def train_truncated_model(self, train_x, train_y, batch_size,
num_of_epochs, shuffle_data):
### Method 1 ###
temp_train_x = data_utils.transform_data_to_3d_matrix(
train_x,
seq_length=self.seq_length,
merge_size=self.merge_size,
shuffle_data=shuffle_data)
print(("Input shape: " + str(temp_train_x.shape)))
temp_train_y = data_utils.transform_data_to_3d_matrix(
train_y,
seq_length=self.seq_length,
merge_size=self.merge_size,
shuffle_data=shuffle_data)
print(("Output shape: " + str(temp_train_y.shape)))
if self.stateful:
temp_train_x, temp_train_y = data_utils.get_stateful_data(
temp_train_x, temp_train_y, batch_size)
self.model.fit(temp_train_x,
temp_train_y,
batch_size=batch_size,
epochs=num_of_epochs,
shuffle=False,
verbose=1)
def train_bucket_model_without_padding(self, train_x, train_y, train_flen,
batch_size, num_of_epochs,
shuffle_data):
### Method 3 ###
train_count_list = list(train_flen['framenum2utt'].keys())
if shuffle_data:
random.seed(271638)
random.shuffle(train_count_list)
train_file_number = len(train_x)
for epoch_num in range(num_of_epochs):
print(('Epoch: %d/%d ' % (epoch_num + 1, num_of_epochs)))
file_num = 0
for sequence_length in train_count_list:
train_idx_list = train_flen['framenum2utt'][sequence_length]
sub_train_x = dict((filename, train_x[filename])
for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename])
for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(
sub_train_x, max_length=sequence_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(
sub_train_y, max_length=sequence_length)
self.model.fit(temp_train_x,
temp_train_y,
batch_size=batch_size,
epochs=1,
verbose=0)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
sys.stdout.write("\n")
def train_split_model(self, train_x, train_y, valid_x, valid_y, train_flen,
batch_size, num_of_epochs, shuffle_data):
### Method 3 ###
train_id_list = list(train_flen['utt2framenum'].keys())
if shuffle_data:
random.seed(271638)
random.shuffle(train_id_list)
train_file_number = len(train_id_list)
for epoch_num in range(num_of_epochs):
print(('Epoch: %d/%d ' % (epoch_num + 1, num_of_epochs)))
file_num = 0
while file_num < train_file_number:
train_idx_list = train_id_list[file_num:file_num + batch_size]
sub_train_x = dict((filename, train_x[filename])
for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename])
for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(
sub_train_x,
seq_length=self.seq_length,
merge_size=self.merge_size)
temp_train_y = data_utils.transform_data_to_3d_matrix(
sub_train_y,
seq_length=self.seq_length,
merge_size=self.merge_size)
self.model.train_on_batch(temp_train_x, temp_train_y)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
print(" Validation error: %.3f" %
(self.get_validation_error(valid_x, valid_y)))
def train_split_model_keras_version(self, train_x, train_y, valid_x,
valid_y, train_flen, batch_size,
num_of_epochs, shuffle_data):
"""This function is not used as of now
"""
### Method 3 ###
temp_train_x = data_utils.transform_data_to_3d_matrix(
train_x,
seq_length=self.seq_length,
merge_size=self.merge_size,
shuffle_data=shuffle_data)
print(("Input shape: " + str(temp_train_x.shape)))
temp_train_y = data_utils.transform_data_to_3d_matrix(
train_y,
seq_length=self.seq_length,
merge_size=self.merge_size,
shuffle_data=shuffle_data)
print(("Output shape: " + str(temp_train_y.shape)))
if self.stateful:
temp_train_x, temp_train_y = data_utils.get_stateful_data(
temp_train_x, temp_train_y, batch_size)
self.model.fit(temp_train_x,
temp_train_y,
batch_size=batch_size,
epochs=num_of_epochs)
def train_bucket_model(self, train_x, train_y, valid_x, valid_y, train_flen, batch_size, num_of_epochs, shuffle_data):
### Method 2 ###
train_fnum_list = np.array(list(train_flen['framenum2utt'].keys()))
train_range_list = list(range(min(train_fnum_list), max(train_fnum_list)+1, self.bucket_range))
if shuffle_data:
random.seed(271638)
random.shuffle(train_range_list)
train_file_number = len(train_x)
for epoch_num in range(num_of_epochs):
print(('Epoch: %d/%d ' %(epoch_num+1, num_of_epochs)))
file_num = 0
for frame_num in train_range_list:
min_seq_length = frame_num
max_seq_length = frame_num+self.bucket_range
sub_train_list = train_fnum_list[(train_fnum_list>=min_seq_length) & (train_fnum_list<max_seq_length)]
