def main(model_path, epoch):
# Load config file
with open(os.path.join(model_path, 'config.yml'), "r") as f:
config = yaml.load(f)
param = config['param']
# Except for a blank label
if param['label_type_sub'] == 'phone61':
param['num_classes_sub'] = 61
elif param['label_type_sub'] == 'phone48':
param['num_classes_sub'] = 48
elif param['label_type_sub'] == 'phone39':
param['num_classes_sub'] = 39
# Model setting
CTCModel = load(model_type=config['model_name'])
network = CTCModel(batch_size=1,
input_size=param['input_size'] * param['num_stack'],
num_unit=param['num_unit'],
num_layer_main=param['num_layer_main'],
num_layer_sub=param['num_layer_sub'],
num_classes_main=30,
num_classes_sub=param['num_classes_sub'],
main_task_weight=param['main_task_weight'],
clip_grad=param['clip_grad'],
clip_activation=param['clip_activation'],
dropout_ratio_input=param['dropout_input'],
dropout_ratio_hidden=param['dropout_hidden'],
num_proj=param['num_proj'],
weight_decay=param['weight_decay'])
network.model_dir = model_path
print(network.model_dir)
do_plot(network=network, param=param, epoch=epoch)
def main(model_path):
epoch = None # if None, restore the final epoch
# Load config file
with open(os.path.join(model_path, 'config.yml'), "r") as f:
config = yaml.load(f)
corpus = config['corpus']
feature = config['feature']
param = config['param']
if corpus['label_type_second'] == 'phone61':
output_size_second = 61
elif corpus['label_type_second'] == 'phone48':
output_size_second = 48
elif corpus['label_type_second'] == 'phone39':
output_size_second = 39
# Model setting
CTCModel = load(model_type=config['model_name'])
network = CTCModel(batch_size=1,
input_size=feature['input_size'] * feature['num_stack'],
num_unit=param['num_unit'],
num_layer_main=param['num_layer_main'],
num_layer_second=param['num_layer_second'],
output_size_main=30,
output_size_second=output_size_second,
main_task_weight=param['main_task_weight'],
parameter_init=param['weight_init'],
clip_grad=param['clip_grad'],
clip_activation=param['clip_activation'],
dropout_ratio_input=param['dropout_input'],
dropout_ratio_hidden=param['dropout_hidden'],
num_proj=param['num_proj'],
weight_decay=param['weight_decay'])
network.model_dir = model_path
print(network.model_dir)
do_eval(network=network,
label_type_second=corpus['label_type_second'],
num_stack=feature['num_stack'],
num_skip=feature['num_skip'],
epoch=epoch)
def main(config_path):
# Load a config file (.yml)
with open(config_path, "r") as f:
config = yaml.load(f)
param = config['param']
if param['label_type_sub'] == 'phone61':
param['num_classes_sub'] = 61
elif param['label_type_sub'] == 'phone48':
param['num_classes_sub'] = 48
elif param['label_type_sub'] == 'phone39':
param['num_classes_sub'] = 39
# Model setting
CTCModel = load(model_type=param['model'])
network = CTCModel(batch_size=param['batch_size'],
input_size=param['input_size'] * param['num_stack'],
num_unit=param['num_unit'],
num_layer_main=param['num_layer_main'],
num_layer_sub=param['num_layer_sub'],
num_classes_main=33,
num_classes_sub=param['num_classes_sub'],
main_task_weight=param['main_task_weight'],
parameter_init=param['weight_init'],
clip_grad=param['clip_grad'],
clip_activation=param['clip_activation'],
dropout_ratio_input=param['dropout_input'],
dropout_ratio_hidden=param['dropout_hidden'],
num_proj=param['num_proj'],
weight_decay=param['weight_decay'])
network.model_name = param['model']
network.model_name += '_' + str(param['num_unit'])
network.model_name += '_main' + str(param['num_layer_main'])
network.model_name += '_sub' + str(param['num_layer_sub'])
network.model_name += '_' + param['optimizer']
network.model_name += '_lr' + str(param['learning_rate'])
if param['num_proj'] != 0:
network.model_name += '_proj' + str(param['num_proj'])
if param['dropout_input'] != 1:
network.model_name += '_dropi' + str(param['dropout_input'])
if param['dropout_hidden'] != 1:
network.model_name += '_droph' + str(param['dropout_hidden'])
if param['num_stack'] != 1:
network.model_name += '_stack' + str(param['num_stack'])
if param['weight_decay'] != 0:
network.model_name += '_weightdecay' + str(param['weight_decay'])
network.model_name += '_taskweight' + str(param['main_task_weight'])
if param['decay_rate'] != 1:
network.model_name += '_lrdecay' + \
str(param['decay_steps'] + param['decay_rate'])
# Set save path
network.model_dir = mkdir('/n/sd8/inaguma/result/timit/')
network.model_dir = mkdir_join(network.model_dir, 'ctc')
network.model_dir = mkdir_join(network.model_dir,
'char_' + param['label_type_sub'])
network.model_dir = mkdir_join(network.model_dir, network.model_name)
# Reset model directory
if not isfile(join(network.model_dir, 'complete.txt')):
tf.gfile.DeleteRecursively(network.model_dir)
tf.gfile.MakeDirs(network.model_dir)
else:
raise ValueError('File exists.')
# Set process name
setproctitle('timit_multictc')
# Save config file
shutil.copyfile(config_path, join(network.model_dir, 'config.yml'))
sys.stdout = open(join(network.model_dir, 'train.log'), 'w')
print(network.model_name)
do_train(network=network, param=param)
def main(config_path):
# Load a config file (.yml)
with open(config_path, "r") as f:
config = yaml.load(f)
corpus = config['corpus']
feature = config['feature']
param = config['param']
if corpus['label_type_second'] == 'phone61':
output_size_second = 61
elif corpus['label_type_second'] == 'phone48':
output_size_second = 48
elif corpus['label_type_second'] == 'phone39':
output_size_second = 39
# Model setting
CTCModel = load(model_type=config['model_name'])
network = CTCModel(batch_size=param['batch_size'],
input_size=feature['input_size'] * feature['num_stack'],
num_unit=param['num_unit'],
num_layer_main=param['num_layer_main'],
num_layer_second=param['num_layer_second'],
# bottleneck_dim=param['bottleneck_dim'],
output_size_main=30,
output_size_second=output_size_second,
main_task_weight=param['main_task_weight'],
parameter_init=param['weight_init'],
clip_grad=param['clip_grad'],
clip_activation=param['clip_activation'],
dropout_ratio_input=param['dropout_input'],
dropout_ratio_hidden=param['dropout_hidden'],
num_proj=param['num_proj'],
weight_decay=param['weight_decay'])
network.model_name = config['model_name'].upper()
network.model_name += '_' + str(param['num_unit'])
network.model_name += '_main' + str(param['num_layer_main'])
network.model_name += '_second' + str(param['num_layer_second'])
network.model_name += '_' + param['optimizer']
network.model_name += '_lr' + str(param['learning_rate'])
if param['num_proj'] != 0:
network.model_name += '_proj' + str(param['num_proj'])
if feature['num_stack'] != 1:
network.model_name += '_stack' + str(feature['num_stack'])
if param['weight_decay'] != 0:
network.model_name += '_weightdecay' + str(param['weight_decay'])
network.model_name += '_taskweight' + str(param['main_task_weight'])
# Set save path
network.model_dir = mkdir('/n/sd8/inaguma/result/timit/')
network.model_dir = mkdir_join(network.model_dir, 'ctc')
network.model_dir = mkdir_join(
network.model_dir, 'char_' + corpus['label_type_second'])
network.model_dir = mkdir_join(network.model_dir, network.model_name)
# Reset model directory
if not isfile(join(network.model_dir, 'complete.txt')):
tf.gfile.DeleteRecursively(network.model_dir)
tf.gfile.MakeDirs(network.model_dir)
else:
raise ValueError('File exists.')
# Set process name
setproctitle('multitaskctc_timit')
# Save config file
shutil.copyfile(config_path, join(network.model_dir, 'config.yml'))
sys.stdout = open(join(network.model_dir, 'train.log'), 'w')
print(network.model_name)
do_train(network=network,
optimizer=param['optimizer'],
learning_rate=param['learning_rate'],
batch_size=param['batch_size'],
epoch_num=param['num_epoch'],
label_type_second=corpus['label_type_second'],
num_stack=feature['num_stack'],
num_skip=feature['num_skip'])
sys.stdout = sys.__stdout__
def main(config_path):
# Read a config file (.yml)
with open(config_path, "r") as f:
config = yaml.load(f)
param = config['param']
# Except for a blank label
if param['label_type_main'] == 'kanji':
param['num_classes_main'] = 3386
elif param['label_type_main'] == 'kana':
param['num_classes_main'] = 147
if param['label_type_sub'] == 'kana':
param['num_classes_sub'] = 147
elif param['label_type_sub'] == 'phone':
param['num_classes_sub'] = 38
# Model setting
CTCModel = load(model_type=param['model'])
network = CTCModel(
batch_size=param['batch_size'],
input_size=param['input_size'] * param['num_stack'],
num_unit=param['num_unit'],
num_layer_main=param['num_layer_main'],
num_layer_sub=param['num_layer_sub'],
# bottleneck_dim=param['bottleneck_dim'],
num_classes_main=param['num_classes_main'],
num_classes_sub=param['num_classes_sub'],
main_task_weight=param['main_task_weight'],
parameter_init=param['weight_init'],
clip_grad=param['clip_grad'],
clip_activation=param['clip_activation'],
dropout_ratio_input=param['dropout_input'],
dropout_ratio_hidden=param['dropout_hidden'],
num_proj=param['num_proj'],
weight_decay=param['weight_decay'])
network.model_name = param['model']
network.model_name += '_' + str(param['num_unit'])
network.model_name += '_main' + str(param['num_layer_main'])
network.model_name += '_sub' + str(param['num_layer_sub'])
network.model_name += '_' + param['optimizer']
network.model_name += '_lr' + str(param['learning_rate'])
if param['bottleneck_dim'] != 0:
network.model_name += '_bottoleneck' + str(param['bottleneck_dim'])
if param['num_proj'] != 0:
network.model_name += '_proj' + str(param['num_proj'])
if param['num_stack'] != 1:
network.model_name += '_stack' + str(param['num_stack'])
if param['weight_decay'] != 0:
network.model_name += '_weightdecay' + str(param['weight_decay'])
network.model_name += '_taskweight' + str(param['main_task_weight'])
if param['train_data_size'] == 'large':
network.model_name += '_large'
# Set save path
network.model_dir = mkdir('/n/sd8/inaguma/result/csj/')
network.model_dir = mkdir_join(network.model_dir, 'ctc')
network.model_dir = mkdir_join(
network.model_dir,
param['label_type_main'] + '_' + param['label_type_sub'])
network.model_dir = mkdir_join(network.model_dir, network.model_name)
# Reset model directory
if not isfile(join(network.model_dir, 'complete.txt')):
tf.gfile.DeleteRecursively(network.model_dir)
tf.gfile.MakeDirs(network.model_dir)
else:
raise ValueError('File exists.')
# Set process name
setproctitle('csj_multictc_' + param['label_type_main'] + '_' +
param['label_type_sub'] + '_' + param['train_data_size'])
# Save config file
shutil.copyfile(config_path, join(network.model_dir, 'config.yml'))
sys.stdout = open(join(network.model_dir, 'train.log'), 'w')
print(network.model_name)
do_train(network=network, param=param)
sys.stdout = sys.__stdout__