.. include:: /keyword.rst

.. _ml-common:

================================
Machine Learning Developer Guide
================================

.. contents:: Sections
    :local:
    :depth: 1

.. toctree::
    :hidden:
    
    Genio 350-EVK <ml-g350-evk>
    Genio 510/700-EVK <ml-g700-evk>
    Genio 1200-EVK <ml-g1200-demo>
    Neuron SDK <ml-neuron-sdk>
    Model Hub <ml-model-hub>
    TAO on Genio <tao-on-genio>
    Common Q&A <ml-common-qa>
    Neuron Development Workflow <neuron_dev_flow>

--------------------------------

Overview
========

Due to the different hardware on each platform, the |IOT-YOCTO| provides different 
machine learning software stacks for the developer. Table 1 shows the hardware difference on different 
boards. Table 2 shows the difference in machine learning software stacks on different boards.

.. csv-table:: Table 1. Hardware Devices on Board
    :class: longtable
    :file: /_asset/tables/ml-platform-hw-acc-devices.csv
    :width: 65%
    :widths: 20 100 100 100 100

.. note::

    For the introduction of hardware devices, please refer to :ref:`Hardware Devices <ml_hw-devices>`

.. csv-table:: Table 2. Software Stack on Board
    :class: longtable
    :file: /_asset/tables/ml-platform-sw-stack.csv
    :width: 65%
    :widths: 140 100 100 100 100 100

--------------------------------

Reference Boards
================

|IOT-YOCTO| provides different machine learning software stacks on different SoC platforms. Please 
find more details about machine learning on each reference board:

- :doc:`Genio 350-EVK Machine Learning </sw/yocto/ml-guide/ml-g350-evk>`.

- :doc:`Genio 510/700-EVK Machine Learning </sw/yocto/ml-guide/ml-g700-evk>`.

- :doc:`Genio 1200-EVK Machine Learning </sw/yocto/ml-guide/ml-g1200-demo>`.


Model Hub
=========

|IOT-YOCTO| provides a list of models that are usable on G510, G700 and G1200.
Please go to :doc:`Model Hub section </sw/yocto/ml-guide/ml-model-hub>` to download them.

Common Q&A
==========

Frequently asked questions for machine learning are collected and record in:

- :doc:`Common Q&A </sw/yocto/ml-guide/ml-common-qa>`.

Appendix
========

.. _ml_hw-devices:

Hardware Devices
****************

GPU
^^^

The GPU provides neural network acceleration for floating point models.

- ARM-based platforms could support GPU neural network acceleration via Arm NN and the Arm Compute Library.

- Non-ARM platforms could support GPU neural network acceleration via Google’s TensorFlow Lite GPU delegate. 
  This GPU delegate can accelerate a wide selection of TFLite operations.

.. note::

    On |IOT-YOCTO|, we support both of the above GPU neural network accelerations.

VPU
^^^

The Vision Processing Unit (VPU) offers general-purpose Digital Signal Processing (DSP) capabilities, 
with special hardware for accelerating complex imaging and computer vision algorithms. The VPU also offers outstanding performance while running AI models.

MDLA
^^^^

The MediaTek Deep Learning Accelerator (MDLA) is a powerful and efficient Convolutional Neural Network (CNN) accelerator. The MDLA is capable of achieving high 
AI benchmark results with high Multiply-Accumulate (MAC) utilization rates. The design integrates MAC units with dedicated function blocks, which handle activation 
functions, element-wise operations, and pooling layers.