# tensorplay.nn.functional.smooth_l1_loss

Source: https://www.tensorplay.cn/docs/generated/tensorplay.nn.functional.smooth_l1_loss.html

# tensorplay.nn.functional.smooth_l1_loss

tensorplay.nn.functional.smooth_l1_loss(input: TensorBase, target: TensorBase, size_average=None, reduce=None, reduction: [str](https://docs.python.org/3/library/stdtypes.html#str) = 'mean', beta: [float](https://docs.python.org/3/library/functions.html#float) = 1.0) → TensorBase[[source]](../_modules/tensorplay/nn/functional.html#smooth_l1_loss)

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.