LPBNNLinear#
- class torch_uncertainty.layers.bayesian.LPBNNLinear(in_features, out_features, num_estimators, hidden_size=32, std_factor=0.01, bias=True, device=None, dtype=None)[source]#
LPBNN-style linear layer.
- Parameters:
in_features (int) – Number of input features.
out_features (int) – Number of output features.
num_estimators (int) – Number of models to sample from.
hidden_size (int) – Size of the hidden layer. Defaults to
32
.std_factor (float) – Factor to multiply the standard deviation of the latent noise. Defaults to
1e-2
.bias (bool) – If
True
, adds a learnable bias to the output. Defaults toTrue
.device (torch.device) – Device on which the layer is stored. Defaults to
None
.dtype (torch.dtype) – Data type of the layer. Defaults to
None
.
References
[1] Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification.