dicee.static_funcs_training

Functions

evaluate_lp(model, triple_idx, num_entities, er_vocab, ...)	Evaluate model in a standard link prediction task
evaluate_bpe_lp(model, triple_idx, ...[, info])
efficient_zero_grad(model)

Module Contents

dicee.static_funcs_training.evaluate_lp(model, triple_idx, num_entities, er_vocab: Dict[Tuple, List], re_vocab: Dict[Tuple, List], info='Eval Starts')

Evaluate model in a standard link prediction task

for each triple the rank is computed by taking the mean of the filtered missing head entity rank and the filtered missing tail entity rank :param model: :param triple_idx: :param info: :return:

dicee.static_funcs_training.evaluate_bpe_lp(model, triple_idx: List[Tuple], all_bpe_shaped_entities, er_vocab: Dict[Tuple, List], re_vocab: Dict[Tuple, List], info='Eval Starts')

dicee.static_funcs_training.efficient_zero_grad(model)