.. include:: /keyword.rst

===========================
Build from IoT Yocto Layer
===========================

.. note::

    Before downloading the Yocto layer, make sure you already have a populated Yocto building
    environment. Please refer to :doc:`/sw/yocto/get-started/build-code` for more information.

Please run following command to download the Yocto layer:

.. prompt:: bash

    git clone https://gitlab.com/mediatek/aiot/rity/meta-mediatek-demo.git $PROJ_ROOT/src/meta-mediatek-demo

Setup Yocto building environment as described in :doc:`/sw/yocto/get-started/build-code`:

.. prompt:: bash

    cd $PROJ_ROOT
    export TEMPLATECONF=${PWD}/src/meta-rity/meta/conf/
    source src/poky/oe-init-build-env
    export BUILD_DIR=`pwd`

Run following command to add the layer we just downloaded to the environment:

.. prompt:: bash

    bitbake-layers add-layer ../src/meta-mediatek-demo

Enable R2Inference and GstInference in your `$PROJ_ROOT/build/conf/local.conf`.

.. prompt:: bash
    
    IMAGE_INSTALL:append = "r2inference gstinference"

Rebuild the image:

.. prompt:: bash

    DISTRO=rity-demo MACHINE=genio-1200-evk bitbake rity-demo-image

Please refer to :doc:`/sw/yocto/get-started/flash` to flash the target board
with the built image.

You can find the example models and labels in the ``/usr/share/gstinference_example`` directory.
Here is the folder structure of gstinference_example:

.. code-block::

    .
    ├── image_classification
    │   ├── labels.txt
    │   ├── mobilenet_v1_1.0_224_quant.tflite
    │   └── mobilenet_v1_1.0_224_quant.dla
    └── object_detection
        ├── labels_pascal.txt
        ├── mobilenet_ssd_pascal_quant.tflite
        └── mobilenet_ssd_pascal_quant.dla


To run the built-in application, please connect the camera to the board first. Please refer to :doc:`/sw/yocto/app-dev/camera/camera-common` section for camera configuration.

:doc:`/tools/ai-demo-app/run-the-demo` section has the detail for how to launch the APP.