emmi_inference.models.modules.continuous_sincos_embed
=====================================================

.. py:module:: emmi_inference.models.modules.continuous_sincos_embed


Classes
-------

.. autoapisummary::

   emmi_inference.models.modules.continuous_sincos_embed.ContinuousSincosEmbed


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

.. py:class:: ContinuousSincosEmbed(dim, ndim, max_wavelength = 10000, assert_positive = True)

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


   Embedding layer for continuous coordinates using sine and cosine functions as used in transformers.
   This implementation is able to deal with arbitrary coordinate dimensions (e.g., 2D and 3D coordinate systems).

   :param dim: Dimensionality of the embedded input coordinates.
   :param ndim: 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.

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


   .. py:attribute:: dim


   .. py:attribute:: ndim


   .. py:attribute:: ndim_padding


   .. py:attribute:: sincos_padding


   .. py:attribute:: max_wavelength
      :value: 10000



   .. py:attribute:: padding


   .. py:attribute:: assert_positive
      :value: True



   .. 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).

      :returns: Tensor with embedded coordinates.