.. include:: /keyword.rst

===========
AI Demo App
===========

Overview
--------

|IOT-YOCTO| has integrated two open-source gstreamer streaming pipeline frameworks for complex neural network applications.

- **GstInference**: 

    It is an `open-source project from Ridgerun Engineering <https://developer.ridgerun.com/wiki/index.php?title=GstInference>`_ that provides a framework for integrating deep learning inference into GStreamer. Either use one of the included elements 
    to do out-of-the-box inference using the most popular deep learning architectures or leverage the base classes and utilities to support your custom architecture.

    This repo uses `R²Inference <https://github.com/RidgeRun/r2inference>`_, an abstraction layer in C/C++ for a variety of machine learning frameworks. With R²Inference a single 
    C/C++ application may work with models on different frameworks. This is useful to execute inference taking advantage of different hardware resources such as CPU, GPU, or AI 
    optimized accelerators.

- **NNStreamer**:

    It is an `open-source project <https://nnstreamer.ai/>`_ which was initially developed by Samsung and then transferred to LF AI Foundation as an incubation project.
    It proivdes a set of `Gstreamer plugins <https://nnstreamer.github.io/component-description.html#gstreamer-elements-plugins>`_ that allow 
    Gstreamer developers to adopt neural network models easily and efficiently and neural network developers to manage neural network pipelines and their filters easily and 
    efficiently.

    NNStreamer provides the `new Gstreamer stream data type and a set of Gstreamer elements (plugins) <https://nnstreamer.github.io/component-description.html>`_ to construct media 
    stream pipeline with neural network models. It is well documented through its `online document site <https://nnstreamer.github.io/index.html>`_ and it supports well-known neural 
    network frameworks including Tensorflow, Tensorflow-lite, Caffe2, PyTorch, OpenVINO and ARMNN. 

    |IOT-YOCTO| have provided a new ``tensor_filter`` for Neuron SDK. Users can use ``tensor_filter_neuronsdk`` to create gstreamer media stream pipeline and leverage Genio platform's powerful AI hardware accelerator, 
    such as MDLA. You can find the implementation of the ``tensor_filter_neuronsdk`` in |IOT-YOCTO| NNStreamer source (``$BUILD_DIR/tmp/work/armv8a-poky-linux/nnstreamer/$PV/git/ext/nnstreamer/tensor_filter/tensor_filter_neuronsdk.cc``).

For a detailed introduction and usage guide of these frameworks, please refer to the:


.. toctree::
    :hidden:

    GstInference (EOL) <gstinference>
    NNStreamer <nnstreamer>
	
- :doc:`gstinference`
- :doc:`nnstreamer`