https://www.tensorflow.org/lite/microcontrollers/overview
https://github.com/espressif/tflite-micro-esp-examples
This library runs TensorFlow machine learning models on microcontrollers, allowing you to build AI/ML applications powered by deep learning and neural networks.
With the included examples, you can recognize speech, detect people using a camera, and recognise "magic wand" gestures using an accelerometer.
The examples work best with the M5StickC(ESP32) board, which has a microphone and accelerometer.
Outputs sine waves to serial outputs and build-in LEDs.
In tanakamasayuki's original version there are more examples, however, I could not not checked if they work as I only have an ESP32 WROOM DevKit V1.
cd scripts
bash ./sync_from_tflite_micro.sh
You can also make this library using the last version of TensorFlowLite (as synced from https://github.com/espressif/tflite-micro-esp-examples)
cd scripts
bash ./sync_from_tflite_micro_version_schema_3.sh
This latter script will create the folder TensorFlowLite_ESP32_tmp
.
└── TensorFlowLite_ESP32_tmp
├── examples
│ └── hello_world
├── LICENSE
└── src
├── bus
├── screen
├── tensorflow
├── TensorFlowLite_ESP32.h
├── third_party
└── utility.h