Multimodal-Fatima/VQAv2_test_split_0
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: 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: 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 splits: - name: test num_bytes: 9462509481.0 num_examples: 44780 download_size: 1944305372 dataset_size: 9462509481.0 --- # Dataset Card for "VQAv2_test_split_0" [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: - 问题类型(question_type):字符串类型 - 多选题答案(multiple_choice_answer):字符串类型 - 答案(answers):字符串序列类型 - 原始答案(answers_original):列表类型,包含: - 答案(answer):字符串类型 - 答案置信度(answer_confidence):字符串类型 - 答案ID(answer_id):64位整数类型 - 图像ID(id_image):64位整数类型 - 答案类型(answer_type):字符串类型 - 问题ID(question_id):64位整数类型 - 问题(question):字符串类型 - 图像(image):图像类型 - 样本ID(id):64位整数类型 - ViT-L/14版CLIP(Contrastive Language-Image Pre-training)标签(clip_tags_ViT_L_14):字符串序列类型 - BLIP图像描述(blip_caption):字符串类型 - 基于ViT-L/14的视觉基因组下游任务GPT-3生成的大语言模型描述(LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14):字符串序列类型 - 适配O365与COCO类别的DETA_Swin Large检测结果(DETA_detections_deta_swin_large_o365_coco_classes):列表类型,包含: - 属性(attribute):字符串类型 - 边界框(box):32位浮点序列类型 - 标签(label):字符串类型 - 位置(location):字符串类型 - 比例(ratio):32位浮点类型 - 尺寸(size):字符串类型 - 标记(tag):字符串类型 - ViT-L/14版属性描述符(text-davinci-003完整版生成,Attributes_ViT_L_14_descriptors_text_davinci_003_full):字符串序列类型 - 不带OpenAI标签的ViT-L/14版CLIP标签(clip_tags_ViT_L_14_wo_openai):字符串序列类型 - 带OpenAI标签的ViT-L/14版CLIP标签(clip_tags_ViT_L_14_with_openai):字符串序列类型 - 不带OpenAI标签的LAION ViT-H/14 2B版CLIP标签(clip_tags_LAION_ViT_H_14_2B_wo_openai):字符串序列类型 - 带OpenAI标签的LAION ViT-H/14 2B版CLIP标签(clip_tags_LAION_ViT_H_14_2B_with_openai):字符串序列类型 - 不带OpenAI标签的LAION ViT-bigG/14 2B版CLIP标签(clip_tags_LAION_ViT_bigG_14_2B_wo_openai):字符串序列类型 - 带OpenAI标签的LAION ViT-bigG/14 2B版CLIP标签(clip_tags_LAION_ViT_bigG_14_2B_with_openai):字符串序列类型 - LAION ViT-H/14 2B版属性描述符(text-davinci-003完整版生成,Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full):字符串序列类型 - LAION ViT-bigG/14 2B版属性描述符(text-davinci-003完整版生成,Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full):字符串序列类型 - 带OpenAI标签的ViT-B/16版CLIP标签(clip_tags_ViT_B_16_with_openai):字符串序列类型 - 带随机字幕模块的适配O365与COCO类别的DETA_Swin Large检测结果(DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random):列表类型,包含: - 属性(attribute):字符串类型 - 边界框(box):64位浮点序列类型 - 字幕模块(captions_module):字符串序列类型 - 字幕模块过滤结果(captions_module_filter):字符串序列类型 - 标签(label):字符串类型 - 位置(location):字符串类型 - 比例(ratio):64位浮点类型 - 尺寸(size):字符串类型 - 标记(tag):字符串类型 数据划分: - 测试集(test):字节占用:9462509481.0,样本数量:44780 下载大小:1944305372 数据集总大小:9462509481.0 # 「VQAv2测试拆分0」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
数据集特征
- question_type
- 数据类型: string
- multiple_choice_answer
- 数据类型: string
- answers
- 数据类型: sequence of string
- answers_original
- 结构: list
- answer
- 数据类型: string
- answer_confidence
- 数据类型: string
- answer_id
- 数据类型: int64
- answer
- 结构: list
- id_image
- 数据类型: int64
- answer_type
- 数据类型: string
- question_id
- 数据类型: int64
- question
- 数据类型: string
- image
- 数据类型: image
- id
- 数据类型: int64
- clip_tags_ViT_L_14
- 数据类型: sequence of string
- blip_caption
- 数据类型: string
- LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14
- 数据类型: sequence of string
- DETA_detections_deta_swin_large_o365_coco_classes
- 结构: list
- attribute
- 数据类型: string
- box
- 数据类型: sequence of float32
- label
- 数据类型: string
- location
- 数据类型: string
- ratio
- 数据类型: float32
- size
- 数据类型: string
- tag
- 数据类型: string
- attribute
- 结构: list
- Attributes_ViT_L_14_descriptors_text_davinci_003_full
- 数据类型: sequence of string
- clip_tags_ViT_L_14_wo_openai
- 数据类型: sequence of string
- clip_tags_ViT_L_14_with_openai
- 数据类型: sequence of string
- clip_tags_LAION_ViT_H_14_2B_wo_openai
- 数据类型: sequence of string
- clip_tags_LAION_ViT_H_14_2B_with_openai
- 数据类型: sequence of string
- clip_tags_LAION_ViT_bigG_14_2B_wo_openai
- 数据类型: sequence of string
- clip_tags_LAION_ViT_bigG_14_2B_with_openai
- 数据类型: sequence of string
- Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full
- 数据类型: sequence of string
- Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full
- 数据类型: sequence of string
- clip_tags_ViT_B_16_with_openai
- 数据类型: sequence of string
- DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random
- 结构: list
- attribute
- 数据类型: string
- box
- 数据类型: sequence of float64
- captions_module
- 数据类型: sequence of string
- captions_module_filter
- 数据类型: sequence of string
- label
- 数据类型: string
- location
- 数据类型: string
- ratio
- 数据类型: float64
- size
- 数据类型: string
- tag
- 数据类型: string
- attribute
- 结构: list
数据集分割
- test
- 字节数: 9462509481.0
- 示例数: 44780
数据集大小
- 下载大小: 1944305372
- 数据集大小: 9462509481.0