if len(sub_train_list)==0:
continue;
train_idx_list = sum([train_flen['framenum2utt'][framenum] for framenum in sub_train_list], [])
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, max_length=max_seq_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, max_length=max_seq_length)
self.model.fit(temp_train_x, temp_train_y, batch_size=batch_size, shuffle=False, epochs=1, verbose=0)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
print(" Validation error: %.3f" % (self.get_validation_error(valid_x, valid_y)))
def train_bucket_model_without_padding(self, train_x, train_y, valid_x, valid_y, train_flen, batch_size, num_of_epochs, shuffle_data):
"""This function is not used as of now
"""
### Method 4 ###
train_count_list = list(train_flen['framenum2utt'].keys())
if shuffle_data:
random.seed(271638)
random.shuffle(train_count_list)
train_file_number = len(train_x)
for epoch_num in range(num_of_epochs):
print(('Epoch: %d/%d ' %(epoch_num+1, num_of_epochs)))
file_num = 0
for sequence_length in train_count_list:
train_idx_list = train_flen['framenum2utt'][sequence_length]
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, max_length=sequence_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, max_length=sequence_length)
self.model.fit(temp_train_x, temp_train_y, batch_size=batch_size, epochs=1, verbose=0)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
sys.stdout.write("\n")
def train_bucket_model_with_padding(self, train_x, train_y, train_flen, batch_size, num_of_epochs, shuffle_data):
### Method 3 ###
train_fnum_list = np.array(train_flen['framenum2utt'].keys())
train_range_list = range(min(train_fnum_list), max(train_fnum_list), self.bucket_range)
if shuffle_data:
random.seed(271638)
random.shuffle(train_range_list)
train_file_number = len(train_x)
for epoch_num in xrange(num_of_epochs):
print 'Epoch: %d/%d ' %(epoch_num+1, num_of_epochs)
file_num = 0
for frame_num in train_range_list:
min_seq_length = frame_num
max_seq_length = frame_num+self.bucket_range
sub_train_list = train_fnum_list[(train_fnum_list>min_seq_length) & (train_fnum_list<=max_seq_length)]
if len(sub_train_list)==0:
continue;
train_idx_list = sum([train_flen['framenum2utt'][framenum] for framenum in sub_train_list], [])
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, max_length=max_seq_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, max_length=max_seq_length)
self.model.fit(temp_train_x, temp_train_y, batch_size=batch_size, epochs=1, verbose=0)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
sys.stdout.write("\n")
def train_bucket_model_with_padding(self, train_x, train_y, train_flen, batch_size, num_of_epochs, shuffle_data):
### Method 2 ###
train_fnum_list = np.array(train_flen['framenum2utt'].keys())
train_range_list = range(min(train_fnum_list), max(train_fnum_list), self.bucket_range)
if shuffle_data:
random.seed(271638)
random.shuffle(train_range_list)
train_file_number = len(train_x)
for epoch_num in xrange(num_of_epochs):
print('Epoch: %d/%d ' %(epoch_num+1, num_of_epochs))
file_num = 0
for frame_num in train_range_list:
min_seq_length = frame_num
max_seq_length = frame_num+self.bucket_range
sub_train_list = train_fnum_list[(train_fnum_list>min_seq_length) & (train_fnum_list<=max_seq_length)]
if len(sub_train_list)==0:
continue;
train_idx_list = sum([train_flen['framenum2utt'][framenum] for framenum in sub_train_list], [])
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, max_length=max_seq_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, max_length=max_seq_length)
self.model.fit(temp_train_x, temp_train_y, batch_size=batch_size, epochs=1, verbose=0)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
sys.stdout.write("\n")
def train_bucket_model(self, train_x, train_y, valid_x, valid_y, train_flen):
# TODO: use packaged params
### Method 2 ###
train_fnum_list = np.array(list(train_flen['framenum2utt'].keys()))
train_range_list = list(range(min(train_fnum_list), max(train_fnum_list)+1, self.bucket_range))
if self.shuffle_data:
random.seed(271638)
random.shuffle(train_range_list)
train_file_number = len(train_x)
for epoch_num in range(self.num_of_epochs):
print(('Epoch: %d/%d ' %(epoch_num+1, self.num_of_epochs)))
file_num = 0
for frame_num in train_range_list:
min_seq_length = frame_num
