def backup_settings(args):
"""
The settings saved in setting_folder_path/task_name/cur_data_setting.json and setting_folder_path/task_name/cur_task_setting.json
:param args:
:return: None
"""
setting_folder_path = args.setting_folder_path
dm_json_path = os.path.join(setting_folder_path, 'cur_data_setting.json')
tsm_json_path = os.path.join(setting_folder_path, 'cur_task_setting.json')
dm = DataTask('task_reg',
dm_json_path) if os.path.isfile(dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
task_name = args.task_name_record
setting_backup = os.path.join(setting_folder_path, task_name + '_backup')
os.makedirs(setting_backup, exist_ok=True)
dm_backup_json_path = os.path.join(setting_backup, 'cur_data_setting.json')
tsm_backup_json_path = os.path.join(setting_backup,
'cur_task_setting.json')
if tsm.task_par['tsk_set'][
'model'] == 'reg_net' and 'mermaid' in tsm.task_par['tsk_set'][
'method_name']:
mermaid_backup_json_path = os.path.join(setting_backup,
'mermaid_nonp_settings.json')
mermaid_setting_json = tsm.task_par['tsk_set']['reg']['mermaid_net'][
'mermaid_net_json_pth']
if len(mermaid_setting_json) == 0:
mermaid_setting_json = os.path.join(setting_folder_path,
'mermaid_nonp_settings.json')
mermaid_setting = pars.ParameterDict()
mermaid_setting.load_JSON(mermaid_setting_json)
mermaid_setting.write_ext_JSON(mermaid_backup_json_path)
tsm.save(tsm_backup_json_path)
if dm is not None:
dm.save(dm_backup_json_path)
def init_train_env(setting_path,
output_root_path,
task_name,
data_task_name=None):
"""
create train environment.
:param setting_path: the path to load 'cur_task_setting.json' and 'cur_data_setting.json' (optional if the related settings are in cur_task_setting)
:param output_root_path: the output path
:param data_task_name: data task name i.e. lung_seg_task , oai_seg_task
:param task_name: task name i.e. run_unet, run_with_ncc_loss
:return:
"""
dm_json_path = os.path.join(setting_path, 'cur_data_setting.json')
tsm_json_path = os.path.join(setting_path, 'cur_task_setting.json')
assert os.path.isfile(tsm_json_path), "task setting not exists"
dm = DataTask('task_reg',
dm_json_path) if os.path.isfile(dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
data_task_name = data_task_name if len(data_task_name) else 'custom'
data_task_path = os.path.join(output_root_path, data_task_name)
if dm is not None:
dm.data_par['datapro']['dataset']['output_path'] = output_root_path
dm.data_par['datapro']['dataset']['task_name'] = data_task_name
tsm.task_par['tsk_set']['task_name'] = task_name
tsm.task_par['tsk_set']['output_root_path'] = data_task_path
return dm, tsm
def init_train_env(self):
assert os.path.isfile(self.tsm_json_path),"task setting not exists"
dm = DataTask('task_reg', self.dm_json_path) if os.path.isfile(self.dm_json_path) else None
tsm = ModelTask('task_reg',tsm_json_path)
self.data_task_name = self.data_task_name if len(self.data_task_name)>0 else 'custom'
if dm is not None:
dm.data_par['datapro']['dataset']['output_path'] = self.output_root_path
dm.data_par['datapro']['dataset']['task_name'] = self.data_task_name
tsm.task_par['tsk_set']['task_name'] = self.task_name
tsm.task_par['tsk_set']['output_root_path'] = self.data_task_path
return dm, tsm
def save_settings(self):
self.setting_folder_path = args.setting_folder_path
self.dm_json_path = os.path.join(setting_folder_path, 'cur_data_setting.json')
self.tsm_json_path = os.path.join(setting_folder_path, 'cur_task_setting.json')
dm = DataTask('task_reg', self.dm_json_path) if os.path.isfile(self.dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
task_name = args.task_name_record
setting_backup = os.path.join(setting_folder_path, task_name+'_backup')
os.makedirs(setting_backup, exist_ok=True)
dm_backup_json_path = os.path.join(setting_backup, 'cur_data_setting.json')
tsm_backup_json_path =os.path.join(setting_backup,'cur_task_setting.json')
tsm.save(tsm_backup_json_path)
if dm is not None:
dm.save(dm_backup_json_path)
def init_test_env(setting_path, output_path, file_list, fname_list):
"""
create test environment, the file list would be saved into output_path/reg/test/file_path_list.txt,
a corresponding auto-parsed filename list would also be saved in output/path/reg/test/file_name_list.txt
:param setting_path: the path to load 'cur_task_setting.json' and 'cur_data_setting.json' (optional if the related settings are in cur_task_setting)
:param output_path: the output path of the task
:param image_path_list: the image list, each item refers to the abstract path of the image
:param l_path_list:optional, the label of image list, each item refers to the abstract path of the image
:return: tuple of ParameterDict, datapro (optional) and tsk_set
"""
dm_json_path = os.path.join(setting_path, 'cur_data_setting.json')
tsm_json_path = os.path.join(setting_path, 'cur_task_setting.json')
assert os.path.isfile(tsm_json_path), "task setting not exists"
dm = DataTask('task_reg',
dm_json_path) if os.path.isfile(dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
file_num = len(file_list)
os.makedirs(os.path.join(output_path, 'seg/test'), exist_ok=True)
os.makedirs(os.path.join(output_path, 'seg/res'), exist_ok=True)
file_txt_path = os.path.join(output_path, 'seg/test/file_path_list.txt')
fn_txt_path = os.path.join(output_path, 'seg/test/file_name_list.txt')
has_label = len(file_list[0]) == 2
if fname_list is None:
if has_label:
fname_list = [
get_file_name(file_list[i][0]) for i in range(file_num)
]
else:
fname_list = [get_file_name(file_list[i]) for i in range(file_num)]
write_list_into_txt(file_txt_path, file_list)
write_list_into_txt(fn_txt_path, fname_list)
data_task_name = 'seg'
cur_task_name = 'res'
if dm is not None:
dm.data_par['datapro']['dataset']['output_path'] = output_path
dm.data_par['datapro']['dataset']['task_name'] = data_task_name
tsm.task_par['tsk_set']['task_name'] = cur_task_name
tsm.task_par['tsk_set']['output_root_path'] = os.path.join(
output_path, data_task_name)
return dm, tsm
def backup_settings(args):
"""
The settings saved in setting_folder_path/task_name/cur_data_setting.json and setting_folder_path/task_name/cur_task_setting.json
:param args:
:return: None
"""
setting_folder_path = args.setting_folder_path
dm_json_path = os.path.join(setting_folder_path, 'cur_data_setting.json')
tsm_json_path = os.path.join(setting_folder_path, 'cur_task_setting.json')
dm = DataTask('task_reg',
dm_json_path) if os.path.isfile(dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
task_name = args.task_name_record
setting_backup = os.path.join(setting_folder_path, task_name + '_backup')
os.makedirs(setting_backup, exist_ok=True)
dm_backup_json_path = os.path.join(setting_backup, 'cur_data_setting.json')
tsm_backup_json_path = os.path.join(setting_backup,
'cur_task_setting.json')
tsm.save(tsm_backup_json_path)
if dm is not None:
dm.save(dm_backup_json_path)
def init_train_env(setting_path,
output_root_path,
task_name,
data_task_name=None):
"""
create train environment.
