting training.')
help='Numpy embeddings file. If not supplied, '
'random embeddings are generated.')
parser.add_argument('vocab', help='Vocabulary file')
parser.add_argument('train', help='Training set')
parser.add_argument('valid', help='Validation set')
args = parser.parse_args()
logging.basicConfig(level=logging.INFO)
sess = tf.Session()
wd = utils.WordDictionary(args.vocab)
embeddings = load_or_create_embeddings(args.embeddings, wd.vocabulary_size,
args.embedding_size)
logging.info('Reading training data')
train_data = utils.load_binary_data(args.train)
logging.info('Reading validation data')
valid_data = utils.load_binary_data(args.valid)
logging.info('Creating model')
train_embeddings = args.train_embeddings if args.embeddings else True
model = autoencoder.TextAutoencoder(args.lstm_units,
embeddings,
wd.eos_index,
train_embeddings=train_embeddings,
bidirectional=args.bidirectional)
sess.run(tf.global_variables_initializer())
show_parameter_count(model.get_trainable_variables())
logging.info('Initialized the model and all variables. Starting training.')
model.train(sess,