mdlearn.nn.modules.linear_discriminator

Classes

LinearDiscriminator(*args, **kwargs)

class mdlearn.nn.modules.linear_discriminator.LinearDiscriminator(*args: Any, **kwargs: Any)
__init__(latent_dim: int = 20, bias: bool = True, relu_slope: float = 0.0, affine_widths: List[int] = [512, 128, 64])

LinearDiscriminator module.

Parameters

  • 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(x: torch.Tensor)