*DIRESA* - distance-regularized Siamese twin autoencoder
========================================================
 
*DIRESA* is a Python package for dimension reduction based on TensorFlow_.
The distance-regularized Siamese twin autoencoder architecture is designed
to preserve distance (ordering) in latent space while capturing the non-linearities in
the datasets.

.. _TensorFlow: https://www.tensorflow.org

**Introduction**

* :doc:`architecture`
* :doc:`install`

.. toctree::
   :maxdepth: 1
   :caption: Introduction:
   :hidden:
   
   architecture
   install
   
**Tutorial**
 
* :doc:`start`
* :doc:`build`
* :doc:`eval`
* :doc:`conv2D`
* :doc:`custom`

.. toctree::
   :maxdepth: 1
   :caption: Tutorial:
   :hidden:
   
   start
   build
   eval
   conv2D
   custom
   
**Module reference**

* :doc:`models`
* :doc:`loss`
* :doc:`callback`
* :doc:`tool`

.. toctree::
   :maxdepth: 1
   :caption: Module reference:
   :hidden:
   
   models
   loss
   callback
   tool
