xlnstorch.operators.lns_huber_loss

xlnstorch.operators.lns_huber_loss(x, y, delta, base, reduction='mean', weight=None)

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

Parameters:

• x (Tensor)

• y (Tensor)

• delta (Tensor)

• base (Tensor)

• reduction (str)

• weight (Tensor)

Return type:

Tensor