def get_data_and_config(global_args):
data_loader = DataLoader(global_args)
train_set, test_set = data_loader.split()
model_args = get_model_args(data_loader.item_nums, global_args)
logging.info(dict_to_str(model_args, "Configurations"))
return model_args, train_set, test_set
def get_data_and_config(global_args):
data_loader = DataLoader(global_args)
train_set, test_set = data_loader.split()
model_args = get_model_args(data_loader.item_nums, global_args)
logging.info(dict_to_str(model_args, "Model Configurations"))
if model_args["gen_sub_sess"]:
train_set = data_loader.generate_sub_sessions(train_set,
model_args["pad_token"])
return model_args, train_set, test_set
def log_configs(args):
logging.info(dict_to_str(args, "Global Configurations"))
# 0. setup folder and logger
path = setup_folder(configs)
configs.update({"store_path": path})
logger.setup_logger(configs)
# 1. setup env, seed and gpu
environment_preset(configs)
gpu_config = get_gpu_config(configs["occupy"])
sess = tf.Session(config=gpu_config)
# 2. prepare dataset
data_loader = DataLoaderPretrain(configs, configs["min_freq"])
train_set, test_set = data_loader.split()
data_loader.save_dict()
logging.info("item dict saved to itemdict.pkl")
# 3. update model configs
configs = update_model_args(data_loader.item_nums)
logging.info(dict_to_str(configs, "Configurations"))
# 4. create model
model = NextItNet(configs)
with tf.variable_scope(tf.get_variable_scope(), reuse=tf.AUTO_REUSE):
optimizer = tf.train.AdamOptimizer(configs["lr"]).minimize(
model.loss_train)
# 5. launch the rocket
start()
sess.close()