xlnstorch.operators.lns_nll_loss

xlnstorch.operators.lns_nll_loss(x, y, base, weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean')

See docs for torch.nn.functional.nll_loss() for parameter/return details. Typically, torch.Tensor arguments are the equivalent internal representations of LNStensors.

Parameters:

• x (Tensor)

• y (Tensor)

• base (Tensor)

• weight (Tensor)

• size_average (bool)

• ignore_index (int)

• reduce (bool)

• reduction (str)

Return type:

Tensor