vocab_size = 4
for word in vocab:
word2id[word] = vocab_size
vocab_size += 1
region2id , numRegions = getRegionLabels(train_set)
period2id , numPeriods = getPeriodLabels(train_set)
train_input , train_output_region , train_output_time = getInput(train_set , word2id , period2id , region2id , maxL)
test_input , test_output_region , test_output_time = getInput(test_set , word2id , period2id , region2id , maxL)
print(train_set[0])
print(train_input[0])
print(train_output_region[0])
print(train_output_time[0])
model = RNN_Model(embed_size=args.embed_size,
hidden_size=args.hidden_size,
vocab_len=vocab_size,
epoch=args.epoch_size,
learning_rate=args.lr,
batch_size=args.batch_size)
model.train(numpy.asarray(train_input) , numpy.asarray(train_output_region) , numpy.asarray(train_output_time))
model.test(test_input , test_output_region , test_output_time)
print()
print()
print("Training Results:")
print()
model.test(train_input , train_output_region , train_output_time)
config.direction,
config.cell_type,
str(config.layers))
config.model_dir = join(config.output_dir, config.model_name)
if not exists(config.output_dir):
mkdir(config.output_dir)
if not exists(config.model_dir):
mkdir(config.model_dir)
model = RNN_Model(config)
if config.testing:
test_ids, test_data, _ = load_timit(config, data_set='test')
test_ids = np.expand_dims(test_ids, 1)
predictions = model.test(test_data)
predictions = np.expand_dims(
post_processing(config, predictions, threshold=2), 1)
outputs = np.append(test_ids, predictions, axis=1)
df = pd.DataFrame(outputs).to_csv(join(
config.model_dir, '{}.csv'.format(config.model_name)),
index=False,
header=['id', 'phone_sequence'])
else:
train_ids, train_data, train_labels = load_timit(config,
data_set='train')
model.train(train_data, train_labels)