mindspore.ops.smooth_l1_loss

mindspore.ops.smooth_l1_loss(input, target, beta=1.0, reduction='none')[source]

Computes smooth L1 loss, a robust L1 loss.

SmoothL1Loss is a Loss similar to MSELoss but less sensitive to outliers as described in the Fast R-CNN by Ross Girshick.

Given two input \(x,\ y\) of length \(N\), the unreduced SmoothL1Loss can be described as follows:

\[\begin{split}L_{i} = \begin{cases} \frac{0.5 (x_i - y_i)^{2}}{\beta}, & \text{if } |x_i - y_i| < \beta \\ |x_i - y_i| - 0.5 * \beta, & \text{otherwise. } \end{cases}\end{split}\]

If reduction is not none, then:

\[\begin{split}L = \begin{cases} \operatorname{mean}(L_{i}), & \text{if reduction} = \text{'mean';}\\ \operatorname{sum}(L_{i}), & \text{if reduction} = \text{'sum'.} \end{cases}\end{split}\]

Here \(\text{beta}\) controls the point where the loss function changes from quadratic to linear. \(\text{beta}>0\) , its default value is 1.0 . \(N\) is the batch size.

Parameters

  • input (Tensor) – Tensor of shape \((N, *)\) where \(*\) means, any number of additional dimensions.

  • target (Tensor) – Ground truth data, tensor of shape \((N, *)\), same shape and dtype as the input.

  • beta (float) – A parameter used to control the point where the function will change between L1 to L2 loss. The value should be greater than zero. Default: 1.0 .

  • reduction (str) – Apply specific reduction method to the output: 'none' , 'mean' or 'sum' . Default: 'none' .

Returns

Tensor, if reduction is ‘none’, then output is a tensor with the same shape as input. Otherwise, the shape of output tensor is \((1,)\).

Raises

  • TypeError – If beta is not a float.

  • ValueError – If reduction is not one of ‘none’, ‘mean’, ‘sum’.

  • TypeError – If dtype of input or target is not one of float16, float32, float64.

  • ValueError – If beta is less than or equal to 0.

  • ValueError – If shape of input is not the same as target.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
>>> labels = Tensor(np.array([1, 2, 2]), mindspore.float32)
>>> output = ops.smooth_l1_loss(logits, labels)
>>> print(output)
[0.  0.  0.5]