Usar la aplicación APKPure
Obtener TFProfiler versión histórica en Android
Perfila tu modelo de Tensorflow Lite en el dispositivo con diferentes opciones
TFProfiler is an app that aims to profile TensorFlow Lite model or OpenCV DNN supported ones (*.onnx, *.caffemodel, *.pb, *.weights, *.t7, *.net, etc). Measure model performance with FPS, model initialization time, inference time, memory consumption, etc. You can tweak model inferences on Android smartphone with different accelerators:
• 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 may be used for testing model inferences.
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.
Last updated on 09/06/2022
Fixes and improvements
Presentado por
Khinsoeoo Soeoo
Requisitos
Android 5.0+
Categoría
Reportar
TFProfiler
1.2.0 by FRUCT
09/06/2022