Multimodal-Fatima/VQAv2_test_no_image_split_9
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: 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 splits: - name: test num_bytes: 2186231101 num_examples: 44779 download_size: 571318700 dataset_size: 2186231101 --- # Dataset Card for "VQAv2_test_no_image_split_9" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
数据集信息(dataset_info): 特征(features): - 名称:问题类型(question_type),数据类型:字符串(string) - 名称:多项选择答案(multiple_choice_answer),数据类型:字符串(string) - 名称:答案序列(answers),数据类型:字符串序列(sequence: string) - 名称:原始答案列表(answers_original),数据类型:列表(list),包含子字段: - 答案(answer):字符串(string) - 答案置信度(answer_confidence):字符串(string) - 答案ID(answer_id):64位整型(int64) - 名称:图像ID(id_image),数据类型:64位整型(int64) - 名称:答案类型(answer_type),数据类型:字符串(string) - 名称:问题ID(question_id),数据类型:64位整型(int64) - 名称:问题文本(question),数据类型:字符串(string) - 名称:条目ID(id),数据类型:64位整型(int64) - 名称:CLIP (Contrastive Language-Image Pre-training) 标签 ViT-L/14(clip_tags_ViT_L_14),数据类型:字符串序列(sequence: string) - 名称:BLIP (Bootstrapping Language-Image Pre-training) 图像字幕(blip_caption),数据类型:字符串(string) - 名称:基于GPT3的大语言模型(Large Language Model,LLM)描述(针对视觉基因组(Visual Genome)的ViT-L/14下游任务)(LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14),数据类型:字符串序列(sequence: string) - 名称:DETA检测结果(使用deta_swin_large_o365_coco_classes模型)(DETA_detections_deta_swin_large_o365_coco_classes),数据类型:列表(list),包含子字段: - 属性(attribute):字符串(string) - 边界框(box):单精度浮点序列(sequence: float32) - 标签(label):字符串(string) - 位置(location):字符串(string) - 宽高比(ratio):单精度浮点数(float32) - 尺寸(size):字符串(string) - 标记(tag):字符串(string) - 名称:基于text-davinci-003的ViT-L/14属性描述符序列(Attributes_ViT_L_14_descriptors_text_davinci_003_full),数据类型:字符串序列(sequence: string) - 名称:CLIP ViT-L/14标签(不含OpenAI预设)(clip_tags_ViT_L_14_wo_openai),数据类型:字符串序列(sequence: string) - 名称:CLIP ViT-L/14标签(含OpenAI预设)(clip_tags_ViT_L_14_with_openai),数据类型:字符串序列(sequence: string) - 名称:CLIP LAION ViT-H/14 2B标签(不含OpenAI预设)(clip_tags_LAION_ViT_H_14_2B_wo_openai),数据类型:字符串序列(sequence: string) - 名称:CLIP LAION ViT-H/14 2B标签(含OpenAI预设)(clip_tags_LAION_ViT_H_14_2B_with_openai),数据类型:字符串序列(sequence: string) - 名称:CLIP LAION ViT-bigG/14 2B标签(不含OpenAI预设)(clip_tags_LAION_ViT_bigG_14_2B_wo_openai),数据类型:字符串序列(sequence: string) - 名称:CLIP LAION ViT-bigG/14 2B标签(含OpenAI预设)(clip_tags_LAION_ViT_bigG_14_2B_with_openai),数据类型:字符串序列(sequence: string) - 名称:基于text-davinci-003的LAION ViT-H/14 2B属性描述符序列(Attributes_LAION_ViT_H_14_2B_descriptors_text_davinci_003_full),数据类型:字符串序列(sequence: string) - 名称:基于text-davinci-003的LAION ViT-bigG/14 2B属性描述符序列(Attributes_LAION_ViT_bigG_14_2B_descriptors_text_davinci_003_full),数据类型:字符串序列(sequence: string) - 名称:DETA检测结果(使用deta_swin_large_o365_coco_classes_caption_module_random模型)(DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random),数据类型:列表(list),包含子字段: - 属性(attribute):字符串(string) - 边界框(box):双精度浮点序列(sequence: float64) - 字幕模块结果(captions_module):字符串序列(sequence: string) - 过滤后字幕模块结果(captions_module_filter):字符串序列(sequence: string) - 标签(label):字符串(string) - 位置(location):字符串(string) - 宽高比(ratio):双精度浮点数(float64) - 尺寸(size):字符串(string) - 标记(tag):字符串(string) 划分(splits): - 名称:测试集(test),字节数:2186231101,样本数:44779 下载大小(download_size):571318700 数据集总大小(dataset_size):2186231101 # 数据集卡片 "VQAv2_test_no_image_split_9" [更多信息请参阅](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
- 名称: VQAv2_test_no_image_split_9
数据集特征
- 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
- id: 整数类型(64位)
- clip_tags_ViT_L_14: 字符串序列
- blip_caption: 字符串类型
- LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14: 字符串序列
- DETA_detections_deta_swin_large_o365_coco_classes: 列表类型,包含:
- attribute: 字符串类型
- box: 浮点序列(32位)
- label: 字符串类型
- location: 字符串类型
- ratio: 浮点类型(32位)
- size: 字符串类型
- tag: 字符串类型
- 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
- DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random: 列表类型,包含:
- attribute: 字符串类型
- box: 浮点序列(64位)
- captions_module: 字符串序列
- captions_module_filter: 字符串序列
- label: 字符串类型
- location: 字符串类型
- ratio: 浮点类型(64位)
- size: 字符串类型
- tag: 字符串类型
数据集分割
- test:
- num_bytes: 2186231101
- num_examples: 44779
数据集大小
- download_size: 571318700
- dataset_size: 2186231101



