mindspore.ops.SmoothL1Loss

View Source On Gitee
class mindspore.ops.SmoothL1Loss(beta=1.0, reduction='none')[source]

Calculate the smooth L1 loss, and the L1 loss function has robustness.

Refer to mindspore.ops.smooth_l1_loss() for more details.

Parameters

  • beta (float, optional) – 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, optional) –

    Apply specific reduction method to the output: 'none' , 'mean' , 'sum' . Default: 'none' .

    • 'none': no reduction will be applied.

    • 'mean': compute and return the mean of elements in the output.

    • 'sum': the output elements will be summed.

Inputs:

  • logits (Tensor) - Input Tensor of any dimension. Data type must be float16, float32 or float64.

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

Outputs:

Tensor, loss float tensor, same shape and dtype as the logits.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> loss = ops.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]