arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01388cs.SEcs.LG
收藏

深度学习缺陷特征的综合研究

A Comprehensive Study on Deep Learning Bug Characteristics

Iowa State University(爱荷华州立大学)

Md Johirul Islam, Giang Nguyen, Rangeet Pan, Hridesh Rajan

摘要:

近年来,深度学习获得了极大的普及。开发人员主要依靠库和工具来为他们的软件添加深度学习功能。在这些软件中经常发现什么样的bug?此类错误的根本原因是什么?这些bug有什么影响?深度学习管道的哪个阶段更容易出现错误?是否存在任何反模式?理解深度学习软件中缺陷的这些特征有可能促进更好的深度学习平台、调试机制、开发实践的开发,并鼓励分析和验证框架的开发。因此,我们研究了来自Stack Overflow的2716篇高质量帖子和来自Github的500个bug修复提交,这些帖子涉及五个流行的深度学习库Caffe,Keras,Tensorflow,Theano和Torch,以了解bug的类型,bug的根本原因,bug的影响,深度学习管道的bug易发阶段以及在这个bug软件中是否存在一些常见的反模式。我们研究的主要发现包括:数据错误和逻辑错误是深度学习软件中最严重的错误类型,出现的次数超过48%,这些错误的主要根源是模型参数不正确(IPS)和结构效率低下(SI),出现的次数超过43%。我们还发现,使用深度学习库时的错误有一些共同的反模式,导致库之间的错误类型具有很强的相关性。

英文摘要:

Deep learning has gained substantial popularity in recent years. Developers mainly rely on libraries and tools to add deep learning capabilities to their software. What kinds of bugs are frequently found in such software? What are the root causes of such bugs? What impacts do such bugs have? Which stages of deep learning pipeline are more bug prone? Are there any antipatterns? Understanding such characteristics of bugs in deep learning software has the potential to foster the development of better deep learning platforms, debugging mechanisms, development practices, and encourage the development of analysis and verification frameworks. Therefore, we study 2716 high-quality posts from Stack Overflow and 500 bug fix commits from Github about five popular deep learning libraries Caffe, Keras, Tensorflow, Theano, and Torch to understand the types of bugs, root causes of bugs, impacts of bugs, bug-prone stage of deep learning pipeline as well as whether there are some common antipatterns found in this buggy software. The key findings of our study include: data bug and logic bug are the most severe bug types in deep learning software appearing more than 48% of the times, major root causes of these bugs are Incorrect Model Parameter (IPS) and Structural Inefficiency (SI) showing up more than 43% of the times. We have also found that the bugs in the usage of deep learning libraries have some common antipatterns that lead to a strong correlation of bug types among the libraries.

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。

↑