def load_model(self, folder_path, file_name = None, is_earlystopping_format = False):
if file_name is None:
file_name = self.RECOMMENDER_NAME
self._print("Loading model from file '{}'".format(folder_path + file_name))
if not is_earlystopping_format:
shutil.unpack_archive(folder_path + file_name + ".zip",
folder_path + file_name + "/",
"zip")
dataIO = DataIO(folder_path=folder_path + file_name + "/")
data_dict = dataIO.load_data(file_name="fit_attributes")
for attrib_name in data_dict.keys():
self.__setattr__(attrib_name, data_dict[attrib_name])
tf.compat.v1.reset_default_graph()
q_dims = self.p_dims[::-1]
self.vae = _MultVAE_original(self.p_dims, q_dims=q_dims, lr=self.learning_rate, lam=self.l2_reg, random_seed=98765)
self.saver, self.logits_var, self.loss_var, self.train_op_var, self.merged_var = self.vae.build_graph()
self.sess = tf.compat.v1.Session()
self.sess.run(tf.compat.v1.global_variables_initializer())
self.saver.restore(self.sess, folder_path + file_name + "/session")
# self.summary_writer = tf.compat.v1.summary.FileWriter(self.log_dir, graph=tf.compat.v1.get_default_graph())
shutil.rmtree(folder_path + file_name + "/", ignore_errors=True)
self._print("Loading complete")
def load_data(self, save_folder_path):
dataIO = DataIO(folder_path=save_folder_path)
global_attributes_dict = dataIO.load_data(
file_name="dataset_global_attributes")
for attrib_name, attrib_object in global_attributes_dict.items():
self.__setattr__(attrib_name, attrib_object)
self.AVAILABLE_URM = dataIO.load_data(file_name="dataset_URM")
if self._HAS_ICM:
self.AVAILABLE_ICM = dataIO.load_data(file_name="dataset_ICM")
self.AVAILABLE_ICM_feature_mapper = dataIO.load_data(
file_name="dataset_ICM_mappers")
if self._HAS_UCM:
self.AVAILABLE_UCM = dataIO.load_data(file_name="dataset_UCM")
self.AVAILABLE_UCM_feature_mapper = dataIO.load_data(
file_name="dataset_UCM_mappers")
if self._HAS_additional_mapper:
self.dataset_additional_mappers = dataIO.load_data(
file_name="dataset_additional_mappers")
def load_model(self, folder_path, file_name=None):
if file_name is None:
file_name = self.RECOMMENDER_NAME
self._print("Loading model from file '{}'".format(folder_path +
file_name))
dataIO = DataIO(folder_path=folder_path)
data_dict = dataIO.load_data(file_name=file_name)
for attrib_name in data_dict.keys():
self.__setattr__(attrib_name, data_dict[attrib_name])
self._print("Loading complete")
def _load_previously_built_split_and_attributes(self, save_folder_path):
"""
Loads all URM and ICM
:return:
"""
if self.allow_cold_users:
allow_cold_users_suffix = "allow_cold_users"
else:
allow_cold_users_suffix = "only_warm_users"
if self.user_wise:
user_wise_string = "user_wise"
else:
user_wise_string = "global_sample"
name_suffix = "_{}_{}".format(allow_cold_users_suffix,
user_wise_string)
dataIO = DataIO(folder_path=save_folder_path)
split_parameters_dict = dataIO.load_data(file_name="split_parameters" +
name_suffix)
for attrib_name in split_parameters_dict.keys():
self.__setattr__(attrib_name, split_parameters_dict[attrib_name])
self.SPLIT_GLOBAL_MAPPER_DICT = dataIO.load_data(
file_name="split_mappers" + name_suffix)
self.SPLIT_URM_DICT = dataIO.load_data(file_name="split_URM" +
name_suffix)
if len(self.dataReader_object.get_loaded_ICM_names()) > 0:
self.SPLIT_ICM_DICT = dataIO.load_data(file_name="split_ICM" +
name_suffix)
self.SPLIT_ICM_MAPPER_DICT = dataIO.load_data(
file_name="split_ICM_mappers" + name_suffix)
if len(self.dataReader_object.get_loaded_UCM_names()) > 0:
self.SPLIT_UCM_DICT = dataIO.load_data(file_name="split_UCM" +
name_suffix)
self.SPLIT_UCM_MAPPER_DICT = dataIO.load_data(
file_name="split_UCM_mappers" + name_suffix)