Should I use TensorFlow
It provides guidance for experienced ML practitioners deciding whether to adopt TensorFlow in their environment, focusing on practical aspects like flexibility and performance.
This paper examines TensorFlow's suitability for machine learning practitioners by comparing a pure Python linear classification implementation with a TensorFlow version and contrasting it with other frameworks on aspects like modeling capability, deployment, and performance.
Google's Machine Learning framework TensorFlow was open-sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its models to be deployed productively. This work is aimed towards people with experience in Machine Learning considering whether they should use TensorFlow in their environment. Several aspects of the framework important for such a decision are examined, such as the heterogenity, extensibility and its computation graph. A pure Python implementation of linear classification is compared with an implementation utilizing TensorFlow. I also contrast TensorFlow to other popular frameworks with respect to modeling capability, deployment and performance and give a brief description of the current adaption of the framework.