Skip to content

sum

Composite loss: sum of several (logits, target) losses.

Classes:

  • SumLoss –

    Sum of several loss modules sharing a (logits, target) signature.

SumLoss 

SumLoss(losses: Sequence[Module])

Bases: Module

Sum of several loss modules sharing a (logits, target) signature.

Each sub-loss is evaluated on the same inputs and the results are added (e.g. cross-entropy plus Lovász). Apply per-loss weights through each module's own option (e.g. LovaszLoss(loss_weight=...)).

Parameters:

  • losses (Sequence[Module]) –

    The loss modules to sum.

Methods:

  • forward –

    Compute the summed loss over all sub-losses.

forward 

forward(logits: Tensor, target: Tensor) -> Tensor

Compute the summed loss over all sub-losses.