Multimodal-Fatima/VQAv2_test_split_4
收藏Hugging Face2023-05-12 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/Multimodal-Fatima/VQAv2_test_split_4
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: 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: 9135639447.0
num_examples: 44779
download_size: 1867482751
dataset_size: 9135639447.0
---
# Dataset Card for "VQAv2_test_split_4"
[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):数据类型为字符串
- 选择题答案(multiple_choice_answer):数据类型为字符串
- 答案(answers):序列字符串类型
- 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
- 条目ID(id):64位整数类型
- CLIP标签(ViT-L/14)(clip_tags_ViT_L_14):序列字符串类型
- BLIP图像字幕(blip_caption):字符串类型
- 基于GPT-3的大语言模型(LLM)描述(针对视觉基因组(Visual Genome)数据集与ViT-L/14模型的下游任务)(LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14):序列字符串类型
- DETA目标检测结果(基于deta_swin_large_o365_coco_classes模型)(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位浮点数类型
- 尺寸(size):字符串类型
- 标记(tag):字符串类型
- 基于ViT-L/14与text-davinci-003的图像属性描述符(Attributes_ViT_L_14_descriptors_text_davinci_003_full):序列字符串类型
- 无OpenAI标签的CLIP标签(ViT-L/14)(clip_tags_ViT_L_14_wo_openai):序列字符串类型
- 含OpenAI标签的CLIP标签(ViT-L/14)(clip_tags_ViT_L_14_with_openai):序列字符串类型
- 无OpenAI标签的CLIP标签(LAION ViT-H/14 2B)(clip_tags_LAION_ViT_H_14_2B_wo_openai):序列字符串类型
- 含OpenAI标签的CLIP标签(LAION ViT-H/14 2B)(clip_tags_LAION_ViT_H_14_2B_with_openai):序列字符串类型
- 无OpenAI标签的CLIP标签(LAION ViT-bigG/14 2B)(clip_tags_LAION_ViT_bigG_14_2B_wo_openai):序列字符串类型
- 含OpenAI标签的CLIP标签(LAION ViT-bigG/14 2B)(clip_tags_LAION_ViT_bigG_14_2B_with_openai):序列字符串类型
- 基于LAION ViT-H/14 2B与text-davinci-003的图像属性描述符(Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full):序列字符串类型
- 基于LAION ViT-bigG/14 2B与text-davinci-003的图像属性描述符(Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full):序列字符串类型
- 含OpenAI标签的CLIP标签(ViT-B/16)(clip_tags_ViT_B_16_with_openai):序列字符串类型
- 带随机字幕模块的DETA目标检测结果(基于deta_swin_large_o365_coco_classes模型)(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
- 字幕模块结果(captions_module):序列字符串类型
- 字幕模块过滤结果(captions_module_filter):序列字符串类型
- 标签(label):字符串类型
- 位置(location):字符串类型
- 比例(ratio):64位浮点数类型
- 尺寸(size):字符串类型
- 标记(tag):字符串类型
数据集划分:
- 测试集(test):字节数9135639447.0,样本数量44779
下载大小:1867482751字节
数据集总大小:9135639447.0字节
---
# 数据集卡片:"VQAv2_test_split_4"
[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_split_4
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
- Attributes_ViT_L_14_descriptors_text_davinci_003_full: 字符串序列
- 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
- clip_tags_ViT_B_16_with_openai: 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
数据集分割
- test:
- 字节数: 9135639447.0
- 示例数: 44779
数据集大小
- 下载大小: 1867482751
- 数据集大小: 9135639447.0



