emmi.modules.layers.continuous_sincos_embed
===========================================

.. py:module:: emmi.modules.layers.continuous_sincos_embed


Classes
-------

.. autoapisummary::

   emmi.modules.layers.continuous_sincos_embed.ContinuousSincosEmbed


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

.. py:class:: ContinuousSincosEmbed(config)

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


   Embedding layer for continuous coordinates using sine and cosine functions.
   The original implementation from the Attenion is All You Need paper, deals with descrete 1D cordinates (i.e., a sequence).
   Howerver, this implementation is able to deal with 2D and 3D coordinate systems as well.


   Initialize the ContinuousSincosEmbed layer.

   :param hidden_dim: Dimensionality of the embedded input coordinates.
   :param input_dim: Number of dimensions of the input domain.
   :param max_wavelength: Max length. Defaults to 10000.
   :param assert_positive: If true, assert if all input coordiantes are positive. Defaults to True.


   .. py:attribute:: hidden_dim


   .. py:attribute:: input_dim


   .. py:attribute:: ndim_padding


   .. py:attribute:: sincos_padding


   .. py:attribute:: max_wavelength


   .. py:attribute:: padding


   .. py:attribute:: assert_positive


   .. py:method:: forward(coords)

      Forward method of the ContinuousSincosEmbed layer.

      :param coords: Tensor of coordinates. The shape of the tensor should be [batch size, number of points, coordinate dimension] or [number of points, coordinate dimension].

      :raises NotImplementedError: Only supports sparse (i.e. [number of points, coordinate dimension]) or dense (i.e. [batch size, number of points, coordinate dimension]) coordinates systems.

      :returns: Tensor with embedded coordinates.