Creates a criterion that uses a squared term if the absolute
element-wise error falls below 1 and an L1 term otherwise.
It is less sensitive to outliers than the MSELoss
and in some cases
prevents exploding gradients (e.g. see Fast R-CNN
paper by Ross Girshick).
Also known as the Huber loss:
Arguments
- reduction
(string, optional): Specifies the reduction to apply to the output:
'none'
| 'mean'
| 'sum'
. 'none'
: no reduction will be applied,
'mean'
: the sum of the output will be divided by the number of
elements in the output, 'sum'
: the output will be summed.
Details
where is given by:
and arbitrary shapes with a total of elements each
the sum operation still operates over all the elements, and divides by .
The division by can be avoided if sets reduction = 'sum'
.
Shape
Input: where means, any number of additional
dimensions
Target: , same shape as the input
Output: scalar. If reduction
is 'none'
, then
, same shape as the input