TFProfiler

TFProfiler is an app that aims to profile TensorFlow Lite model and measure its performance using FPS, model initialization time, model inference time, memory consumption, etc. You can tweak model interferences on Android smartphone with different options:

•  CPU

•  GPU

•  NNAPI

•  HEXAGON

•  XNNPACK

The app has a built-in subset of public available image dataset Caltech 101 (http://www.vision.caltech.edu/Image_Datasets/Caltech101/). It is used for running model inteferences.

Source code of the app can be found here: https://github.com/iglaweb/TFProfiler

The app is intended only for testing and conducting experiments on your Android smartphone.