minerva.models.nets.lfr_har_architectures
=========================================

.. py:module:: minerva.models.nets.lfr_har_architectures


Classes
-------

.. autoapisummary::

   minerva.models.nets.lfr_har_architectures.HARSCnnEncoder
   minerva.models.nets.lfr_har_architectures.LFR_HAR_Predictor
   minerva.models.nets.lfr_har_architectures.LFR_HAR_Predictor_List
   minerva.models.nets.lfr_har_architectures.LFR_HAR_Projector
   minerva.models.nets.lfr_har_architectures.LFR_HAR_Projector_List


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

.. py:class:: HARSCnnEncoder(dim = 128, input_channel = 9, inner_conv_output_dim = 128 * 18, permute = False)

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


   A convolutional encoder used with the LFR technique, adapted from
   https://github.com/layer6ai-labs/lfr/blob/main/ssl_models/models/encoders.py
   to work with our HAR dataset.

   Parameters
   ----------
   dim : int
       The dimension of the latent space, by default 128.
   input_channel : int
       The number of input channels, by default 9. In the LFR paper, the shape of
       the input data was (batch, 9, 128), which required an input_channel value
       of 9. However, for data in the shape (batch, 6, 60), a value of 6 is required.
   inner_conv_output_dim : int
       The output dimension of the inner convolutional layers, by default 128*18.
       In the LFR paper, the shape of the input data was (batch, 9, 128), which
       required an inner_conv_output_dim value of 128*18. However, for data in the
       shape (batch, 6, 60), a value of 128*10 is required.


   .. py:attribute:: conv


   .. py:method:: forward(xb)


   .. py:attribute:: permute
      :value: False



.. py:class:: LFR_HAR_Predictor(encoding_size, middle_dim, num_layers)

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


   A predictor module for LFR in HAR tasks that maps latent embeddings to a randomly
   projected data representation.

   Initializes a predictor module.

   Parameters
   ----------
   encoding_size: int
       The input and output dimensionality of the predictor module.
   middle_dim: int
       Dimensionality of the hidden layers in the predictor.
   num_layers: int
       Number of layers in the predictor. If set to 1, the predictor becomes a single
       linear layer and 'middle_dim' is ignored.


   .. py:method:: forward(z)


.. py:class:: LFR_HAR_Predictor_List(size, encoding_size, middle_dim, num_layers)

   Bases: :py:obj:`minerva.models.ssl.lfr.RepeatedModuleList`


   A repeated list of predictor modules for LFR in HAR tasks. Each predictor maps latent
   embeddings to a randomly projected data representation.

   Initializes a list of predictor modules.

   Parameters
   ----------
   size: int
       Number of predictor modules to instantiate in the list.
   encoding_size: int
       The input and output dimensionality of each predictor module.
   middle_dim: int
       Dimensionality of the hidden layers in each predictor.
   num_layers: int
       Number of layers in each predictor. If set to 1, the predictors become single
       linear layers and 'middle_dim' is ignored.


.. py:class:: LFR_HAR_Projector(encoding_size = 512, input_channel = 9, middle_dim = 1088)

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


   A projector module for LFR in HAR tasks that projects the input data into a random
   latent space.

   Initializes a projector module.

   Parameters
   ----------
   encoding_size: int
       The output dimensionality of the projector module.
   input_channel: int
       The number of channels in the input data.
   middle_dim: int
       The expected dimensionality after the convolution module, by default 1088. The
       original paper, where the input has 9 channels and 128 timestamps, requires 1088.
       For data with 6 channels and 60 timestamps, 544 should be used.


   .. py:attribute:: conv


   .. py:method:: forward(x)


   .. py:attribute:: mlp


.. py:class:: LFR_HAR_Projector_List(size, encoding_size, input_channel, middle_dim)

   Bases: :py:obj:`minerva.models.ssl.lfr.RepeatedModuleList`


   A repeated list of projector modules for LFR in HAR tasks. Each one projects the
   input data into a random latent space.

   Initializes a list of projector modules.

   Parameters
   ----------
   size: int
       Number of projector modules to instantiate in the list.
   encoding_size: int
       The output dimensionality of each projector module.
   input_channel: int
       The number of channels in the input data.