five

thomas-yanxin/erqa-mirror

收藏
Hugging Face2026-04-07 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/thomas-yanxin/erqa-mirror
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: question_id dtype: string - name: question dtype: string - name: question_type dtype: string - name: answer dtype: string - name: visual_indices sequence: int32 - name: images sequence: image splits: - name: test num_bytes: 91359624.0 num_examples: 400 download_size: 77790243 dataset_size: 91359624.0 configs: - config_name: default data_files: - split: test path: data/test-* --- # Introduction **Disclaimer:** This dataset is organized and adapted from [embodiedreasoning/ERQA](https://github.com/embodiedreasoning/ERQA). The original data was provided in TFRecord format and has been converted here into a more accessible and easy-to-use format. This evaluation benchmark covers a variety of topics related to spatial reasoning and world knowledge focused on real-world scenarios, particularly in the context of robotics. Please find more details and visualizations in the tech report. # Data Fields | Field Name | Type | Description | |------------------|-------------------|-------------------------| | question_id | string | Unique question ID | | question | string | Question text | | question_type | string | Type of question | | answer | string | Answer | | visual_indices | list[int] | List of visual indices | | images | list[Image] | Image data | | images_base64 | list[string] | Image data in base64 |

数据集信息: 特征: - 名称:question_id,数据类型:字符串 - 名称:question,数据类型:字符串 - 名称:question_type,数据类型:字符串 - 名称:answer,数据类型:字符串 - 名称:visual_indices,数据类型:int32序列 - 名称:images,数据类型:图像(image)序列 划分集: - 名称:test,字节数:91359624.0,示例数量:400 下载大小:77790243,数据集总大小:91359624.0 配置项: - 配置名称:default,数据文件: - 划分集:test,路径:data/test-* --- # 简介 **免责声明:** 本数据集整理改编自[embodiedreasoning/ERQA](https://github.com/embodiedreasoning/ERQA)。原始数据以TFRecord格式提供,现已转换为更易于访问和使用的格式。 本评测基准涵盖了与空间推理和世界知识相关的多种主题,聚焦真实世界场景,尤其适用于机器人学场景。如需了解更多细节与可视化内容,请参阅该技术报告。 # 数据字段 | 字段名 | 数据类型 | 描述 | |----------------|-------------------|--------------------------| | question_id | 字符串 | 唯一问题标识符 | | question | 字符串 | 问题文本 | | question_type | 字符串 | 问题类型 | | answer | 字符串 | 答案 | | visual_indices | 整数列表 | 视觉索引列表 | | images | 图像列表 | 图像数据 | | images_base64 | 字符串列表 | Base64编码的图像数据 |
提供机构:
thomas-yanxin
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作