Aidge
=====

:Release: |version|
:Date: |today|



.. grid:: 1 2 2 3
    :margin: 4 4 0 0
    :gutter: 1

    .. grid-item-card:: :octicon:`desktop-download` Install
        :link: source/GetStarted/install
        :link-type: doc

        Find your configuration and requirements.

    .. grid-item-card:: :octicon:`table` Quick Start
        :link: source/GetStarted/quickStart
        :link-type: doc

        Build, train and deploy your first network.

    .. grid-item-card:: :octicon:`checklist` User Guide
        :link: source/UserGuide/index
        :link-type: doc

        The main hub for detailed usage explanations.

    .. grid-item-card:: :octicon:`book` API Reference
        :link: source/API/index
        :link-type: doc

        Details every module, class and function.

    .. grid-item-card:: :octicon:`light-bulb` Tutorials
        :link: source/Tutorial/index
        :link-type: doc

        Learn by seeing.
    
    .. grid-item-card:: :octicon:`comment` Exchange forum
        :link: https://gitlab.eclipse.org/groups/eclipse/aidge/-/issues

        Exchange with the team and other users over features.

What is Aidge?
--------------

.. |Aidge| image:: /source/_static/Logotype-aidge.png
   :scale: 2%

|Aidge| is an open-source deep learning platform specialized in the design of deep neural networks intended to operate in systems constrained by power consumption or dissipation, latency, form factor (dimensions, size, etc.), and/or cost criteria.

Aidge's eventual ambition is to offer:

* an integrated approach encompassing the entire design flow, from application development to deployment: data formatting, neural network exploration, learning, testing, and optimized code generation;
* several functions to reduce the computational complexity of models and their memory requirements, most often using quantization (during or after training) and topological optimization techniques;
* compatibility with a wide range of commercially available hardware targets, offering optimized implementations for MCUs and DSPs, GPUs, FPGAs or NPUs;
* a modular design and simple abstraction layer, so features can be added and modified with ease, including the low-level implementation of calculation functions depending on the specific characteristics of the hardware being deployed (approximate calculation, specific saturated arithmetic, etc.);
* a high degree of interoperability, with support for the ONNX standard and integration with the PyTorch and Keras platforms;
* a multiparadigm approach that integrates the simulation of neuromorphic neural network models into the same platform;
* sovereignty and control of the code, as Aidge is independent of other deep learning platforms.

For more detailed technical insights into some interesting Aidge's features, please have a look to :ref:`Why Aidge? <source/GetStarted/whyAidge:Why Aidge?>`.

License
-------

Aidge is released under the Eclipse Public License 2.0


.. toctree::
    :maxdepth: 1
    :hidden:
    
    source/GetStarted/index.rst
    source/UserGuide/index.rst
    source/Tutorial/index.rst
    source/API/index.rst