hyrax.models.hyrax_autoencoder
==============================

.. py:module:: hyrax.models.hyrax_autoencoder


Attributes
----------

.. autoapisummary::

   hyrax.models.hyrax_autoencoder.logger


Classes
-------

.. autoapisummary::

   hyrax.models.hyrax_autoencoder.HyraxAutoencoder


Module Contents
---------------

.. py:data:: logger

.. py:class:: HyraxAutoencoder(config, data_sample=None)

   Bases: :py:obj:`torch.nn.Module`


   This autoencoder is designed to work with a wide range of image datasets to allow testing.

   This example model is taken from this
   `autoenocoder tutorial <https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial9/AE_CIFAR10.html>`_

   The train function has been converted into train_batch for use with pytorch-ignite.

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: config


   .. py:attribute:: c_hid


   .. py:attribute:: latent_dim


   .. py:attribute:: conv_end_w


   .. py:attribute:: conv_end_h


   .. py:method:: conv2d_multi_layer(input_size, num_applications, **kwargs) -> int


   .. py:method:: conv2d_output_size(input_size, kernel_size, padding=0, stride=1, dilation=1) -> int


   .. py:method:: _init_encoder()


   .. py:method:: _eval_encoder(x)


   .. py:method:: _init_decoder()


   .. py:method:: _eval_decoder(x)


   .. py:method:: forward(batch)


   .. py:method:: train_batch(batch)

      This function contains the logic for a single training step. i.e. the
      contents of the inner loop of a ML training process.

      :param batch: A tuple containing the input data for the current batch, possibly
                    with labels that are ignored.
      :type batch: tuple

      :returns: **Current loss value** -- Dictionary containing the loss value for the current batch.
      :rtype: dict



   .. py:method:: validate_batch(batch)

      This function contains the logic for a single validation step that will
      process a single batch of data. i.e. the contents of the inner loop of a
      ML validation process.

      :param batch: A tuple containing the input data for the current batch, possibly
                    with labels that are ignored.
      :type batch: tuple

      :returns: **Current loss value** -- Dictionary containing the loss value for the current batch.
      :rtype: dict



   .. py:method:: test_batch(batch)

      This function contains the logic for a single testing step that will
      process a single batch of data. i.e. the contents of the inner loop of a
      ML testing process. In this case, it is identical to `validate_batch`.

      :param batch: A tuple containing the input data for the current batch, possibly
                    with labels that are ignored.
      :type batch: tuple

      :returns: **Current loss value** -- Dictionary containing the loss value for the current batch.
      :rtype: dict



   .. py:method:: infer_batch(batch)

      This function contains the logic for a single inference step. i.e. the
      contents of the inner loop of a ML inference process.

      :param batch: A tuple containing the input data for the current batch, possibly
                    with labels that are ignored.
      :type batch: tuple

      :returns: **Reconstructed inputs** -- The reconstructed inputs from the autoencoder.
      :rtype: torch.Tensor



   .. py:method:: prepare_inputs(data_dict) -> tuple
      :staticmethod:


      This function converts structured data to the input tensor we need to run

      :param data_dict: The dictionary returned from our data source
      :type data_dict: dict



   .. py:method:: _optimizer()