max_seq_length = frame_num+self.bucket_range
sub_train_list = train_fnum_list[(train_fnum_list>=min_seq_length) & (train_fnum_list<max_seq_length)]
if len(sub_train_list)==0:
continue;
train_idx_list = sum([train_flen['framenum2utt'][framenum] for framenum in sub_train_list], [])
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, max_length=max_seq_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, max_length=max_seq_length)
self.model.fit(temp_train_x, temp_train_y, batch_size=self.batch_size, shuffle=False, epochs=1, verbose=0)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
print(" Validation error: %.3f" % (self.get_validation_error(valid_x, valid_y)))
def train_padding_model(self, train_x, train_y, valid_x, valid_y, train_flen):
# TODO: use packaged params
### Method 1 ###
train_id_list = list(train_flen['utt2framenum'].keys())
if self.shuffle_data:
random.seed(271638)
random.shuffle(train_id_list)
train_file_number = len(train_id_list)
for epoch_num in range(self.num_of_epochs):
print(('Epoch: %d/%d ' %(epoch_num+1, self.num_of_epochs)))
file_num = 0
while file_num < train_file_number:
train_idx_list = train_id_list[file_num: file_num + self.batch_size]
seq_len_arr = [train_flen['utt2framenum'][filename] for filename in train_idx_list]
max_seq_length = max(seq_len_arr)
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, max_length=max_seq_length)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, max_length=max_seq_length)
self.model.train_on_batch(temp_train_x, temp_train_y)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
print(" Validation error: %.3f" % (self.get_validation_error(valid_x, valid_y)))
def train_truncated_model(self, train_x, train_y, batch_size, num_of_epochs, shuffle_data):
### Method 1 ###
temp_train_x = data_utils.transform_data_to_3d_matrix(train_x, seq_length=self.seq_length, merge_size=self.merge_size, shuffle_data=shuffle_data)
print("Input shape: "+str(temp_train_x.shape))
temp_train_y = data_utils.transform_data_to_3d_matrix(train_y, seq_length=self.seq_length, merge_size=self.merge_size, shuffle_data=shuffle_data)
print("Output shape: "+str(temp_train_y.shape))
if self.stateful:
temp_train_x, temp_train_y = get_stateful_data(temp_train_x, temp_train_y, batch_size)
self.model.fit(temp_train_x, temp_train_y, batch_size=batch_size, epochs=num_of_epochs, shuffle=False, verbose=1)
def train_split_model_keras_version(self, train_x, train_y, valid_x, valid_y, train_flen, batch_size, num_of_epochs, shuffle_data):
"""This function is not used as of now
"""
### Method 3 ###
temp_train_x = data_utils.transform_data_to_3d_matrix(train_x, seq_length=self.seq_length, merge_size=self.merge_size, shuffle_data=shuffle_data)
print(("Input shape: "+str(temp_train_x.shape)))
temp_train_y = data_utils.transform_data_to_3d_matrix(train_y, seq_length=self.seq_length, merge_size=self.merge_size, shuffle_data=shuffle_data)
print(("Output shape: "+str(temp_train_y.shape)))
if self.stateful:
temp_train_x, temp_train_y = data_utils.get_stateful_data(temp_train_x, temp_train_y, batch_size)
self.model.fit(temp_train_x, temp_train_y, batch_size=batch_size, epochs=num_of_epochs)
def train_split_model(self, train_x, train_y, valid_x, valid_y, train_flen, batch_size, num_of_epochs, shuffle_data):
### Method 3 ###
train_id_list = list(train_flen['utt2framenum'].keys())
if shuffle_data:
random.seed(271638)
random.shuffle(train_id_list)
train_file_number = len(train_id_list)
for epoch_num in range(num_of_epochs):
print(('Epoch: %d/%d ' %(epoch_num+1, num_of_epochs)))
file_num = 0
while file_num < train_file_number:
train_idx_list = train_id_list[file_num: file_num + batch_size]
sub_train_x = dict((filename, train_x[filename]) for filename in train_idx_list)
sub_train_y = dict((filename, train_y[filename]) for filename in train_idx_list)
temp_train_x = data_utils.transform_data_to_3d_matrix(sub_train_x, seq_length=self.seq_length, merge_size=self.merge_size)
temp_train_y = data_utils.transform_data_to_3d_matrix(sub_train_y, seq_length=self.seq_length, merge_size=self.merge_size)
self.model.train_on_batch(temp_train_x, temp_train_y)
file_num += len(train_idx_list)
data_utils.drawProgressBar(file_num, train_file_number)
print(" Validation error: %.3f" % (self.get_validation_error(valid_x, valid_y)))
