kl_div¶

dragon.vm.torch.nn.functional.kl_div(
  input,
  target,
  size_average=None,
  reduce=None,
  reduction='mean',
  log_target=False
)[source]¶

Compute the Kullback-Leibler divergence.

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.
• target (dragon.vm.torch.Tensor) – The target tensor.
• size_average (bool, optional) – Whether to average the loss.
• reduce (bool, optional) – Whether to reduce the loss.
• reduction ({'none', 'batchmean', 'mean', 'sum'}, optional) – The reduce method.
• log_target (bool, optional, default=False) – The flag indicating whether target is passed in log space.

Returns:

dragon.vm.torch.Tensor – The output tensor.

See also

torch.nn.KLDivLoss(…)