mlx.nn.losses.smooth_l1_loss#
- class smooth_l1_loss(predictions: array, targets: array, beta: float = 1.0, reduction: Literal['none', 'mean', 'sum'] = 'mean')#
Computes the smooth L1 loss.
The smooth L1 loss is a variant of the L1 loss which replaces the absolute difference with a squared difference when the absolute difference is less than
beta.The formula for the smooth L1 Loss is:
\[\begin{split}l = \begin{cases} 0.5 (x - y)^2, & \text{if } (x - y) < \beta \\ |x - y| - 0.5 \beta, & \text{otherwise} \end{cases}\end{split}\]- Parameters:
predictions (array) – Predicted values.
targets (array) – Ground truth values.
beta (float, optional) – The threshold after which the loss changes from the squared to the absolute difference. Default:
1.0.reduction (str, optional) – Specifies the reduction to apply to the output:
'none'|'mean'|'sum'. Default:'mean'.
- Returns:
The computed smooth L1 loss.
- Return type: