def main(_):
avalialbe_cpu, available_gpu, available_cpu_num, available_gpu_num = get_available_gpus(
)
forward_backward_device = list()
if available_gpu_num == 0:
print(
"No available GPU found!!! The calculation will be performed with CPU only."
)
args.device_mode = 0
parameter_update_device = avalialbe_cpu[0]
forward_backward_device.append(avalialbe_cpu[0])
# parameter_update_device = available_gpu[0]
# forward_backward_device.append(available_gpu[0])
forward_backward_device_list = list()
forward_backward_device_list.extend(forward_backward_device)
print("Available devices for forward && backward:")
for device in forward_backward_device_list:
print(device)
print("Available devices for parameter update:%s" %
parameter_update_device)
model_for_train = UNet(
training_mode=args.training_mode,
base_trained_model_dir=args.base_trained_model_dir,
infer_obj_name=args.infer_name,
infer_copy_num=args.infer_copy_num,
ebdd_dictionary_dim=args.ebdd_dictionary_dim,
base_training_font_num=args.base_training_font_num,
parameter_update_device=parameter_update_device,
forward_backward_device=forward_backward_device_list)
if os.path.exists(args.inferred_result_saving_path):
shutil.rmtree(args.inferred_result_saving_path)
os.makedirs(args.inferred_result_saving_path)
model_for_train.infer_procedures(
inferred_result_saving_path=args.inferred_result_saving_path,
base_trained_model_dir=args.base_trained_model_dir,
freeze_ebdd_weights=0,
freeze_encoder=0,
freeze_decoder=0)
def main(_):
avalialbe_cpu, available_gpu, available_cpu_num, available_gpu_num = get_available_gpus(
)
forward_backward_device = list()
if available_gpu_num == 0:
print(
"No available GPU found!!! The calculation will be performed with CPU only."
)
args.device_mode = 0
# parameter_update_device = avalialbe_cpu[0]
# forward_backward_device.append(avalialbe_cpu[0])
parameter_update_device = available_gpu[0]
forward_backward_device.append(available_gpu[0])
forward_backward_device_list = list()
forward_backward_device_list.extend(forward_backward_device)
print("Available devices for forward && backward:")
for device in forward_backward_device_list:
print(device)
print("Available devices for parameter update:%s" %
parameter_update_device)
model_for_train = UNet(
training_mode=args.training_mode,
base_trained_model_dir=args.base_trained_model_dir,
infer_obj_name=args.infer_name,
infer_copy_num=args.infer_copy_num,
ebdd_dictionary_dim=args.ebdd_dictionary_dim,
base_training_font_num=args.base_training_font_num,
parameter_update_device=parameter_update_device,
forward_backward_device=forward_backward_device_list)
base_models = listdir(args.base_trained_model_dir)
for traveller in base_models:
if not traveller.find('DS') == -1:
base_models.remove(traveller)
base_models_with_path = list()
for ii in range(len(base_models)):
base_models_with_path.append(
os.path.join(args.base_trained_model_dir, base_models[ii]))
print("Found Model No:%d named %s" % (ii, base_models[ii]))
for ii in range(len(base_models_with_path)):
current_inferred_result_saving_path = os.path.join(
args.inferred_result_saving_path, base_models[ii])
not_freeze_encoder = current_inferred_result_saving_path.find(
'encoder_not_freeze')
not_freeze_decoder = current_inferred_result_saving_path.find(
'decoder_not_freeze')
if args.training_mode == 0:
freeze_ebdd_weights = 1
freeze_encoder = 0
freeze_decoder = 0
else:
freeze_ebdd_weights = 0
if not not_freeze_encoder == -1:
freeze_encoder = 1
else:
freeze_encoder = 0
if not not_freeze_decoder == -1:
freeze_decoder = 1
else:
freeze_decoder = 0
if os.path.exists(current_inferred_result_saving_path):
shutil.rmtree(current_inferred_result_saving_path)
os.makedirs(current_inferred_result_saving_path)
print("New inferred dir created for %s." %
(current_inferred_result_saving_path))
model_for_train.infer_procedures(
inferred_result_saving_path=current_inferred_result_saving_path,
base_trained_model_dir=base_models_with_path[ii],
freeze_ebdd_weights=freeze_ebdd_weights,
freeze_encoder=freeze_encoder,
freeze_decoder=freeze_decoder)
