emmi.modules.encoder.mlp_encoder
================================

.. py:module:: emmi.modules.encoder.mlp_encoder


Classes
-------

.. autoapisummary::

   emmi.modules.encoder.mlp_encoder.MlpEncoder


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

.. py:class:: MlpEncoder(input_dim, hidden_dim, init_weights='truncnormal002')

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


   A 2-layer MLP encoder. Can be use to encode (i.e., embed) the input data.

   Initialize the MlpEncoder.

   :param input_dim: Number of dimensions of the input tensor.
   :param hidden_dim: Hidden dimensionality of the network.
   :param init_weights: Initialization method for the weight matrixes of the linear layers. Defaults to "truncnormal002".


   .. py:attribute:: layer


   .. py:method:: forward(x)

      Forward method of the MlpEncoder.

      :param x: Tensor of input data.

      :returns: Embedded/encoded tensor.