TinyMLgen for Python

A Python package to export TensorFlow Lite neural networks to C++ for microcontrollers

Tinymlgen is a Python library to export TensorFlow models into C format with a single line of code.

As an Arduino maker, you can then run that model on your microcontroller using the EloquentTinyML library.

Installation

Tinymlgen is available on PyPi, so you can use pip to install.

pip install -U tinymlgen

Or you can clone the Github repo

git clone https://github.com/eloquentarduino/tinymlgen

How to use

Tinymlgen package has a single method called port(): it accepts a TensorFlow model and returns the C code you need to import in your Arduino sketch.


from tinymlgen import port

if __name__ == '__main__':
    tf_model = create_tf_model()
    c_code = port(tf_model)

    with open('tensorflow_model.h', 'w') as file:
        file.write(c_code)

Want to quickly integrate TensorFlow Lite models into your Arduino project? EloquentTinyML library makes it a breeze.

Configuration

The port() method accepts 2 optional configuration options:

variable_name (str, defaults to 'model_data'): this is the name of the exported variable in C
pretty_print (bool, defaults to False): if True, the output is formatted in a more readable format