torch.nn.functional.smooth_l1_loss

torch.nn.functional.smooth_l1_loss(input, target, size_average=None, reduce=None, reduction='mean', beta=1.0)

Compute the Smooth L1 loss.

Function uses a squared term if the absolute element-wise error falls below beta and an L1 term otherwise.

See SmoothL1Loss for details.

Return type

Tensor