create new tag
view all tags

The Hello World example as provided by the tflite-micro repository

The TensorFlowLite-Micro repository provides the code

  • creating the hello world neural network model
  • creating input tensors with x and sin(x) values used to train the model
  • converting the model to tflite flatbuffer format and quantizing it to int8_t numbers
    The quantized mode can be read from a file in case of the MicroPython version of the hello world example. The Arduino SDK does not use a file system and the quantized model is therefore converted into C++ code included into the source code of the Arduino hello world version.
  • testing the model with input tensor values 0..2π

-- Uli Raich - 2023-12-18


Topic attachments
I Attachment History Action Size Date Who Comment
PNGpng hello_world_test_include.png r1 manage 51.2 K 2023-12-18 - 16:00 UliRaich  
PNGpng hello_world_test_run.png r1 manage 152.4 K 2023-12-18 - 16:00 UliRaich  
PNGpng tflite_examples_arduino.png r1 manage 178.7 K 2023-12-18 - 16:01 UliRaich  
Topic revision: r1 - 2023-12-18 - UliRaich
This site is powered by the TWiki collaboration platform Powered by PerlCopyright © 2008-2024 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback