five

Multimodal-Fatima/VQAv2_minival_validation

收藏
Hugging Face2023-06-09 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/Multimodal-Fatima/VQAv2_minival_validation
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 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: 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_clip_ViT_L_14 list: - name: attribute dtype: string - name: box sequence: float64 - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: id dtype: int64 - name: DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption_caption_module list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - name: captions_module sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption_caption_module_without_filtering list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - name: captions_module sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption_caption_module_random list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - 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: clip_tags_LAION_ViT_H_14_2B sequence: string - name: LLM_Description_gpt3_downstream_tasks_visual_genome_LAION-ViT-H-14-2B sequence: 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: clip_tags_ViT_B_16_with_openai sequence: string - name: blip_caption_beam_5_Salesforce_blip2_flan_t5_xxl dtype: string - name: DETA_detections_deta_swin_large_o365_coco_classes_caption_all_patches_Salesforce_blip_image_captioning_large_ list: - name: attribute dtype: string - name: box sequence: float64 - name: captions_all_patches sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: DETA_detections_deta_swin_large_o365_coco_classes_caption_all_patches_Salesforce_blip_image_captioning_large_clean list: - name: attribute dtype: string - name: box sequence: float64 - name: captions_all_patches sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: blip_caption_Salesforce_blip_image_captioning_large_intensive sequence: string - name: blip_caption_Salesforce_blip_image_captioning_base_intensive sequence: string splits: - name: validation num_bytes: 10757838822.0 num_examples: 25994 download_size: 2788131849 dataset_size: 10757838822.0 --- # Dataset Card for "VQAv2_minival_validation_v2" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

dataset_info: features: - name: 问题类型 dtype: 字符串 - name: 多项选择答案 dtype: 字符串 - name: 答案集合 dtype: 字符串序列 - name: 原始答案 list: - name: 答案内容 dtype: 字符串 - name: 答案置信度 dtype: 字符串 - name: 答案ID dtype: 64位整数 - name: 图像ID dtype: 64位整数 - name: 答案类型 dtype: 字符串 - name: 问题ID dtype: 64位整数 - name: 问题文本 dtype: 字符串 - name: 图像 dtype: 图像类型 - name: 基于视觉Transformer（ViT）-L/14的CLIP标签 dtype: 字符串序列 - name: BLIP字幕模型（BLIP）字幕 dtype: 字符串 - name: 基于ViT-L/14的GPT-3下游任务视觉基因组（Visual Genome）大语言模型描述 dtype: 字符串序列 - name: 基于deta_swin_large、O365及COCO类别的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float32序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float32 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 基于deta_swin_large、O365及CLIP ViT-L/14的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 基于deta_swin_large、O365、CLIP ViT-L/14且结合BLIP字幕的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 字幕内容 dtype: 字符串 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 样本ID dtype: 64位整数 - name: 基于deta_swin_large、O365、CLIP ViT-L/14、BLIP字幕且使用字幕模块的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 字幕内容 dtype: 字符串 - name: 字幕模块输出 dtype: 字符串序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 基于deta_swin_large、O365、CLIP ViT-L/14、BLIP字幕且使用未过滤字幕模块的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 字幕内容 dtype: 字符串 - name: 字幕模块输出 dtype: 字符串序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 基于deta_swin_large、O365、CLIP ViT-L/14、BLIP字幕且使用随机过滤字幕模块的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 字幕内容 dtype: 字符串 - name: 字幕模块输出 dtype: 字符串序列 - name: 字幕模块过滤规则 dtype: 字符串序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 基于LAION ViT-H/14 2B的CLIP标签 dtype: 字符串序列 - name: 基于LAION ViT-H/14 2B的GPT-3下游任务视觉基因组（Visual Genome）大语言模型描述 dtype: 字符串序列 - name: 基于ViT-L/14的text-davinci-003完整版属性描述符 dtype: 字符串序列 - name: 无OpenAI标签的ViT-L/14 CLIP标签 dtype: 字符串序列 - name: 带OpenAI标签的ViT-L/14 CLIP标签 dtype: 字符串序列 - name: 无OpenAI标签的LAION ViT-H/14 2B CLIP标签 dtype: 字符串序列 - name: 带OpenAI标签的LAION ViT-H/14 2B CLIP标签 dtype: 字符串序列 - name: 无OpenAI标签的LAION ViT-bigG/14 2B CLIP标签 dtype: 字符串序列 - name: 带OpenAI标签的LAION ViT-bigG/14 2B CLIP标签 dtype: 字符串序列 - name: 基于LAION ViT-H/14 2B的text-davinci-003完整版属性描述符 dtype: 字符串序列 - name: 基于LAION ViT-bigG/14 2B的text-davinci-003完整版属性描述符 dtype: 字符串序列 - name: 带OpenAI标签的ViT-B/16 CLIP标签 dtype: 字符串序列 - name: Salesforce BLIP2 FLAN-T5-XXL模型束宽5的BLIP字幕 dtype: 字符串 - name: 基于deta_swin_large、O365、COCO类别且结合Salesforce BLIP图像字幕大模型全补丁字幕的DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 全补丁字幕内容 dtype: 字符串序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: 基于deta_swin_large、O365、COCO类别且结合Salesforce BLIP图像字幕大模型全补丁字幕的清洗版DETA目标检测器（DETA）检测结果 list: - name: 属性 dtype: 字符串 - name: 边界框 dtype: float64序列 - name: 全补丁字幕内容 dtype: 字符串序列 - name: 类别标签 dtype: 字符串 - name: 位置信息 dtype: 字符串 - name: 宽高比 dtype: float64 - name: 尺寸信息 dtype: 字符串 - name: 检测标记 dtype: 字符串 - name: Salesforce BLIP图像字幕大模型密集型字幕 dtype: 字符串序列 - name: Salesforce BLIP图像字幕基础模型密集型字幕 dtype: 字符串序列 splits: - name: 验证集 num_bytes: 10757838822.0 num_examples: 25994 download_size: 2788131849 dataset_size: 10757838822.0 --- # 数据集卡片："VQAv2_minival_validation_v2" [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_minival_validation_v2"

