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.
Read more
Collapse
Loading…

What's New

First release!
Read more
Collapse

Additional Information

Updated
November 1, 2020
Size
71M
Installs
5+
Current Version
0.93
Requires Android
5.0 and up
Content Rating
Everyone
Permissions
Offered By
FRUCT
Developer
199155, St-Petersburg, Russia or 00930, Helsinki, Finland
©2021 GoogleSite Terms of ServicePrivacyDevelopersAbout Google|Location: United StatesLanguage: English (United States)
By purchasing this item, you are transacting with Google Payments and agreeing to the Google Payments Terms of Service and Privacy Notice.