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.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.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 __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
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 __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 fit(self, train_data, valid_data=None, verbose=True, saved=True, show_progress=False, callback_fn=None): r"""Train the model based on the train data and the valid data. Args: train_data (DataLoader): the train data valid_data (DataLoader, optional): the valid data, default: None. If it's None, the early_stopping is invalid. verbose (bool, optional): whether to write training and evaluation information to logger, default: True saved (bool, optional): whether to save the model parameters, default: True show_progress (bool): Show the progress of training epoch and evaluate epoch. Defaults to ``False``. callback_fn (callable): Optional callback function executed at end of epoch. Includes (epoch_idx, valid_score) input arguments. Returns: (float, dict): best valid score and best valid result. If valid_data is None, it returns (-1, None) """ if saved and self.start_epoch >= self.epochs: self._save_checkpoint(-1) for epoch_idx in range(self.start_epoch, self.epochs): # train training_start_time = time() train_loss = self._train_epoch(train_data, epoch_idx, show_progress=show_progress) self.train_loss_dict[epoch_idx] = sum(train_loss) if isinstance( train_loss, tuple) else train_loss training_end_time = time() train_loss_output = \ self._generate_train_loss_output(epoch_idx, training_start_time, training_end_time, train_loss) #if verbose: # self.logger.info(train_loss_output) # eval if self.eval_step <= 0 or not valid_data: if saved: self._save_checkpoint(epoch_idx) update_output = set_color( 'Saving current', 'blue') + ': %s' % self.saved_model_file #if verbose: # self.logger.info(update_output) continue if (epoch_idx + 1) % self.eval_step == 0: valid_start_time = time() valid_score, valid_result = self._valid_epoch( valid_data, show_progress=show_progress) self.best_valid_score, self.cur_step, stop_flag, update_flag = early_stopping( valid_score, self.best_valid_score, self.cur_step, max_step=self.stopping_step, bigger=self.valid_metric_bigger) valid_end_time = time() valid_score_output = (set_color("epoch %d evaluating", 'green') + " [" + set_color("time", 'blue') + ": %.2fs, " + set_color("valid_score", 'blue') + ": %f]") % \ (epoch_idx, valid_end_time - valid_start_time, valid_score) valid_result_output = set_color( 'valid result', 'blue') + ': \n' + dict2str(valid_result) if verbose: self.logger.info(valid_score_output) names = [k for k, _ in valid_result.items()] values = [round(v, 3) for _, v in valid_result.items()] my_table = PrettyTable() my_table.field_names = names my_table.add_row(values) print(my_table) if update_flag: if saved: self._save_checkpoint(epoch_idx) update_output = set_color( 'Saving current best', 'blue') + ': %s' % self.saved_model_file #if verbose: # self.logger.info(update_output) self.best_valid_result = valid_result if callback_fn: callback_fn(epoch_idx, valid_score) if stop_flag: stop_output = 'Finished training, best eval result in epoch %d' % \ (epoch_idx - self.cur_step * self.eval_step) if verbose: self.logger.info(stop_output) break if self.draw_loss_pic: save_path = '{}-{}-train_loss.pdf'.format(self.config['model'], get_local_time()) self.plot_train_loss(save_path=os.path.join(save_path)) return self.best_valid_score, self.best_valid_result