mdlearn.nn.modules.linear_decoder

LinearDecoder module for point cloud data.

Classes

LinearDecoder(*args, **kwargs)

class mdlearn.nn.modules.linear_decoder.LinearDecoder(*args: Any, **kwargs: Any)
__init__(num_points: int, num_features: int = 0, latent_dim: int = 20, bias: bool = True, relu_slope: float = 0.0, affine_widths: List[int] = [64, 128, 512, 1024])

LinearDecoder module for point cloud data.

Parameters

  • num_points (int) – Number of input points in point cloud.

  • num_features (int, optional) – Number of scalar features per point in addition to 3D coordinates, by default 0.

  • latent_dim (int, optional) – Latent dimension of the decoder, by default 20.

  • bias (bool, optional) – Use a bias term in the Linear layers, by default True.

  • relu_slope (float, optional) – If greater than 0.0, will use LeakyReLU activiation with negative_slope set to relu_slope, by default 0.0.

  • affine_widths (List[int], optional) – Linear layers in_features, by default [64, 128, 512, 1024].

forward(z: torch.Tensor) → torch.Tensor