Skip to main content

KLDivLoss

KLDivLoss(reduction="mean", log_target=False)

Kullback-Leibler divergence of target from input, where input holds log-probabilities.

The module form of clika_runtime.nn.functional.kl_div: construct it once with the settings, then call it like a function.

Args: reduction: how the elementwise losses reduce. log_target: reads target as log-probabilities.

__init__​

__init__(self, reduction: '_Reduction' = 'mean', log_target: 'bool' = False) -> 'None'

Initialize self. See help(type(self)) for accurate signature.

extra_repr​

extra_repr(self) -> 'str'

extra_repr() -> str

One line of per-class detail for :meth:__repr__; a layer prints its geometry here (in_features=64, out_features=256).

forward​

forward(self, input: 'Tensor', target: 'Tensor') -> 'Tensor'

forward(input, target) -> Tensor

Runs clika_runtime.nn.functional.kl_div on input, target with the stored settings; returns a new tensor.