1# TensorFlow Lite Micro ESP-IDF Project
2
3This folder has been autogenerated by TensorFlow, and contains source, header,
4and project files needed to build a single TensorFlow Lite Micro target using
5Espressif's [ESP-IDF](https://docs.espressif.com/projects/esp-idf/en/latest/).
6
7## Usage
8
9### Install the ESP IDF
10
11Follow the instructions of the
12[ESP-IDF get started guide](https://docs.espressif.com/projects/esp-idf/en/latest/get-started/index.html)
13to setup the toolchain and the ESP-IDF itself.
14
15The next steps assume that the
16[IDF environment variables are set](https://docs.espressif.com/projects/esp-idf/en/latest/get-started/index.html#step-4-set-up-the-environment-variables) :
17 * The `IDF_PATH` environment variable is set.
18 * `idf.py` and Xtensa-esp32 tools (e.g., `xtensa-esp32-elf-gcc`) are in `$PATH`.
19
20## Build the example
21
22To build this, run:
23
24```
25idf.py build
26```
27
28### Load and run the example
29
30To flash (replace `/dev/ttyUSB0` with the device serial port):
31```
32idf.py --port /dev/ttyUSB0 flash
33```
34
35Monitor the serial output:
36```
37idf.py --port /dev/ttyUSB0 monitor
38```
39
40Use `Ctrl+]` to exit.
41
42The previous two commands can be combined:
43```
44idf.py --port /dev/ttyUSB0 flash monitor
45```
46
47## Project Generation
48
49See
50[tensorflow/lite/micro](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro)
51for details on how projects like this can be generated from the main source
52tree.
53
54## License
55
56TensorFlow's code is covered by the Apache2 License included in the repository,
57and third party dependencies are covered by their respective licenses, in the
58third_party folder of this package.
59