NormalInverseGammaConvNd

class torch_uncertainty.layers.distributions.NormalInverseGammaConvNd(base_layer, event_dim, min_lmbda=1e-06, min_alpha=1e-06, min_beta=1e-06, **layer_args)

Normal-Inverse-Gamma Distribution Convolutional Density Layer.

Parameters:

• base_layer (type[nn.Module]) – The base layer class.

• event_dim (int) – The number of event dimensions.

• min_lmbda (float) – The minimal value of the \(\lambda\) parameter.

• min_alpha (float) – The minimal value of the \(\alpha\) parameter.

• min_beta (float) – The minimal value of the \(\beta\) parameter.

• **layer_args – Additional arguments for the base layer.

Shape:

• Input: \((N, C_{in}, \ast)\) where \(\ast\) means any number of dimensions and \(C_{in} = \text{in_channels}\) and \(N\) is the batch size.

• Output: A dict with the following keys

  • "loc": The mean of the Normal-Inverse-Gamma distribution of shape \((N, C_{out}, \ast)\) where \(C_{out} = \text{out_channels}\).

  • "lmbda": The lambda parameter of the Normal-Inverse-Gamma distribution of shape \((N, C_{out}, \ast)\).

  • "alpha": The alpha parameter of the Normal-Inverse-Gamma distribution of shape \((N, C_{out}, \ast)\).

  • "beta": The beta parameter of the Normal-Inverse-Gamma distribution of shape \((N, C_{out}, \ast)\).

Source:

• Normal-Inverse-Gamma Distribution