Google unveils TensorFlow tool for making mobile-ready models
TensorFlow Lite Model Maker shrinks TensorFlow models to more efficiently serve predictions on mobile devices
20 April 2020 | 0
In a blog post, Google described how TensorFlow Lite Model Maker adapts existing TensorFlow models to the Lite format with only a few lines of code. The adaptation process uses one of a small number of task types to evaluate the model and generate a Lite version. The downside is that only a couple of task types are available for use right now – i.e. image and text classification – so models for other tasks (e.g. machine vision) are not yet supported.
Other TensorFlow Lite tools announced in the same post include a tool to automatically generate platform-specific wrapper code to work with a given model. Because hand-coding wrappers for models can be error-prone, the tool automatically generates the wrapper from metadata in the model autogenerated by Model Maker. The tool is currently available in a pre-release beta version, and supports only Android right now, with plans to eventually integrate it into Android Studio.
IDG News Service