:param setting_path: the path to load 'cur_task_setting.json' and 'cur_data_setting.json' (optional if the related settings are in cur_task_setting)
:param output_root_path: the output path
:param data_task_name: data task name i.e. lung_reg_task , oai_reg_task
:param task_name: task name i.e. run_training_vsvf_task, run_training_rdmm_task
:return:
"""
dm_json_path = os.path.join(setting_path, 'cur_data_setting.json')
tsm_json_path = os.path.join(setting_path, 'cur_task_setting.json')
assert os.path.isfile(tsm_json_path), "task setting not exists"
dm = DataTask('task_reg',
dm_json_path) if os.path.isfile(dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
data_task_name = data_task_name if len(data_task_name) else 'custom'
data_task_path = os.path.join(output_root_path, data_task_name)
if dm is not None:
dm.data_par['datapro']['dataset']['output_path'] = output_root_path
dm.data_par['datapro']['dataset']['task_name'] = data_task_name
tsm.task_par['tsk_set']['task_name'] = task_name
tsm.task_par['tsk_set']['output_root_path'] = data_task_path
if tsm.task_par['tsk_set'][
'model'] == 'reg_net' and 'mermaid' in tsm.task_par['tsk_set'][
'method_name']:
mermaid_setting_json = tsm.task_par['tsk_set']['reg']['mermaid_net'][
'mermaid_net_json_pth']
if len(mermaid_setting_json) == 0:
tsm.task_par['tsk_set']['reg']['mermaid_net'][
'mermaid_net_json_pth'] = os.path.join(
setting_path, 'mermaid_nonp_settings.json')
return dm, tsm
def init_test_env(setting_path,
output_path,
registration_pair_list,
pair_name_list=None):
"""
create test environment, the pair list would be saved into output_path/reg/test/pair_path_list.txt,
a corresponding auto-parsed filename list would also be saved in output/path/reg/test/pair_name_list.txt
:param setting_path: the path to load 'cur_task_setting.json' and 'cur_data_setting.json' (optional if the related settings are in cur_task_setting)
:param output_path: the output path of the task
:param registration_pair_list: including source_path_list, target_path_list, l_source_path_list, l_target_path_list
:return: tuple of ParameterDict, datapro (optional) and tsk_set
"""
source_path_list, target_path_list, l_source_path_list, l_target_path_list = registration_pair_list
dm_json_path = os.path.join(setting_path, 'cur_data_setting.json')
tsm_json_path = os.path.join(setting_path, 'cur_task_setting.json')
assert os.path.isfile(tsm_json_path), "task setting {} not exists".format(
tsm_json_path)
dm = DataTask('task_reg',
dm_json_path) if os.path.isfile(dm_json_path) else None
tsm = ModelTask('task_reg', tsm_json_path)
file_num = len(source_path_list)
if l_source_path_list is not None and l_target_path_list is not None:
file_list = [[
source_path_list[i], target_path_list[i], l_source_path_list[i],
l_target_path_list[i]
] for i in range(file_num)]
else:
file_list = [[source_path_list[i], target_path_list[i]]
for i in range(file_num)]
os.makedirs(os.path.join(output_path, 'reg/test'), exist_ok=True)
os.makedirs(os.path.join(output_path, 'reg/res'), exist_ok=True)
pair_txt_path = os.path.join(output_path, 'reg/test/pair_path_list.txt')
fn_txt_path = os.path.join(output_path, 'reg/test/pair_name_list.txt')
if pair_name_list is None:
pair_name_list = [
generate_pair_name([file_list[i][0], file_list[i][1]], detail=True)
for i in range(file_num)
]
write_list_into_txt(pair_txt_path, file_list)
write_list_into_txt(fn_txt_path, pair_name_list)
data_task_name = 'reg'
cur_task_name = 'res'
if dm is not None:
dm.data_par['datapro']['dataset']['output_path'] = output_path
dm.data_par['datapro']['dataset']['task_name'] = data_task_name
tsm.task_par['tsk_set']['task_name'] = cur_task_name
tsm.task_par['tsk_set']['output_root_path'] = os.path.join(
output_path, data_task_name)
if tsm.task_par['tsk_set']['model'] == 'reg_net':
tsm.task_par['tsk_set']['reg']['mermaid_net'][
'mermaid_net_json_pth'] = os.path.join(
setting_path, 'mermaid_nonp_settings.json')
if tsm.task_par['tsk_set']['model'] == 'mermaid_iter':
tsm.task_par['tsk_set']['reg']['mermaid_iter'][
'mermaid_affine_json'] = os.path.join(
setting_path, 'mermaid_affine_settings.json')
tsm.task_par['tsk_set']['reg']['mermaid_iter'][
'mermaid_nonp_json'] = os.path.join(setting_path,
'mermaid_nonp_settings.json')
return dm, tsm