Skip to main content

ClikaRT::ops::nll_loss

function

nll_loss()​

Tensor nll_loss(
    Tensor input,
    Tensor target,
    OptionalTensor weight = {},
    std::optional<int64_t> ignore_index = std::nullopt,
    Reduction reduction = Reduction::Mean
)

Negative-log-likelihood loss over LOG-probabilities; class dim LAST.

ℓ=−xy\ell = -x_{y}

input is expected to already be log-probabilities (pair with log_softmax; cross_entropy is the fused form).

Parameters

  • input: log-probabilities [.., C].
  • target: class indices [..] (integer dtype).
  • weight: optional per-class weight [C].
  • ignore_index: optional target value whose positions contribute no loss; absent = no masking.
  • reduction: None / Mean / Sum; default Mean.

Returns: the loss (0-D under Mean/Sum; [..] under None).

Throws

  • ClikaRT::Error: (INVALID_ARGUMENT) when target's shape is not input's minus the class axis, or a target index is out of range.

Declared in ClikaRT/compute/ops.h, line 3018