torch.nn.functional.kl_div

torch.nn.functional.kl_div(input, target, size_average=None, reduce=None, reduction='mean', log_target=False)

The Kullback-Leibler divergence Loss

See KLDivLoss for details.

Parameters

• input – Tensor of arbitrary shape in log-probabilities.

• target – Tensor of the same shape as input. See log_target for the target’s interpretation.

• size_average (bool, optional) – Deprecated (see reduction). By default, the losses are averaged over each loss element in the batch. Note that for some losses, there multiple elements per sample. If the field size_average is set to False, the losses are instead summed for each minibatch. Ignored when reduce is False. Default: True

• reduce (bool, optional) – Deprecated (see reduction). By default, the losses are averaged or summed over observations for each minibatch depending on size_average. When reduce is False, returns a loss per batch element instead and ignores size_average. Default: True

• reduction (string, optional) – Specifies the reduction to apply to the output: 'none' | 'batchmean' | 'sum' | 'mean'. 'none': no reduction will be applied 'batchmean': the sum of the output will be divided by the batchsize 'sum': the output will be summed 'mean': the output will be divided by the number of elements in the output Default: 'mean'

• log_target (bool) – A flag indicating whether target is passed in the log space. It is recommended to pass certain distributions (like softmax) in the log space to avoid numerical issues caused by explicit log. Default: False

Note

size_average and reduce are in the process of being deprecated, and in the meantime, specifying either of those two args will override reduction.

Note

reduction = 'mean' doesn’t return the true kl divergence value, please use reduction = 'batchmean' which aligns with KL math definition. In the next major release, 'mean' will be changed to be the same as ‘batchmean’.