five

Multimodal-Fatima/VQAv2_test_no_image

收藏
Hugging Face2023-05-13 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/Multimodal-Fatima/VQAv2_test_no_image
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: question_type dtype: string - name: multiple_choice_answer dtype: 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: 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: Attributes_ViT_L_14_descriptors_text_davinci_003_full sequence: string - name: clip_tags_ViT_L_14_wo_openai sequence: string - name: clip_tags_ViT_L_14_with_openai sequence: string - name: clip_tags_LAION_ViT_H_14_2B_wo_openai sequence: string - name: clip_tags_LAION_ViT_H_14_2B_with_openai sequence: string - name: clip_tags_LAION_ViT_bigG_14_2B_wo_openai sequence: string - name: clip_tags_LAION_ViT_bigG_14_2B_with_openai sequence: string - name: Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full sequence: string - name: Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full sequence: 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: answers sequence: string splits: - name: test num_bytes: 21976237587 num_examples: 447793 download_size: 5670512625 dataset_size: 21976237587 --- # Dataset Card for "VQAv2_test_no_image" [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: - 字段名:question_type,数据类型:字符串 - 字段名:multiple_choice_answer,数据类型:字符串 - 字段名:answers_original,类型为列表,包含子字段: - 字段名:answer,数据类型:字符串 - 字段名:answer_confidence,数据类型:字符串 - 字段名:answer_id,数据类型:64位整数 - 字段名:id_image,数据类型:64位整数 - 字段名:answer_type,数据类型:字符串 - 字段名:question_id,数据类型:64位整数 - 字段名:question,数据类型:字符串 - 字段名:id,数据类型:64位整数 - 字段名:clip_tags_ViT_L_14,类型为字符串序列,指ViT-L/14模型的CLIP(CLIP)标签 - 字段名:blip_caption(BLIP),数据类型:字符串 - 字段名:LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14,类型为字符串序列,指基于ViT-L/14模型、面向视觉基因组下游任务的GPT-3(GPT-3)大语言模型生成的描述文本 - 字段名:DETA_detections_deta_swin_large_o365_coco_classes,类型为列表,指基于DETA-Swin-Large(Swin)模型、针对O365(O365)与COCO(COCO)类别的目标检测结果,包含子字段: - 字段名:attribute,数据类型:字符串 - 字段名:box,类型为单精度浮点数序列 - 字段名:label,数据类型:字符串 - 字段名:location,数据类型:字符串 - 字段名:ratio,数据类型:单精度浮点数 - 字段名:size,数据类型:字符串 - 字段名:tag,数据类型:字符串 - 字段名:Attributes_ViT_L_14_descriptors_text_davinci_003_full,类型为字符串序列,指基于ViT-L/14模型、通过text-davinci-003生成的完整属性描述词 - 字段名:clip_tags_ViT_L_14_wo_openai,类型为字符串序列,指未使用OpenAI预设的ViT-L/14模型CLIP标签 - 字段名:clip_tags_ViT_L_14_with_openai,类型为字符串序列,指使用OpenAI预设的ViT-L/14模型CLIP标签 - 字段名:clip_tags_LAION_ViT_H_14_2B_wo_openai,类型为字符串序列,指未使用OpenAI预设的LAION-ViT-H-14-2B模型CLIP标签 - 字段名:clip_tags_LAION_ViT_H_14_2B_with_openai,类型为字符串序列,指使用OpenAI预设的LAION-ViT-H-14-2B模型CLIP标签 - 字段名:clip_tags_LAION_ViT_bigG_14_2B_wo_openai,类型为字符串序列,指未使用OpenAI预设的LAION-ViT-bigG-14-2B模型CLIP标签 - 字段名:clip_tags_LAION_ViT_bigG_14_2B_with_openai,类型为字符串序列,指使用OpenAI预设的LAION-ViT-bigG-14-2B模型CLIP标签 - 字段名:Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full,类型为字符串序列,指基于LAION-ViT-H-14-2B模型、通过text-davinci-003生成的完整属性描述词 - 字段名:Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full,类型为字符串序列,指基于LAION-ViT-bigG-14-2B模型、通过text-davinci-003生成的完整属性描述词 - 字段名:DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random,类型为列表,指基于DETA-Swin-Large模型、针对O365与COCO类别的随机caption模块目标检测结果,包含子字段: - 字段名:attribute,数据类型:字符串 - 字段名:box,类型为双精度浮点数序列 - 字段名:captions_module,类型为字符串序列 - 字段名:captions_module_filter,类型为字符串序列 - 字段名:label,数据类型:字符串 - 字段名:location,数据类型:字符串 - 字段名:ratio,数据类型:双精度浮点数 - 字段名:size,数据类型:字符串 - 字段名:tag,数据类型:字符串 - 字段名:answers,类型为字符串序列 数据集划分: - 划分名称:test(测试集),字节占用大小:21976237587,样本数量:447793 下载大小:5670512625 数据集总大小:21976237587 # “无图像版VQAv2测试集”数据集卡片 【需补充更多信息】https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards
提供机构:
Multimodal-Fatima
原始信息汇总

数据集概述

数据集名称

  • VQAv2_test_no_image

数据集特征

基本特征

  • question_type (字符串)
  • multiple_choice_answer (字符串)
  • id_image (整数64位)
  • answer_type (字符串)
  • question_id (整数64位)
  • question (字符串)
  • id (整数64位)

答案相关特征

  • answers_original (列表)
    • answer (字符串)
    • answer_confidence (字符串)
    • answer_id (整数64位)

图像和描述相关特征

  • 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)

检测和属性相关特征

  • 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32位)
    • size (字符串)
    • tag (字符串)
  • Attributes_ViT_L_14_descriptors_text_davinci_003_full (字符串序列)

其他相关特征

  • clip_tags_ViT_L_14_wo_openai (字符串序列)

  • clip_tags_ViT_L_14_with_openai (字符串序列)

  • clip_tags_LAION_ViT_H_14_2B_wo_openai (字符串序列)

  • clip_tags_LAION_ViT_H_14_2B_with_openai (字符串序列)

  • clip_tags_LAION_ViT_bigG_14_2B_wo_openai (字符串序列)

  • clip_tags_LAION_ViT_bigG_14_2B_with_openai (字符串序列)

  • Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full (字符串序列)

  • Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full (字符串序列)

  • 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)
  • answers (字符串序列)

数据集分割

  • test
    • 数据量: 21976237587 字节
    • 示例数量: 447793

数据集大小

  • 下载大小: 5670512625 字节
  • 数据集大小: 21976237587 字节
二维码
社区交流群
二维码
科研交流群
商业服务