数据集特征

数据集包含以下特征：

  • question_type (string)
  • multiple_choice_answer (string)
  • answers (sequence: string)
  • answers_original (list)
    • answer (string)
    • answer_confidence (string)
    • answer_id (int64)
  • id_image (int64)
  • answer_type (string)
  • question_id (int64)
  • question (string)
  • image (image)
  • clip_tags_ViT_L_14 (sequence: string)
  • blip_caption (string)
  • LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14 (sequence: string)
  • DETA_detections_deta_swin_large_o365_coco_classes (list)
    • attribute (string)
    • box (sequence: float32)
    • label (string)
    • location (string)
    • ratio (float32)
    • size (string)
    • tag (string)
  • DETA_detections_deta_swin_large_o365_clip_ViT_L_14 (list)
    • attribute (string)
    • box (sequence: float64)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption (list)
    • attribute (string)
    • box (sequence: float64)
    • caption (string)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • id (int64)
  • DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption_caption_module (list)
    • attribute (string)
    • box (sequence: float64)
    • caption (string)
    • captions_module (sequence: string)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption_caption_module_without_filtering (list)
    • attribute (string)
    • box (sequence: float64)
    • caption (string)
    • captions_module (sequence: string)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption_caption_module_random (list)
    • attribute (string)
    • box (sequence: float64)
    • caption (string)
    • captions_module_filter (sequence: string)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • clip_tags_LAION_ViT_H_14_2B (sequence: string)
  • LLM_Description_gpt3_downstream_tasks_visual_genome_LAION-ViT-H-14-2B (sequence: string)
  • Attributes_ViT_L_14_descriptors_text_davinci_003_full (sequence: string)
  • clip_tags_ViT_L_14_wo_openai (sequence: string)
  • clip_tags_ViT_L_14_with_openai (sequence: string)
  • clip_tags_LAION_ViT_H_14_2B_wo_openai (sequence: string)
  • clip_tags_LAION_ViT_H_14_2B_with_openai (sequence: string)
  • clip_tags_LAION_ViT_bigG_14_2B_wo_openai (sequence: string)
  • clip_tags_LAION_ViT_bigG_14_2B_with_openai (sequence: string)
  • Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full (sequence: string)
  • Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full (sequence: string)
  • clip_tags_ViT_B_16_with_openai (sequence: string)
  • blip_caption_beam_5_Salesforce_blip2_flan_t5_xxl (string)
  • DETA_detections_deta_swin_large_o365_coco_classes_caption_all_patches_Salesforce_blip_image_captioning_large_ (list)
    • attribute (string)
    • box (sequence: float64)
    • captions_all_patches (sequence: string)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • DETA_detections_deta_swin_large_o365_coco_classes_caption_all_patches_Salesforce_blip_image_captioning_large_clean (list)
    • attribute (string)
    • box (sequence: float64)
    • captions_all_patches (sequence: string)
    • label (string)
    • location (string)
    • ratio (float64)
    • size (string)
    • tag (string)
  • blip_caption_Salesforce_blip_image_captioning_large_intensive (sequence: string)
  • blip_caption_Salesforce_blip_image_captioning_base_intensive (sequence: string)

数据集拆分

  • validation
    • num_bytes: 10757838822.0
    • num_examples: 25994

数据集大小

  • download_size: 2788131849
  • dataset_size: 10757838822.0
搜集汇总
背景与挑战
背景概述
该数据集是VQAv2的minival验证集，专注于视觉问答任务，包含25,994个示例，每个示例有图像、问题、答案等核心字段。其特点在于集成了多种预训练模型生成的扩展特征，如CLIP标签、BLIP描述和DETA检测结果，以增强图像的多模态表示，适用于多模态AI模型训练和评估。
以上内容由遇见数据集搜集并总结生成
关于我们
遇见数据集——让每个数据集都被发现，让每一次遇见都有价值。
数发科官网www.sfktec.com
联系我们
youjian
selectdataset@iotsh.com.cn
商业合作
数据驱动未来，携手共赢发展
二维码
社区交流群
二维码
科研交流群
商业服务