Example #1
0
 def __init__(self, config, result):
     self.config = config
     self.result = result
     self.setup = self._nothing_
     self.cleanup = self._nothing_
     self.case = []
     self.name = utils.get_script_name()
Example #2
0
 def __init__(self, config, result):
     self.config = config
     self.result = result
     self.setup = self._nothing_
     self.cleanup = self._nothing_
     self.case = []
     self.name = utils.get_script_name()
Example #3
0
 def gen_file_name(self):
     """ """
     m = hashlib.md5()
     m.update(sys.argv[0])
     m.update(time.strftime("%d_%m_%Y_%H_%M_%S", self.gtime.start_date))        
     name_script = utils.get_script_name()
     name_hash = m.hexdigest()[0:16].upper()
     return"%s_%s.log" % (name_script, name_hash)
Example #4
0
 def gen_file_name(self):
     """ """
     m = hashlib.md5()
     m.update(sys.argv[0])
     m.update(time.strftime("%d_%m_%Y_%H_%M_%S", self.gtime.start_date))
     name_script = utils.get_script_name()
     name_hash = m.hexdigest()[0:16].upper()
     return"%s_%s.log" % (name_script, name_hash)
Example #5
0
 def set_doc(self, doc):
     des = dict()
     des[KEY_TYPE] = TYPE_SCRIPT
     des[KEY_NAME] = utils.get_script_name()
     if doc is None :
         des[KEY_DOC] = ""
     else:
         des[KEY_DOC] = Pydoc.clean(doc)
     self.result.doc(des)
Example #6
0
    p_transform_augment=None,
    p_transform=p_transform,
    world_coord_system=False,
    luna_origin=None)

rng = patch_class_config.rng

# candidates after segmentations path
predictions_dir = utils.get_dir_path('model-predictions',
                                     pathfinder.METADATA_PATH)
segmentation_outputs_path = predictions_dir + '/%s' % seg_config_name
id2candidates_path = utils_lung.get_candidates_paths(segmentation_outputs_path)

# filter our those, who are already generated
predictions_dir = utils.get_dir_path('model-predictions', pathfinder.METADATA_PATH) \
                  + '/' + utils.get_script_name(__file__)
exclude_pids = utils_lung.get_generated_pids(predictions_dir)

data_iterator = data_iterators.CandidatesDSBDataGenerator(
    data_path=pathfinder.DATA_PATH,
    transform_params=p_transform,
    data_prep_fun=data_prep_function,
    id2candidates_path=id2candidates_path,
    exclude_pids=exclude_pids)


def build_model():
    metadata_dir = utils.get_dir_path('models', pathfinder.METADATA_PATH)
    metadata_path = utils.find_model_metadata(
        metadata_dir,
        patch_class_config.__name__.split('.')[-1])
Example #7
0
data_prep_function = patch_class_config.partial(patch_class_config.data_prep_function,
                                                p_transform_augment=None,
                                                p_transform=p_transform,
                                                world_coord_system=False,
                                                luna_origin=None)

rng = patch_class_config.rng

# candidates after segmentations path
predictions_dir = utils.get_dir_path('model-predictions', pathfinder.METADATA_PATH)
segmentation_outputs_path = predictions_dir + '/%s' % seg_config_name
id2candidates_path = utils_lung.get_candidates_paths(segmentation_outputs_path)

# filter our those, who are already generated
predictions_dir = utils.get_dir_path('model-predictions', pathfinder.METADATA_PATH) \
                  + '/' + utils.get_script_name(__file__)
exclude_pids = utils_lung.get_generated_pids(predictions_dir)

data_iterator = data_iterators.CandidatesDSBDataGenerator(data_path=pathfinder.DATA_PATH,
                                                          transform_params=p_transform,
                                                          data_prep_fun=data_prep_function,
                                                          id2candidates_path=id2candidates_path,
                                                          exclude_pids=exclude_pids)


def build_model():
    metadata_dir = utils.get_dir_path('models', pathfinder.METADATA_PATH)
    metadata_path = utils.find_model_metadata(metadata_dir, patch_class_config.__name__.split('.')[-1])
    metadata = utils.load_pkl(metadata_path)

    print 'Build model'