uploaded 1 month ago
TensorFlow Lite Micro component for ESP-IDF


# TensorFlow Lite Micro for Espressif Chipsets

[![Component Registry](](

- As per TFLite Micro guidelines for vendor support, this repository has the `esp-tflite-micro` component and the examples needed to use Tensorflow Lite Micro on Espressif Chipsets (e.g., ESP32) using ESP-IDF platform.
- The base repo on which this is based can be found [here.](

## Build Status

|   Build Type  |  Status    |
| -----------   |  --------- |
| Examples Build | [![CI](](

## How to Install

### Install the ESP IDF

Follow the instructions of the
[ESP-IDF get started guide](
to setup the toolchain and the ESP-IDF itself.

The next steps assume that this installation is successful and the
[IDF environment variables are set]( Specifically,
* the `IDF_PATH` environment variable is set
* the `` and Xtensa-esp32 tools (e.g., `xtensa-esp32-elf-gcc`) are in `$PATH`

## Using the component

Run the following command in your ESP-IDF project to install this component:

```bash add-dependency "esp-tflite-micro"

## Building the example

To get the example, run the following command:

```bash create-project-from-example "esp-tflite-micro:<example_name>"

  - If you have cloned the repo, the examples come as the part of the clone. Simply go to the example directory (`examples/<example_name>`) and build the example.

Available examples are:
 - hello_world
 - micro_speech
 - person_detection

Set the IDF_TARGET (For ESP32-S3 target, minimum IDF version `release/v4.4` is needed)

```bash set-target esp32s3

To build the example, run:

```bash build

### Load and run the example

To flash (replace `/dev/ttyUSB0` with the device serial port):
```bash --port /dev/ttyUSB0 flash

Monitor the serial output:
```bash --port /dev/ttyUSB0 monitor

Use `Ctrl+]` to exit.

The previous two commands can be combined:
```bash --port /dev/ttyUSB0 flash monitor

  - Please follow example READMEs for more details.

## ESP-NN Integration
[ESP-NN]( contains optimized kernel implementations for kernels used in TFLite Micro. The library is integrated with this repo and gets compiled as a part of every example. Additional information along with performance numbers can be found [here](

### Performance Comparison

A quick summary of ESP-NN optimisations, measured on various chipsets:

|   Target  |   TFLite Micro Example  | without ESP-NN  | with ESP-NN | CPU Freq  |
| --------- | ----------------------- | --------------- | ----------- |-----------|
| ESP32-S3  |   Person Detection      |     2300ms      |     54ms    |  240MHz   |
| ESP32     |   Person Detection      |     4084ms      |    380ms    |  240MHz   |
| ESP32-C3  |   Person Detection      |     3355ms      |    426ms    |  160MHz   |

  - The above is time taken for execution of the `invoke()` call
  - Internal memory used

Detailed kernelwise performance can be found [here](

## Sync to latest TFLite Micro upstream

As per the upstream repository policy, the tflite-lib is copied into the components directory in this repository. We keep updating this to the latest upstream version from time to time. Should you, in any case, wish to update it locally, you may run the `scripts/` script.

## Contributing
- If you find an issue in these examples, or wish to submit an enhancement request, please use the Issues section on Github.
- For ESP-IDF related issues please use [esp-idf]( repo.
- For TensorFlow related information use [tflite-micro]( repo.

## License

This component and the examples are provided under Apache 2.0 license, see [LICENSE]( file for details.

TensorFlow library code and third_party code contains their own license specified under respective [repos](


Supports all targets

License: Apache-2.0

To add this component to your project, run: add-dependency "espressif/esp-tflite-micro^1.3.1"

or download archive


  • Archive size
    Archive size: 1.18 MB
  • Downloaded in total
    Downloaded in total 4.1k times
  • Downloaded this version
    This version: 1.3k times


espressif/esp-tflite-micro version: 1.3.1