def predict(self,
test_x,
out_scaler,
gen_test_file_list,
sequential_training=False,
stateful=False):
#### compute predictions ####
io_funcs = BinaryIOCollection()
test_file_number = len(gen_test_file_list)
print("generating features on held-out test data...")
for utt_index in range(test_file_number):
gen_test_file_name = gen_test_file_list[utt_index]
test_id = os.path.splitext(os.path.basename(gen_test_file_name))[0]
temp_test_x = test_x[test_id]
num_of_rows = temp_test_x.shape[0]
if stateful:
temp_test_x = data_utils.get_stateful_input(
temp_test_x, self.seq_length, self.batch_size)
elif sequential_training:
temp_test_x = np.reshape(temp_test_x,
(1, num_of_rows, self.n_in))
predictions = self.model.predict(temp_test_x)
if sequential_training:
predictions = np.reshape(predictions,
(num_of_rows, self.n_out))
data_utils.denorm_data(predictions, out_scaler)
io_funcs.array_to_binary_file(predictions, gen_test_file_name)
data_utils.drawProgressBar(utt_index + 1, test_file_number)
sys.stdout.write("\n")
def predict(self, test_x, out_scaler, gen_test_file_list, sequential_training=False, stateful=False):
#### compute predictions ####
io_funcs = BinaryIOCollection()
test_file_number = len(gen_test_file_list)
print("generating features on held-out test data...")
for utt_index in range(test_file_number):
gen_test_file_name = gen_test_file_list[utt_index]
test_id = os.path.splitext(os.path.basename(gen_test_file_name))[0]
temp_test_x = test_x[test_id]
num_of_rows = temp_test_x.shape[0]
if stateful:
temp_test_x = data_utils.get_stateful_input(temp_test_x, self.seq_length, self.batch_size)
elif sequential_training:
temp_test_x = np.reshape(temp_test_x, (1, num_of_rows, self.n_in))
predictions = self.model.predict(temp_test_x)
if sequential_training:
predictions = np.reshape(predictions, (num_of_rows, self.n_out))
data_utils.denorm_data(predictions, out_scaler)
io_funcs.array_to_binary_file(predictions, gen_test_file_name)
data_utils.drawProgressBar(utt_index+1, test_file_number)
sys.stdout.write("\n")
def get_validation_error(self,
valid_x,
valid_y,
sequential_training=True,
stateful=False):
valid_id_list = list(valid_x.keys())
valid_id_list.sort()
valid_error = 0.0
valid_file_number = len(valid_id_list)
for utt_index in range(valid_file_number):
temp_valid_x = valid_x[valid_id_list[utt_index]]
temp_valid_y = valid_y[valid_id_list[utt_index]]
num_of_rows = temp_valid_x.shape[0]
if stateful:
temp_valid_x = data_utils.get_stateful_input(
temp_valid_x, self.seq_length, self.batch_size)
elif sequential_training:
temp_valid_x = np.reshape(temp_valid_x,
(1, num_of_rows, self.n_in))
predictions = self.model.predict(temp_valid_x)
if sequential_training:
predictions = np.reshape(predictions,
(num_of_rows, self.n_out))
valid_error += np.mean(
np.sum((predictions - temp_valid_y)**2, axis=1))
valid_error = valid_error / valid_file_number
return valid_error
def get_validation_error(self, valid_x, valid_y, sequential_training=True, stateful=False):
valid_id_list = list(valid_x.keys())
valid_id_list.sort()
valid_error = 0.0
valid_file_number = len(valid_id_list)
for utt_index in range(valid_file_number):
temp_valid_x = valid_x[valid_id_list[utt_index]]
temp_valid_y = valid_y[valid_id_list[utt_index]]
num_of_rows = temp_valid_x.shape[0]
if stateful:
temp_valid_x = data_utils.get_stateful_input(temp_valid_x, self.seq_length, self.batch_size)
elif sequential_training:
temp_valid_x = np.reshape(temp_valid_x, (1, num_of_rows, self.n_in))
predictions = self.model.predict(temp_valid_x)
if sequential_training:
predictions = np.reshape(predictions, (num_of_rows, self.n_out))
valid_error += np.mean(np.sum((predictions - temp_valid_y) ** 2, axis=1))
valid_error = valid_error/valid_file_number
return valid_error