probly.train.evidential.torch.make_in_domain_target_alpha¶

probly.train.evidential.torch.make_in_domain_target_alpha(y: Tensor) → Tensor[source]¶

Construct target Dirichlet distribution for in-distribution samples.

Used by Dirichlet Prior Networks, Posterior Networks, and PN-style paired losses to create a sharp (peaked) Dirichlet target for supervised in-distribution training.

Parameters:: y – Ground-truth class labels, shape (B,).
Returns:: Target Dirichlet concentration parameters, shape (B, C).