def __init__(self, mode = 'chat'): if not os.path.isdir(config.PROCESSED_PATH): data.prepare_raw_data() data.process_data() # create checkpoints folder if there isn't one already data.make_dir(config.CPT_PATH) if(mode == "chat"): self.__chat_init()
def main():
#parser = argparse.ArgumentParser()
#parser.add_argument('--mode', choices={'train', 'chat'},
# default='train', help="mode. if not specified, it's in the train mode")
#args = parser.parse_args()
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print('Data ready!')
# create checkpoints folder if there isn't one already
data.make_dir(config.CPT_PATH)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--mode', choices={'train', 'chat'},
default='train', help="mode. if not specified, it's in the train mode")
args = parser.parse_args()
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print('Data ready!')
# create checkpoints folder if there isn't one already
data.make_dir(config.CPT_PATH)
if args.mode == 'train':
train()
elif args.mode == 'chat':
chat()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--mode',choices={'train','chat'},default='train',help="mode if not specified its in train mode")
args = parser.parse_args()
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print('Data Ready!')
data.make_dir(config.CPT_PATH)
if args.mode == 'train':
train()
elif args.mode == 'chat':
chat()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--mode', choices={'train', 'chat'},
default='train', help="mode. if not specified, it's in the train mode")
args = parser.parse_args()
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print("Data ready, starting application")
# create checkpoints folder if there isn't one already
data.make_dir(config.CPT_PATH)
if args.mode == 'train':
train()
elif args.mode == 'chat':
chat()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('mode',
choices={'train', 'test', 'translate'},
default='train',
help="mode. if not specified, it's in the train mode")
args = parser.parse_args()
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print('Data ready!')
# create checkpoints folder if there isn't one already
data.make_dir(config.CPT_PATH)
if args.mode == 'train':
train()
elif args.mode == 'test':
bleu_scores = test()
elif args.mode == 'translate':
translate()
def main():
"""parser = argparse.ArgumentParser()
parser.add_argument('--mode', choices={'train', 'chat'},
default='train', help="mode. if not specified, it's in the train mode")
args = parser.parse_args()"""
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print('Data ready!')
# create checkpoints folder if there isn't one already
data.make_dir(config.CPT_PATH)
mode = input("Input mode (train|chat): ")
"""if args.mode == 'train':
train()
elif args.mode == 'chat':
chat()"""
if mode == 'train':
train()
else:
chat()
def start_training():
if not os.path.isdir(config.PROCESSED_PATH):
data.prepare_raw_data()
data.process_data()
print('Data ready!')
# create checkpoints folder if there isn't one already
data.make_dir(config.CPT_PATH)
""" Train the bot """
test_buckets, data_buckets, train_buckets_scale = _get_buckets()
# in train mode, we need to create the backward path, so forwrad_only is False
model = Seq2SeqModel(False, config.BATCH_SIZE)
model.build_graph()
saver = tf.train.Saver()
with tf.Session() as sess:
print('Running session')
sess.run(tf.global_variables_initializer())
_check_restore_parameters(sess, saver)
iteration = model.global_step.eval()
total_loss = 0
# Infinite loop
print('Start training ...')
train_record_file = open(
os.path.join(config.PROCESSED_PATH, config.TRAINING_RECORD_FILE),
'a+')
test_record_file = open(
os.path.join(config.PROCESSED_PATH, config.TESTING_RECORD_FILE),
'a+')
while True:
try:
skip_step = _get_skip_step(iteration)
bucket_id = _get_random_bucket(train_buckets_scale)
encoder_inputs, decoder_inputs, decoder_masks = data.get_batch(
data_buckets[bucket_id],
bucket_id,
batch_size=config.BATCH_SIZE)
start = time.time()
_, step_loss, _ = run_step(sess, model, encoder_inputs,
decoder_inputs, decoder_masks,
bucket_id, False)
total_loss += step_loss
iteration += 1
if iteration % skip_step == 0:
_train_info = 'Iter {}: loss {}, time {}'.format(
iteration, total_loss / skip_step,
time.time() - start)
print(_train_info)
train_record_file.write(_train_info + '\n')
start = time.time()
total_loss = 0
saver.save(sess,
os.path.join(config.CPT_PATH, 'chatbot'),
global_step=model.global_step)
if iteration % (10 * skip_step) == 0:
# Run evals on development set and print their loss
_test_info = _eval_test_set(sess, model, test_buckets)
for item in _test_info:
print(item)
test_record_file.write("%s\n" % item)
start = time.time()
sys.stdout.flush()
except KeyboardInterrupt:
print('Interrupted by user at iteration {}'.format(iteration))
train_record_file.close()
test_record_file.close()
