def __init__(self, model_file, word_embeddings_cache_file, stopwords_file,
word2dfs_file):
# init torch random seeds
torch.manual_seed(1234)
np.random.seed(1234)
# load model
self.model = QAModel.load('', model_file)
# load vectors
self.vec_dim = self._preload_cached_embeddings(
word_embeddings_cache_file)
self.unk_term_vec = np.random.uniform(-0.25, 0.25, self.vec_dim)
# stopwords
self.stoplist = set([line.strip() for line in open(stopwords_file)])
# word dfs
if os.path.isfile(word2dfs_file):
with open(word2dfs_file, "rb") as w2dfin:
self.word2dfs = pickle.load(w2dfin)
logger.info('Achieved better dev_map ... saved model')
if args.test_on_each_epoch:
test_scores = trainer.test(test_set, args.batch_size)
map, mrr = compute_map_mrr(args.dataset_folder, test_set,
test_scores)
logger.info("------- MAP {}, MRR {}".format(map, mrr))
if (i - best_model) >= args.patience:
logger.warning('No improvement since the last {} epochs. Stopping training'\
.format(i - best_model))
break
logger.info(' ------------ Training epochs completed! ------------')
logger.info('Best dev MAP in training phase = {:.4f}'.format(best_map))
trained_model = QAModel.load(args.model_outfile)
evaluator = Trainer(trained_model, args.eta, args.mom, args.no_loss_reg,
vec_dim, args.cuda)
for split in [test_set, dev_set]:
evaluator.load_input_data(args.dataset_folder, cache_file, None, None,
split)
if args.paper_ext_feats or args.paper_ext_feats_stem:
evaluator.data_splits[split][-1] = ext_feats_for_splits[split]
#set_external_features_as_per_paper(evaluator)
split_scores = evaluator.test(split, args.batch_size)
map, mrr = compute_map_mrr(args.dataset_folder, split, split_scores,
args.run_name_prefix)
logger.info("-------{} MAP {}, MRR {}".format(split, map, mrr))
dev_map, dev_mrr = compute_map_mrr(args.dataset_folder, dev_set, dev_scores)
logger.info("------- MAP {}, MRR {}".format(dev_map, dev_mrr))
if dev_map - best_map > 1e-3: # new map is better than best map
best_model = i
best_map = dev_map
QAModel.save(net, args.dataset_folder, args.model_fname)
logger.info('Achieved better dev_map ... saved model')
if args.test_on_each_epoch:
test_scores = trainer.test(test_set, args.batch_size)
map, mrr = compute_map_mrr(args.dataset_folder, test_set, test_scores)
logger.info("------- MAP {}, MRR {}".format(map, mrr))
if (i - best_model) >= args.patience:
logger.warning('No improvement since the last {} epochs. Stopping training'.format(i - best_model))
break
logger.info(' ------------ Training epochs completed! ------------')
logger.info('Best MAP in training phase = {:.4f}'.format(best_map))
trained_model = QAModel.load(args.dataset_folder, args.model_fname)
evaluator = Trainer(trained_model, args.eta, args.mom, args.no_loss_reg, vec_dim)
evaluator.load_input_data(args.dataset_folder, cache_file, None, None, test_set)
test_scores = evaluator.test(test_set, args.batch_size)
map, mrr = compute_map_mrr(args.dataset_folder, test_set, test_scores)
logger.info("------- MAP {}, MRR {}".format(map, mrr))
