在Docker上部署机器学习项目的实践研究
Studying the Practices of Deploying Machine Learning Projects on Docker
摘要:
Docker是一种容器化服务,允许通过几行代码方便地部署网站,数据库,应用程序的API和机器学习(ML)模型。最近的研究探索了Docker在部署一般软件项目中的使用,但没有特别关注Docker如何用于部署基于ML的项目。在这项研究中,我们进行了一项探索性研究,以了解Docker如何用于部署基于ML的项目。作为第一步,我们检查了使用Docker的基于ML的项目的类别。然后,我们研究了这些项目为什么以及如何使用Docker,以及生成的Docker镜像的特征。我们的研究结果表明,六类基于ML的项目使用Docker进行部署,包括ML应用程序,MLOps/ AIOps,工具包,DL框架,模型和文档。我们推导出了21个主要类别的分类,这些类别代表了使用Docker的目的,包括那些特定于模型的类别,如模型管理任务(例如,测试、培训)。然后,我们展示了ML工程师使用Docker镜像主要是为了帮助实现平台可移植性,例如跨操作系统、GPU等运行时和语言约束传输软件。然而,我们也发现,由于镜像层中包含大量文件,并且目录嵌套很深,因此可能需要更多的资源来运行Docker镜像以构建基于ML的软件项目。我们希望阐明使用容器部署ML软件项目的新兴实践,并强调应该改进的方面。
英文摘要:
Docker is a containerization service that allows for convenient deployment of websites, databases, applications' APIs, and machine learning (ML) models with a few lines of code. Studies have recently explored the use of Docker for deploying general software projects with no specific focus on how Docker is used to deploy ML-based projects. In this study, we conducted an exploratory study to understand how Docker is being used to deploy ML-based projects. As the initial step, we examined the categories of ML-based projects that use Docker. We then examined why and how these projects use Docker, and the characteristics of the resulting Docker images. Our results indicate that six categories of ML-based projects use Docker for deployment, including ML Applications, MLOps/ AIOps, Toolkits, DL Frameworks, Models, and Documentation. We derived the taxonomy of 21 major categories representing the purposes of using Docker, including those specific to models such as model management tasks (e.g., testing, training). We then showed that ML engineers use Docker images mostly to help with the platform portability, such as transferring the software across the operating systems, runtimes such as GPU, and language constraints. However, we also found that more resources may be required to run the Docker images for building ML-based software projects due to the large number of files contained in the image layers with deeply nested directories. We hope to shed light on the emerging practices of deploying ML software projects using containers and highlight aspects that should be improved.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。