Latest update
First release!
TFProfiler APK Description
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.
How to install TFProfiler APK for Android
Download TFProfiler APK file (ru.igla.tfprofiler_12_58269680.apk) from APKPure.live, then follow these steps:
Update Phone Settings
- Go to your phone Settings page
- Tap Security or Applications (varies with device)
- Check the Unknown Sources box
- Confirm with OK
Go to Downloads
- Open Downloads on your device by going to My Files or Files
- Tap the APK file you downloaded (ru.igla.tfprofiler_12_58269680.apk)
- Tap Install when prompted, the APK file you downloaded will be installed on your device.
How to install TFProfiler APK on Windows PC 7/8/10/11 or MAC?
Download TFProfiler APK file (ru.igla.tfprofiler_12_58269680.apk) from APKPure.live to your PC (ex: C://Users/xxx/Downloads/(ru.igla.tfprofiler_12_58269680.apk), then follow these steps appear on screen.
Using Emulator:
- Download And Install one Emulator Softwares (Ex: Bluestacks, GenyMotion, NoxPlayer)
- Simple install APK on PC by drag and drop file ru.igla.tfprofiler_12_58269680.apk on Emulator screen
TFProfiler APK Pros & Cons
Pros
- This app is safe, it's not require high risk permissions
- Compatible with 32 bit device (most Emulator using 32bit arch CPU)
- Compatible with 64-bit device (some android device and current Bluestacks)
Cons
Everything is good.
