mindspore.nn.SmoothL1Loss

class mindspore.nn.SmoothL1Loss(beta=1.0, reduction='none')[source]

SmoothL1 loss function, if the absolute error element-wise between the predicted value and the target value is less than the set threshold beta, the square term is used, otherwise the absolute error term is used.

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

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

Where \({\beta}\) represents the threshold beta.

If reduction is not none, then:

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

Note

For Ascend platform, the float64 data type of logits is not support now. SmoothL1Loss can be regarded as modified version of L1Loss or a combination of L1Loss and L2Loss. L1Loss computes the element-wise absolute difference between two input tensors while L2Loss computes the squared difference between two input tensors. L2Loss often leads to faster convergence but it is less robust to outliers, and the loss function has better robustness.

Parameters
  • beta (float) – The loss function calculates the threshold of the transformation between L1Loss and L2Loss. Default: 1.0.

  • reduction (str) – Type of reduction to be applied to loss. The optional values are “mean”, “sum”, and “none”. Default: “none”.

Inputs:
  • logits (Tensor) - Predictive value. Tensor of any dimension. Data type must be one of float16, float32 and float64.

  • labels (Tensor) - Ground truth data, same shape and dtype as the logits.

Outputs:

Tensor, if reduction is ‘none’, then output is a tensor with the same shape as logits. 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 logits or labels are not Tensor.

  • TypeError – If dtype of logits or labels is neither float16 not float32.

  • TypeError – If dtype of logits is not the same as labels.

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

  • ValueError – If shape of logits is not the same as labels.

  • TypeError – The float64 data type of logits is support on Ascend platform.

Supported Platforms:

Ascend GPU CPU

Examples

>>> loss = nn.SmoothL1Loss()
>>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
>>> labels = Tensor(np.array([1, 2, 2]), mindspore.float32)
>>> output = loss(logits, labels)
>>> print(output)
[0.  0.  0.5]