Table Of Contents
Table Of Contents

smooth_l1

mxnet.ndarray.smooth_l1(data=None, scalar=_Null, out=None, name=None, **kwargs)

Calculate Smooth L1 Loss(lhs, scalar) by summing

\[\begin{split}f(x) = \begin{cases} (\sigma x)^2/2,& \text{if }x < 1/\sigma^2\\ |x|-0.5/\sigma^2,& \text{otherwise} \end{cases}\end{split}\]

where \(x\) is an element of the tensor lhs and \(\sigma\) is the scalar.

Example:

smooth_l1([1, 2, 3, 4], scalar=1) = [0.5, 1.5, 2.5, 3.5]

Defined in src/operator/tensor/elemwise_binary_scalar_op_extended.cc:L103

Parameters:
  • data (NDArray) – source input
  • scalar (float) – scalar input
  • out (NDArray, optional) – The output NDArray to hold the result.
Returns:

out – The output of this function.

Return type:

NDArray or list of NDArrays