Multimodal-Fatima/VQAv2_testdev
收藏资源简介:
--- dataset_info: features: - name: question_type dtype: string - name: multiple_choice_answer dtype: string - name: answers sequence: string - name: answers_original list: - name: answer dtype: string - name: answer_confidence dtype: string - name: answer_id dtype: int64 - name: id_image dtype: int64 - name: answer_type dtype: string - name: question_id dtype: int64 - name: question dtype: string - name: image dtype: image - name: id dtype: int64 - name: clip_tags_ViT_L_14 sequence: string - name: blip_caption dtype: string - name: LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14 sequence: string - name: DETA_detections_deta_swin_large_o365_coco_classes list: - name: attribute dtype: string - name: box sequence: float32 - name: label dtype: string - name: location dtype: string - name: ratio dtype: float32 - name: size dtype: string - name: tag dtype: string - name: DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random list: - name: attribute dtype: string - name: box sequence: float64 - name: captions_module sequence: string - name: captions_module_filter sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: Attributes_ViT_L_14_descriptors_text_davinci_003_full sequence: string - name: Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full sequence: string - name: clip_tags_ViT_L_14_with_openai sequence: string - name: clip_tags_LAION_ViT_H_14_2B_with_openai sequence: string - name: blip_caption_beam_5 dtype: string splits: - name: testdev num_bytes: 22099136791.0 num_examples: 107394 download_size: 11623275665 dataset_size: 22099136791.0 --- # Dataset Card for "VQAv2_testdev" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
--- 数据集信息: 特征字段: - 名称: question_type, 数据类型: 字符串 - 名称: multiple_choice_answer, 数据类型: 字符串 - 名称: answers, 数据类型: 字符串序列 - 名称: answers_original(原始答案), 数据类型: 列表结构,包含子字段: - answer(答案): 字符串 - answer_confidence(答案置信度): 字符串 - answer_id(答案ID): 整数 - 名称: id_image, 数据类型: 整数 - 名称: answer_type, 数据类型: 字符串 - 名称: question_id, 数据类型: 整数 - 名称: question, 数据类型: 字符串 - 名称: image, 数据类型: 图像 - 名称: id, 数据类型: 整数 - 名称: clip_tags_ViT_L_14, 数据类型: 字符串序列(CLIP(Contrastive Language-Image Pre-training)ViT-L/14标签) - 名称: blip_caption, 数据类型: 字符串(BLIP(Bootstrapping Language-Image Pre-training)字幕) - 名称: LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14, 数据类型: 字符串序列(基于GPT-3的大语言模型描述,适配视觉基因组(Visual Genome)数据集与ViT-L/14模型) - 名称: DETA_detections_deta_swin_large_o365_coco_classes, 数据类型: 列表结构,包含子字段: - attribute(属性): 字符串 - box(边界框): 浮点数序列 - label(标签): 字符串 - location(位置): 字符串 - ratio(比例): 浮点数 - size(尺寸): 字符串 - tag(标记): 字符串 - 名称: DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random, 数据类型: 列表结构,包含子字段: - attribute(属性): 字符串 - box(边界框): 浮点数序列 - captions_module(字幕模块结果): 字符串序列 - captions_module_filter(字幕模块过滤结果): 字符串序列 - label(标签): 字符串 - location(位置): 字符串 - ratio(比例): 浮点数 - size(尺寸): 字符串 - tag(标记): 字符串 - 名称: Attributes_ViT_L_14_descriptors_text_davinci_003_full, 数据类型: 字符串序列(基于ViT-L/14的属性描述符,使用text-davinci-003模型全量版本) - 名称: Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full, 数据类型: 字符串序列(基于LAION(Large-scale Artificial Intelligence Open Network)ViT-H/14 2B的属性描述符,使用text-davinci-003模型全量版本) - 名称: clip_tags_ViT_L_14_with_openai, 数据类型: 字符串序列(带OpenAI标注的CLIP ViT-L/14标签) - 名称: clip_tags_LAION_ViT_H_14_2B_with_openai, 数据类型: 字符串序列(带OpenAI标注的CLIP LAION ViT-H/14 2B标签) - 名称: blip_caption_beam_5, 数据类型: 字符串(波束搜索参数为5的BLIP字幕) 数据划分: - 名称: testdev(测试开发集) 字节大小: 22099136791.0 样本数量: 107394 下载大小: 11623275665 数据集大小: 22099136791.0 --- # 数据集卡片:VQAv2_testdev [需补充更多信息](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
数据集概述
数据集名称
VQAv2_testdev
数据集大小
- 下载大小: 11623275665字节
- 数据集大小: 22099136791字节
数据集分割
- 分割名称: testdev
- 示例数量: 107394
- 字节数: 22099136791.0字节
数据集特征
- question_type (字符串)
- multiple_choice_answer (字符串)
- answers (字符串序列)
- answers_original (列表)
- answer (字符串)
- answer_confidence (字符串)
- answer_id (整数64位)
- id_image (整数64位)
- answer_type (字符串)
- question_id (整数64位)
- question (字符串)
- image (图像)
- id (整数64位)
- clip_tags_ViT_L_14 (字符串序列)
- blip_caption (字符串)
- LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14 (字符串序列)
- DETA_detections_deta_swin_large_o365_coco_classes (列表)
- attribute (字符串)
- box (浮点数32位序列)
- label (字符串)
- location (字符串)
- ratio (浮点数)
- size (字符串)
- tag (字符串)
- DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random (列表)
- attribute (字符串)
- box (浮点数64位序列)
- captions_module (字符串序列)
- captions_module_filter (字符串序列)
- label (字符串)
- location (字符串)
- ratio (浮点数64位)
- size (字符串)
- tag (字符串)
- Attributes_ViT_L_14_descriptors_text_davinci_003_full (字符串序列)
- Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full (字符串序列)
- clip_tags_ViT_L_14_with_openai (字符串序列)
- clip_tags_LAION_ViT_H_14_2B_with_openai (字符串序列)
- blip_caption_beam_5 (字符串)




