KETI-NLP/vqa

# VQA ## What is VQA? VQA is a new dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. - 265,016 images (COCO and abstract scenes) - At least 3 questions (5.4 questions on average) per image - 10 ground truth answers per question - 3 plausible (but likely incorrect) answers per question - Automatic evaluation metric ## Dataset Details on downloading the latest dataset may be found on the download webpage. ## Usage ```python from datasets import load_dataset raw_datasets = load_dataset( "vqa.py", "base", cache_dir="huggingface_datasets", data_dir="data", ignore_verifications=True, ) dataset_train = raw_datasets["train"] for item in dataset_train: print(item) exit() ``` v2 = v2.real + v2.abstract (v2.abstract == v1.abstract) v1 = v1.real + v1.abstract v2.abstract.balanced.bin