def evaluate(args): """ evaluate the trained model on dev files """ logger = logging.getLogger("brc") logger.info('Load data_set and vocab...') with open(os.path.join(args.vocab_dir, 'vocab.data'), 'rb') as fin: vocab = pickle.load(fin) assert len(args.dev_files) > 0, 'No dev files are provided.' brc_data = BRCDataset(args.max_p_num, args.max_p_len, args.max_q_len, args.max_word_len, dev_files=args.dev_files) logger.info('Converting text into ids...') brc_data.convert_to_ids(vocab) logger.info('Restoring the model...') rc_model = RCModel(vocab, args) rc_model.restore(model_dir=args.model_dir, model_prefix=args.algo) rc_model.finalize() logger.info('Evaluating the model on dev set...') dev_batches = brc_data.gen_mini_batches('dev', args.batch_size, pad_id=vocab.get_id( vocab.pad_token), shuffle=False) dev_loss, dev_bleu_rouge = rc_model.evaluate(dev_batches, result_dir=args.result_dir, result_prefix='dev.predicted') logger.info('Loss on dev set: {}'.format(dev_loss)) logger.info('Result on dev set: {}'.format(dev_bleu_rouge)) logger.info('Predicted answers are saved to {}'.format( os.path.join(args.result_dir)))
def train(args): """ trains the reading comprehension model """ logger = logging.getLogger("brc") logger.info('Load data_set and vocab...') with open(os.path.join(args.vocab_dir, 'vocab.data'), 'rb') as fin: vocab = pickle.load(fin) print("vocab.size() = ", vocab.size()) brc_data = BRCDataset(args.max_p_num, args.max_p_len, args.max_q_len, args.max_word_len, args.train_files, args.dev_files) logger.info('Converting text into ids...') brc_data.convert_to_ids(vocab, args.use_char_level == 'true') logger.info('Initialize the model...') rc_model = RCModel(vocab, args) if args.retrain == 'true': rc_model.restore(model_dir=args.model_restore_dir, model_prefix=args.algo_restore) rc_model.finalize() logger.info('Training the model...') rc_model.train(brc_data, args.epochs, args.batch_size, save_dir=args.model_dir, save_prefix=args.algo, dropout_keep_prob=args.dropout_keep_prob) logger.info('Done with model training!')
def predict(args): """ predicts answers for test files """ logger = logging.getLogger("brc") logger.info('Load data_set and vocab...') with open(os.path.join(args.vocab_dir, 'vocab.data'), 'rb') as fin: vocab = pickle.load(fin) assert len(args.test_files) > 0, 'No test files are provided.' brc_data = BRCDataset(args.max_p_num, args.max_p_len, args.max_q_len, args.max_word_len, test_files=args.test_files) logger.info('Converting text into ids...') brc_data.convert_to_ids(vocab) logger.info('Restoring the model...') rc_model = RCModel(vocab, args) rc_model.restore(model_dir=args.model_dir, model_prefix=args.algo) rc_model.finalize() # 增加完所有操作后采用sess.graph.finalize() # 来使得整个graph变为只读的 # 注意:tf.train.Saver() # 也算是往graph中添加node, 所以也必须放在finilize前 # 但是,,tf.train.Saver() # 只会存储 # 在该Saver声明时已经存在的变量!!! logger.info('Predicting answers for test set...') test_batches = brc_data.gen_mini_batches('test', args.batch_size, pad_id=vocab.get_id( vocab.pad_token), shuffle=False) rc_model.evaluate(test_batches, result_dir=args.result_dir, result_prefix='test.predicted')