.. _Backend:

###############
Using ENOT Lite
###############

**ENOT Lite** provides a unified interface for running neural network inference with various technologies.

To run neural network inference using **ENOT Lite** all you need to do is:

#. Create :class:`~enot_lite.backend.backend.Backend` instance by using
   :func:`~enot_lite.backend.backend_factory.BackendFactory.create` method of
   :class:`~enot_lite.backend.backend_factory.BackendFactory`.

#. Pass your input data into created :class:`~enot_lite.backend.backend.Backend` instance by using
   :func:`~enot_lite.backend.backend.Backend.__call__` method to obtain prediction.

Here is an example which fully covers the basic usage of **ENOT Lite**:

.. code-block::
    :linenos:

    from enot_lite.backend import BackendFactory
    from enot_lite.type import BackendType

    backend = BackendFactory().create('path/to/model.onnx', BackendType.ORT_CPU)
    prediction = backend(inputs)

* At line **1** in example above we import :class:`~enot_lite.backend.backend_factory.BackendFactory` which will be
  used to create an instance of :class:`~enot_lite.backend.backend.Backend`.
* At line **2** we import :class:`~enot_lite.type.internal.BackendType` which allows to easily choose among various
  backends.
* At line **4** we create :class:`~enot_lite.backend.backend.Backend` instance by using
  :func:`~enot_lite.backend.backend_factory.BackendFactory.create` method of
  :class:`~enot_lite.backend.backend_factory.BackendFactory`.
  Created ``backend`` is a wrap for your model which provides an easy-to-use interface for inference.
* And finally, at line **5** inference is done by passing ``inputs`` (it can be images, text or something else)
  into ``backend`` and the results are stored in ``prediction`` variable.

:class:`~enot_lite.type.internal.BackendType` allows you to choose among various inference technologies,
so you don't need to do anything special, just create :class:`~enot_lite.backend.backend.Backend` instance by
:class:`~enot_lite.backend.backend_factory.BackendFactory` and use it for inference.

To refine :class:`~enot_lite.backend.backend.Backend` setting, see :class:`~enot_lite.type.internal.BackendType`,
:class:`~enot_lite.type.interface.ModelType`.


.. autoclass:: enot_lite.type.BackendType
    :members:

.. autoclass:: enot_lite.type.ModelType
    :members:

.. autoclass:: enot_lite.type.Device
    :members:

.. autoclass:: enot_lite.backend.backend_factory.BackendFactory
    :members: create

.. autoclass:: enot_lite.backend.backend.Backend
    :members: __call__