INNER CODE UNIT · Python
load_and_cache_examples
thunlp/Few-NERD · run_supervised.py:262
def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode):
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Load data features from cache or dataset file
cached_features_file = os.path.join(args.data_dir, "cached_{}_{}_{}".format(mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length)))
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info("Loading features from cached file %s", cached_features_file)
features = torch.load(cached_features_file)
else:
logger.info("Creating features from dataset file at %s", args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(examples, labels, args.max_seq_length, tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,