arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.01796cs.LGcs.SE
收藏

UniNAS框架:用参数树组合任意复杂配置中的模块

The UniNAS framework: combining modules in arbitrarily complex configurations with argument trees

University of Tuebingen(蒂宾根大学)

Kevin Alexander Laube

摘要:

将代码设计得过于简单,但又提供选择,这就像走钢丝。优化器和数据集等附加模块使框架对更广泛的受众有用,但增加的复杂性很快成为一个问题。框架参数可能只适用于某些模块,而不适用于其他模块,相互排斥或相互依赖,通常方式不明确。即便如此,许多框架也仅限于少数特定用例。本文介绍了UniNAS的基本概念,这是一个旨在整合各种神经架构搜索方法的框架。由于它们在优化器和网络的数量、超参数优化、网络设计、候选操作等方面存在差异,因此传统方法无法解决该任务。相反,每个模块都定义了自己的超参数和模块需求的本地树结构。配置文件指定使用哪些模块,它们使用的参数,以及它们依次使用哪些其他模块。参数树的概念允许在复杂配置中组合和重用模块,同时避免了上面提到的许多问题。参数树也可以从图形用户界面配置,这样设计和更改实验就变得可能,而无需编写一行代码。UniNAS可在https://github.com/cogsys-tuebingen/uninas上公开获取

英文摘要:

Designing code to be simplistic yet to offer choice is a tightrope walk. Additional modules such as optimizers and data sets make a framework useful to a broader audience, but the added complexity quickly becomes a problem. Framework parameters may apply only to some modules but not others, be mutually exclusive or depend on each other, often in unclear ways. Even so, many frameworks are limited to a few specific use cases. This paper presents the underlying concept of UniNAS, a framework designed to incorporate a variety of Neural Architecture Search approaches. Since they differ in the number of optimizers and networks, hyper-parameter optimization, network designs, candidate operations, and more, a traditional approach can not solve the task. Instead, every module defines its own hyper-parameters and a local tree structure of module requirements. A configuration file specifies which modules are used, their used parameters, and which other modules they use in turn This concept of argument trees enables combining and reusing modules in complex configurations while avoiding many problems mentioned above. Argument trees can also be configured from a graphical user interface so that designing and changing experiments becomes possible without writing a single line of code. UniNAS is publicly available at https://github.com/cogsys-tuebingen/uninas

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。

↑