Fixes and improvements
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.
This release of TFProfiler Android App available in 2 variants. Please select the variant to download. Please read our FAQ to find out which variant is suitable for your Android device based on Screen DPI and Processor Architecture.
If you are looking to download other versions of TFProfiler Android App, We have 2 versions in our database. Please select one of them below to download.