VX TFLite

TFlite implementations from https://github.com/sravansenthiln1/armnn_tflite/ adapted to run on Verisilicon's Vivante NPU hardware platform.

Compatible with VIM3/3L, on the 4.9 kernel.

Install pip

sudo apt-get install python3-pip

Install necessary python packages

pip3 install numpy pillow

Install the TFLite runtime interpreter

pip3 install --extra-index-url https://google-coral.github.io/py-repo/ tflite_runtime

Create Library symlink

sudo ln /usr/lib/libOpenVX.so /usr/lib/libOpenVX.so.1

Copy the necessary library files

If you are running on VIM3:

sudo cp libs/VIM3/libtim-vx.so /usr/bin/aarch64-linux-gnu/

If you are running on VIM3L:

sudo cp libs/VIM3L/libtim-vx.so /usr/bin/aarch64-linux-gnu/

Try the examples

• Sine Model - Basic Neural network TFLite model

• Digit recognize Model - Digit recognization model

• Mobilenet v1 Model - Mobilenet v1 image classification model