def predict(args):
logger = logging.getLogger("QANet")
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.'
dataloader = DataLoader(args.max_p_num,
args.max_p_len,
args.max_q_len,
args.save_dir,
test_files=args.test_files)
num_train_steps = int(
len(dataloader.train_set) / args.batch_size * args.epochs)
num_warmup_steps = int(num_train_steps * args.warmup_proportion)
logger.info('Converting text into ids...')
dataloader.convert_to_ids(vocab)
logger.info('Restoring the model...')
model = Model(vocab, num_train_steps, num_warmup_steps, args)
model.restore(args.model_dir, 'qanet_64000')
logger.info('Predicting answers for test set...')
test_batches = dataloader.next_batch('test',
48,
vocab.get_word_id(vocab.pad_token),
shuffle=False)
model.evaluate(test_batches,
result_dir=args.result_dir,
result_prefix='test.predicted')
def evaluate(args):
logger = logging.getLogger("QANet")
logger.info("====== evaluating ======")
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.'
dataloader = DataLoader(args.max_p_num,
args.max_p_len,
args.max_q_len,
args.save_dir,
dev_files=args.dev_files)
num_train_steps = int(
len(dataloader.train_set) / args.batch_size * args.epochs)
num_warmup_steps = int(num_train_steps * args.warmup_proportion)
logger.info('Converting text into ids...')
dataloader.convert_to_ids(vocab)
logger.info('Restoring the model...')
model = Model(vocab, num_train_steps, num_warmup_steps, args)
model.restore(args.model_dir, "averaged.ckpt-0")
logger.info('Evaluating the model on dev set...')
dev_batches = dataloader.next_batch('dev',
16,
vocab.get_word_id(vocab.pad_token),
shuffle=False)
dev_loss, dev_bleu_rouge = 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)))