Multimodal-Fatima/VQAv2_sample_validation_with_img2prompt
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: 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: LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14 sequence: string - name: DETA_detections_deta_swin_large_o365_coco_classes_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 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: detections_img2prompt dtype: string - name: new_info_captions list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - name: captions_module sequence: sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: new_info_captions2 list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - name: captions_module sequence: sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string - name: new_info_captions3 list: - name: attribute dtype: string - name: box sequence: float64 - name: caption dtype: string - name: captions_module sequence: sequence: string - name: label dtype: string - name: location dtype: string - name: ratio dtype: float64 - name: size dtype: string - name: tag dtype: string splits: - name: validation num_bytes: 17864005.0 num_examples: 100 download_size: 15925587 dataset_size: 17864005.0 --- # Dataset Card for "VQAv2_sample_validation_with_img2prompt" [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(问题类型),数据类型:字符串 - 字段名:multiple_choice_answer(单项选择答案),数据类型:字符串 - 字段名:answers(答案集合),数据类型:字符串序列 - 字段名:answers_original(原始答案列表),为包含以下字段的列表: - 字段名:answer(答案),数据类型:字符串 - 字段名:answer_confidence(答案置信度),数据类型:字符串 - 字段名:answer_id(答案编号),数据类型:int64 - 字段名:id_image(图像ID),数据类型:int64 - 字段名:answer_type(答案类型),数据类型:字符串 - 字段名:question_id(问题ID),数据类型:int64 - 字段名:question(问题文本),数据类型:字符串 - 字段名:image(图像数据),数据类型:图像 - 字段名:id(样本ID),数据类型:int64 - 字段名:clip_tags_ViT_L_14(基于ViT-L/14的CLIP标签序列),数据类型:字符串序列 - 字段名:blip_caption(BLIP生成的图像字幕),数据类型:字符串 - 字段名:DETA_detections_deta_swin_large_o365_coco_classes(基于DETA、Swin Large、O365与COCO类别的检测结果列表),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float32序列 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float32 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 - 字段名:LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14(基于ViT-L/14、视觉基因组的GPT-3下游任务大语言模型(Large Language Model,LLM)描述序列),数据类型:字符串序列 - 字段名:DETA_detections_deta_swin_large_o365_coco_classes_ViT_L_14(基于ViT-L/14、DETA、Swin Large、O365与COCO类别的检测结果列表),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float64序列 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float64 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 - 字段名:DETA_detections_deta_swin_large_o365_clip_ViT_L_14(基于ViT-L/14、CLIP、DETA、Swin Large与O365的检测结果列表),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float64序列 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float64 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 - 字段名:DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption(结合ViT-L/14、CLIP、DETA、Swin Large、O365与BLIP字幕的检测结果列表),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float64序列 - 字段名:caption(字幕),数据类型:字符串 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float64 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 - 字段名:detections_img2prompt(img2prompt检测结果),数据类型:字符串 - 字段名:new_info_captions(新信息字幕列表),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float64序列 - 字段名:caption(字幕),数据类型:字符串 - 字段名:captions_module(字幕模块),数据类型:字符串序列的序列 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float64 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 - 字段名:new_info_captions2(新信息字幕列表2),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float64序列 - 字段名:caption(字幕),数据类型:字符串 - 字段名:captions_module(字幕模块),数据类型:字符串序列的序列 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float64 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 - 字段名:new_info_captions3(新信息字幕列表3),为包含以下字段的列表: - 字段名:attribute(属性),数据类型:字符串 - 字段名:box(边界框),数据类型:float64序列 - 字段名:caption(字幕),数据类型:字符串 - 字段名:captions_module(字幕模块),数据类型:字符串序列的序列 - 字段名:label(类别标签),数据类型:字符串 - 字段名:location(位置),数据类型:字符串 - 字段名:ratio(宽高比),数据类型:float64 - 字段名:size(尺寸),数据类型:字符串 - 字段名:tag(标签),数据类型:字符串 拆分集: - 拆分名称:validation(验证集),字节大小:17864005.0,样本数量:100 下载大小:15925587字节 数据集总大小:17864005.0字节 # 「VQAv2_sample_validation_with_img2prompt」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)
数据集概述
数据集名称
- VQAv2_sample_validation_with_img2prompt
数据集特征
-
基本特征
question_type: 字符串类型multiple_choice_answer: 字符串类型answers: 字符串序列answers_original: 列表类型,包含:answer: 字符串类型answer_confidence: 字符串类型answer_id: 整数类型(64位)
id_image: 整数类型(64位)answer_type: 字符串类型question_id: 整数类型(64位)question: 字符串类型image: 图像类型id: 整数类型(64位)clip_tags_ViT_L_14: 字符串序列blip_caption: 字符串类型
-
检测特征
DETA_detections_deta_swin_large_o365_coco_classes: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(32位)label: 字符串类型location: 字符串类型ratio: 浮点数类型(32位)size: 字符串类型tag: 字符串类型
DETA_detections_deta_swin_large_o365_coco_classes_ViT_L_14: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(64位)label: 字符串类型location: 字符串类型ratio: 浮点数类型(64位)size: 字符串类型tag: 字符串类型
DETA_detections_deta_swin_large_o365_clip_ViT_L_14: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(64位)label: 字符串类型location: 字符串类型ratio: 浮点数类型(64位)size: 字符串类型tag: 字符串类型
DETA_detections_deta_swin_large_o365_clip_ViT_L_14_blip_caption: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(64位)caption: 字符串类型label: 字符串类型location: 字符串类型ratio: 浮点数类型(64位)size: 字符串类型tag: 字符串类型
-
其他特征
detections_img2prompt: 字符串类型new_info_captions: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(64位)caption: 字符串类型captions_module: 字符串序列label: 字符串类型location: 字符串类型ratio: 浮点数类型(64位)size: 字符串类型tag: 字符串类型
new_info_captions2: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(64位)caption: 字符串类型captions_module: 字符串序列label: 字符串类型location: 字符串类型ratio: 浮点数类型(64位)size: 字符串类型tag: 字符串类型
new_info_captions3: 列表类型,包含:attribute: 字符串类型box: 浮点数序列(64位)caption: 字符串类型captions_module: 字符串序列label: 字符串类型location: 字符串类型ratio: 浮点数类型(64位)size: 字符串类型tag: 字符串类型
数据集分割
- 验证集
- 示例数量: 100
- 数据大小: 17864005.0字节
数据集大小
- 下载大小: 15925587字节
- 数据集大小: 17864005.0字节



