def __init__(self, config, model):
super(Trainer, self).__init__(config, model)
self.logger = getLogger()
self.learner = config['learner']
self.learning_rate = config['learning_rate']
self.epochs = config['epochs']
self.eval_step = min(config['eval_step'], self.epochs)
self.stopping_step = config['stopping_step']
self.valid_metric = config['valid_metric'].lower()
self.valid_metric_bigger = config['valid_metric_bigger']
self.test_batch_size = config['eval_batch_size']
self.device = config['device']
self.checkpoint_dir = config['checkpoint_dir']
ensure_dir(self.checkpoint_dir)
saved_model_file = '{}-{}.pth'.format(self.config['model'],
get_local_time())
self.saved_model_file = os.path.join(self.checkpoint_dir,
saved_model_file)
self.start_epoch = 0
self.cur_step = 0
self.best_valid_score = -1
self.best_valid_result = None
self.train_loss_dict = dict()
self.optimizer = self._build_optimizer()
self.eval_type = config['eval_type']
if self.eval_type == EvaluatorType.INDIVIDUAL:
self.evaluator = LossEvaluator(config)
else:
self.evaluator = TopKEvaluator(config)
self.item_tensor = None
self.tot_item_num = None
self.iid_field = config['ITEM_ID_FIELD']
def __init__(self, config, model):
super(Trainer, self).__init__(config, model)
self.logger = getLogger()
self.tensorboard = get_tensorboard(self.logger)
self.learner = config['learner']
self.learning_rate = config['learning_rate']
self.epochs = config['epochs']
self.eval_step = min(config['eval_step'], self.epochs)
self.stopping_step = config['stopping_step']
self.clip_grad_norm = config['clip_grad_norm']
self.valid_metric = config['valid_metric'].lower()
self.valid_metric_bigger = config['valid_metric_bigger']
self.test_batch_size = config['eval_batch_size']
self.gpu_available = torch.cuda.is_available() and config['use_gpu']
self.device = config['device']
self.checkpoint_dir = config['checkpoint_dir']
ensure_dir(self.checkpoint_dir)
saved_model_file = '{}-{}.pth'.format(self.config['model'],
get_local_time())
self.saved_model_file = os.path.join(self.checkpoint_dir,
saved_model_file)
self.weight_decay = config['weight_decay']
self.start_epoch = 0
self.cur_step = 0
self.best_valid_score = -np.inf if self.valid_metric_bigger else np.inf
self.best_valid_result = None
self.train_loss_dict = dict()
self.optimizer = self._build_optimizer(self.model.parameters())
self.eval_type = config['eval_type']
self.eval_collector = Collector(config)
self.evaluator = Evaluator(config)
self.item_tensor = None
self.tot_item_num = None
def __init__(self, config, model):
super(Trainer, self).__init__(config, model)
self.logger = getLogger()
self.learner = config['learner']
self.learning_rate = config['learning_rate']
self.epochs = config['epochs']
self.eval_step = min(config['eval_step'], self.epochs)
self.stopping_step = config['stopping_step']
self.clip_grad_norm = config['clip_grad_norm']
self.valid_metric = config['valid_metric'].lower()
self.valid_metric_bigger = config['valid_metric_bigger']
self.test_batch_size = config['eval_batch_size']
self.device = config['device']
self.checkpoint_dir = config['checkpoint_dir']
ensure_dir(self.checkpoint_dir)
saved_model_file = '{}-{}.pth'.format(self.config['model'],
get_local_time())
self.saved_model_file = os.path.join(self.checkpoint_dir,
saved_model_file)
self.weight_decay = config['weight_decay']
self.draw_pic = config['draw_pic']
self.print_latex_code = config['print_latex_code']
self.start_epoch = 0
self.cur_step = 0
self.best_valid_score = -1
self.best_valid_result = None
self.train_loss_dict = dict()
self.optimizer = self._build_optimizer()
self.eval_type = config['eval_type']
self.evaluator = ProxyEvaluator(config)
self.item_tensor = None
self.tot_item_num = None
def save_split_dataloaders(config, dataloaders):
"""Save split dataloaders.
Args:
config (Config): An instance object of Config, used to record parameter information.
dataloaders (tuple of AbstractDataLoader): The split dataloaders.
