emmi.modules.layers.continuous_sincos_embed¶

Classes¶

ContinuousSincosEmbed

Embedding layer for continuous coordinates using sine and cosine functions.

Module Contents¶

class emmi.modules.layers.continuous_sincos_embed.ContinuousSincosEmbed(config)¶

Bases: 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.

Parameters:

hidden_dim – Dimensionality of the embedded input coordinates.
input_dim – Number of dimensions of the input domain.
max_wavelength – Max length. Defaults to 10000.
assert_positive – If true, assert if all input coordiantes are positive. Defaults to True.
config (emmi.schemas.modules.layers.ContinuousSincosEmbeddingConfig)

hidden_dim¶

input_dim¶

ndim_padding¶

sincos_padding¶

max_wavelength¶

padding¶

assert_positive¶

forward(coords)¶

Forward method of the ContinuousSincosEmbed layer.

Parameters:: coords (torch.Tensor) – 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.
Return type:: torch.Tensor