create new tag
view all tags

A detailed Analysis of the hello_world_test.cc program

Below the license header the program has a number of include directives giving access to the tflite micro library as well as a number of macros.



defines the macro TF_LITE_ENSURE_STATUS as well as a number of data structures and it gives access to core functtionality of the tflite core library.

tensorflow/lite/micro/examples/hello_world/models/hello_world_float_model_data.h and 

are the models created with train.py and converted to a C++ array. While the book describes how to create the .cc file using the Unix xxd command ,in which case the corresponding .h file must be created by hand, the new version uses the python script generate_cc_arrays.py in tensorflow/lite/micro/tools to acconplish the conversion.

You can easily try this with the command:


The first parameter to the command is the name of the output directory and the second parameter is the filename of the model (should have the extension .tflite) The same python script can also be used to convert audio files (.wav), image files (.bmp) or excel sheets (.cvs).


The Tensorflow Lite Micro interpreter, which will run the model


Used for error logging. Defines MicroPrintf used to print logging information

-- Uli Raich - 2023-09-08


Topic attachments
I Attachment History Action Size Date Who Comment
PNGpng hello_world_test_include.png r1 manage 51.2 K 2023-09-08 - 08:28 UliRaich  
PNGpng model_conversion.png r1 manage 39.6 K 2023-09-09 - 12:41 UliRaich  
Edit | Attach | Watch | Print version | History: r3 < r2 < r1 | Backlinks | Raw View | Raw edit | More topic actions
Topic revision: r3 - 2023-09-09 - 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