Android Instruct|Android自主代理数据集|移动操作系统数据集
收藏AndroidLab: 训练和系统化基准测试Android自主代理
数据集概述
- 名称: AndroidLab
- 描述: AndroidLab是一个系统化的Android代理框架,包含操作环境和可复现的基准测试。基准测试包括预定义的Android虚拟设备和基于这些设备的138个任务,涵盖九个应用程序。
基准测试组件
- 应用列表:
- Bluecoins: 个人财务管理应用,用于跟踪支出和收入。
- Calendar: 日历应用,帮助组织日程和设置提醒。
- Cantook: 电子书阅读器,用于存储、管理和阅读电子书。
- Clock: 时钟应用,用于显示时间、设置闹钟和使用秒表。
- Contacts: 联系人管理应用,用于存储和组织联系信息。
- Maps.me: 离线地图应用,用于导航和探索地点。
- PiMusic: 音乐播放器应用,用于组织和播放本地存储的音乐文件。
- Settings: 设置应用,用于配置设备设置和偏好。
- Zoom: 视频会议应用,用于主持和加入在线会议。
快速开始
- 环境设置:
- 自动评估管道:
-
运行评估: bash python eval.py -n test_name -c your path to config.yaml
-
并行测试: bash python eval.py -n test_name -c your path to config.yaml -p 3
-
生成评估结果: bash python generate_result.py --input_folder ./logs/evaluation/ --output_folder ./logs/evaluation/ --output_excel ./logs/evaluation/test_name.xlsx --judge_model gpt-4o-2024-05-13
-
引用
@misc{xu2024androidlabtrainingsystematicbenchmarking, title={AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents}, author={Yifan Xu and Xiao Liu and Xueqiao Sun and Siyi Cheng and Hao Yu and Hanyu Lai and Shudan Zhang and Dan Zhang and Jie Tang and Yuxiao Dong}, year={2024}, eprint={2410.24024}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2410.24024}, }

- 1AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents清华大学 · 2024年
jpft/danbooru2023
Danbooru2023是一个大规模的动漫图像数据集,包含超过500万张由爱好者社区贡献并详细标注的图像。图像标签涵盖角色、场景、版权、艺术家等方面,平均每张图像有30个标签。该数据集可用于训练图像分类、多标签标注、角色检测、生成模型等多种计算机视觉任务。数据集基于danbooru2021构建,扩展至包含ID #6,857,737的图像,增加了超过180万张新图像,总大小约为8TB。图像以原始格式提供,分为1000个子目录,使用图像ID的模1000进行分桶,以避免文件系统性能问题。
hugging_face 收录
HazyDet
HazyDet是由解放军工程大学等机构创建的一个大规模数据集,专门用于雾霾场景下的无人机视角物体检测。该数据集包含383,000个真实世界实例,收集自自然雾霾环境和正常场景中人工添加的雾霾效果,以模拟恶劣天气条件。数据集的创建过程结合了深度估计和大气散射模型,确保了数据的真实性和多样性。HazyDet主要应用于无人机在恶劣天气条件下的物体检测,旨在提高无人机在复杂环境中的感知能力。
arXiv 收录
NASA Langley Research Center Turbulence Modeling Resource
该数据集包含用于湍流建模的计算流体动力学(CFD)基准测试案例,涵盖了多种几何形状和流动条件。数据集提供了详细的网格、边界条件、流场解和实验数据,用于验证和开发湍流模型。
turbmodels.larc.nasa.gov 收录
NAICS 2022 (North American Industry Classification System)
**NAICS 2022 (North American Industry Classification System)** **Overview** This is a free dataset of Data LV's North American Industry Classification System (NAICS). This dataset contains the full information about NAICS on USA, Canada and Mexico. The North American Industry Classification System (NAICS) is an industry classification system developed by the statistical agencies of the United States, Canada and Mexico. Created against the background of the North American Free Trade Agreement, it is designed to provide common definitions of the industrial structure of the three countries and a common statistical framework to facilitate the analysis of the three economies. NAICS is based on supply-side or production-oriented principles, to ensure that industrial data, classified to NAICS, are suitable for the analysis of production-related issues such as industrial performance. The great advantage of this dataset compared to other available is that it has all the codes, even if the code is defined by the statistical agency of only one country, and it has the information in **English, French and Spanish**. **Use cases** - Market Segmentation and Analysis - Risk Assessment and Credit Scoring - Customer Profiling and Personalization - Competitor Analysis - Economic Impact and Industry Analysis - Supply Chain Optimization - Regulatory and Compliance Analysis - Data Enrichment for Machine Learning Models - Investment and Portfolio Management **Product details** This share contains the following datasets: - **NAICS_AllCodes**: All the codes defined by any of the national statistical agencies with the title and description in English, French and Spanish. - **CanadianIndustry_Element_EN**: Table containing the elements included or excluded in the different Canadian Sectors, Subsectors, Industry groups and Industries, in English. - **CanadianIndustry_Element_FR**: Table containing the elements included or excluded in the different Canadian Sectors, Subsectors, Industry groups and Industries, in French. - **MexicanIndustry_Element_ES**: Table containing the elements included in the different Mexican Industries, in Spanish. - **Mexico_Included_Excluded_ES**: Table containing the elements included and excluded in the different Mexican Sectors, Subsectors, Industry groups and Industries, in Spanish. **Additional information:** For more details, refer to the embedded notebook. **Additional Insights** For support, please contact support@datalv.io for full product licensing information. For full product licensing information, please contact databricks@datalv.io
Databricks 收录
Digital Typhoon
Digital Typhoon数据集是由日本国立情报学研究所创建的,包含自1978年至2022年共44个台风季节的189,364张卫星图像。该数据集旨在为机器学习模型提供长期时空数据基准,特别适用于深度学习模型的分类和回归任务。数据集通过Lambert等面积投影技术处理,确保图像质量,并解决了传感器噪声、数据缺失和长期传感器校准等数据质量问题。该数据集的应用领域包括气象分析、社会影响评估和气候变化研究,旨在通过机器学习技术提升对台风活动的理解和预测,从而减少灾害风险和应对气候变化。
arXiv 收录