"""
ensure_dir(config['checkpoint_dir'])
save_path = config['checkpoint_dir']
saved_dataloaders_file = f'{config["dataset"]}-for-{config["model"]}-dataloader.pth'
file_path = os.path.join(save_path, saved_dataloaders_file)
logger = getLogger()
logger.info(set_color('Saving split dataloaders into', 'pink') + f': [{file_path}]')
with open(file_path, 'wb') as f:
pickle.dump(dataloaders, f)
def __init__(self, config, model):
super(xgboostTrainer, self).__init__(config, model)
self.xgb = __import__('xgboost')
self.logger = getLogger()
self.label_field = config['LABEL_FIELD']
self.xgb_model = config['xgb_model']
self.convert_token_to_onehot = self.config['convert_token_to_onehot']
# DMatrix params
self.weight = config['xgb_weight']
self.base_margin = config['xgb_base_margin']
self.missing = config['xgb_missing']
self.silent = config['xgb_silent']
self.feature_names = config['xgb_feature_names']
self.feature_types = config['xgb_feature_types']
self.nthread = config['xgb_nthread']
# train params
self.params = config['xgb_params']
self.num_boost_round = config['xgb_num_boost_round']
self.evals = ()
self.obj = config['xgb_obj']
self.feval = config['xgb_feval']
self.maximize = config['xgb_maximize']
self.early_stopping_rounds = config['xgb_early_stopping_rounds']
self.evals_result = {}
self.verbose_eval = config['xgb_verbose_eval']
self.callbacks = None
# evaluator
self.eval_type = config['eval_type']
self.epochs = config['epochs']
self.eval_step = min(config['eval_step'], self.epochs)
self.valid_metric = config['valid_metric'].lower()
self.evaluator = ProxyEvaluator(config)
# model saved
self.checkpoint_dir = config['checkpoint_dir']
ensure_dir(self.checkpoint_dir)
saved_model_file = '{}-{}.pth'.format(self.config['model'],
get_local_time())
self.saved_model_file = os.path.join(self.checkpoint_dir,
saved_model_file)
def save_datasets(save_path, name, dataset):
"""Save split datasets.
Args:
save_path (str): The path of directory for saving.
name (str or list of str): The stage of dataloader. It can only take two values: 'train' or 'evaluation'.
dataset (Dataset or list of Dataset): The split datasets.
"""
if (not isinstance(name, list)) and (not isinstance(dataset, list)):
name = [name]
dataset = [dataset]
if len(name) != len(dataset):
raise ValueError(
f'Length of name {name} should equal to length of dataset {dataset}.'
)
for i, d in enumerate(dataset):
cur_path = os.path.join(save_path, name[i])
ensure_dir(cur_path)
d.save(cur_path)
def __init__(self, config, model):
super(DecisionTreeTrainer, self).__init__(config, model)
self.logger = getLogger()
self.label_field = config['LABEL_FIELD']
self.convert_token_to_onehot = self.config['convert_token_to_onehot']
# evaluator
self.eval_type = config['eval_type']
self.epochs = config['epochs']
self.eval_step = min(config['eval_step'], self.epochs)
self.valid_metric = config['valid_metric'].lower()
self.evaluator = ProxyEvaluator(config)
# model saved
self.checkpoint_dir = config['checkpoint_dir']
ensure_dir(self.checkpoint_dir)
saved_model_file = '{}-{}.pth'.format(self.config['model'], get_local_time())
self.saved_model_file = os.path.join(self.checkpoint_dir, saved_model_file)
def __init__(self, config, model):
super(DecisionTreeTrainer, self).__init__(config, model)
self.logger = getLogger()
self.tensorboard = get_tensorboard(self.logger)
self.label_field = config['LABEL_FIELD']
self.convert_token_to_onehot = self.config['convert_token_to_onehot']
# evaluator
self.eval_type = config['eval_type']
self.epochs = config['epochs']
self.eval_step = min(config['eval_step'], self.epochs)
self.valid_metric = config['valid_metric'].lower()
self.eval_collector = Collector(config)
self.evaluator = Evaluator(config)
# model saved
self.checkpoint_dir = config['checkpoint_dir']
ensure_dir(self.checkpoint_dir)
temp_file = '{}-{}-temp.pth'.format(self.config['model'],
get_local_time())
self.temp_file = os.path.join(self.checkpoint_dir, temp_file)
temp_best_file = '{}-{}-temp-best.pth'.format(self.config['model'],
get_local_time())
self.temp_best_file = os.path.join(self.checkpoint_dir, temp_best_file)
saved_model_file = '{}-{}.pth'.format(self.config['model'],
get_local_time())
self.saved_model_file = os.path.join(self.checkpoint_dir,
saved_model_file)
self.stopping_step = config['stopping_step']
self.valid_metric_bigger = config['valid_metric_bigger']
self.cur_step = 0
self.best_valid_score = -np.inf if self.valid_metric_bigger else np.inf
self.best_valid_result = None
