CExamples < IoT_Course_English

Tags: view all tags
---+ The !TinyML examples written in C++

The !TinyML examples in C++, ported to the ESP32 can be found at https://github.com/espressif/tflite-micro-esp-examples/tree/master/examples. There you also find the procedures to actually build the programs. In fact there are two methods of building:
   * use thee Espressif esp-idf build system
   * use the Arduino IDE
   * use the !MicroPython interface to !TensorFlow [[MicroPython Examples]]
The test programs allowing to test the model before deploying it to the target processor can be found in the [[https://github.com/tensorflow/tflite-micro/tree/main/tensorflow/lite/micro/examples][ TensorFlow Lite Micro repository]].
---++ Arduino

For the Arduino SDK (Software Development Kit) you can install the !TensorFlowLite_ESP32 library, which does not only contain the !TensforFlowLite library but also the examples
   * hello_world
   * wake word detection
   * person detection
   * ... and even some older version of magic wand, which is not available elsewhere

<img alt="tflite_examples_arduino.png" height="905" src="%ATTACHURL%/tflite_examples_arduino.png" title="tflite_examples_arduino.png" width="1288" />

*%RED%Attention: When using Serial.print on the !LoLin !ESP32S3 mini, you must set the option USB CDC on boot to enabled! The option is found in the Tools menu. Oherwise you will not see any output on the Serial monitor.%ENDCOLOR%*
---++ The Hello World test programs

Three test programs are available:
   * hello_world_test.cc
   * evaluate.py
   * evaluate_test.py
These programs are built using the [[https://bazel.build/][bazel ]]build tool. In order tto build hello_world_test.cc, got to the base directory of !TensorFlow Lite Micro directory and enter the commands. First the hello_world_test binary must be built from its source:

<img alt="hello_world_test_build.png" height="195" src="%ATTACHURL%/hello_world_test_build.png" title="hello_world_test_build.png" width="1099" />

before the program can be run:

<img alt="hello_world_test_run.png" height="656" src="%ATTACHURL%/hello_world_test_run.png" title="hello_world_test_run.png" width="1100" />

For a detailed analysis of the test program please set [[analysis cc test]]
---++ The Hello World application with esp-idf

Let's start with the hello_world example. This example uses a pre-built model that has gone through the training process and it has been quantized to reduce its size such that it can be loaded into the small micro-controller memory. Building, training and quantization is described at https://github.com/tensorflow/tflite-micro/tree/main/tensorflow/lite/micro/examples/hello_world.

We must first tell the idf.py that we are using an !ESP32S3 chip:
<verbatim>idf.py set-target esp32s3</verbatim>

After that we may have to clean previous builds:
<verbatim>idf.py fullclean</verbatim>

and finally we can build the hello_world program:
<verbatim>idf.py build</verbatim>

Once the program is built we can flash it and connect the serial monitor to see the results:
<verbatim>idf.py flash monitor</verbatim>

The program repeatedly runs the induction for 20 angle values between 0 and 2&Pi;. These values can easily be captured by redirecting the output to a file. I then used an editor to prepare the data to be plotted with gnuplot.
<verbatim>idf.py flash monitor | tee results.txt</verbatim>

Finally I wrote a simple Python program calculating the correct 20 sine values, which allows to compare them to the results from TinyML.

<img alt="results.png" height="481" src="%ATTACHURL%/results.png" title="results.png" width="631" />
---++ Creating the model and training it

When working with Machine Learning, data play a primordal role because data are used to train the model and therefore influence the opaque algorithm within the model.

The model for the hello world example is created with the Python script train.py.

-- %USERSIG{UliRaich - 2023-09-02}%

---++ Comments

<br />%COMMENT%
Attachments
Topic attachments
I	Attachment	History	Action	Size	Date	Who
png	hello_world_test_build.png	r1	manage	52.2 K	2023-09-08 - 07:30	UliRaich
png	hello_world_test_run.png	r1	manage	152.4 K	2023-09-08 - 07:30	UliRaich
png	results.png	r1	manage	24.2 K	2023-09-02 - 14:28	UliRaich
png	tflite_examples_arduino.png	r1	manage	178.7 K	2023-09-07 - 13:05	UliRaich
Topic revision: r6 - 2023-11-08 - UliRaich