mindspore.ops.soft_shrink

mindspore.ops.soft_shrink(x, lambd=0.5)[source]

Applies the SoftShrink function element-wise.

\[\begin{split}\text{SoftShrink}(x) = \begin{cases} x - \lambda, & \text{ if } x > \lambda \\ x + \lambda, & \text{ if } x < -\lambda \\ 0, & \text{ otherwise } \end{cases}\end{split}\]
Parameters
  • x (Tensor) – The input of soft shrink with data type of float16 or float32.

  • lambd (float) – The \(\lambda\) must be no less than zero. Default: 0.5.

Returns

Tensor, has the same shape and data type as x.

Raises
  • TypeError – If lambd is not a float.

  • TypeError – If input_x is not a Tensor.

  • TypeError – If dtype of input_x is neither float16 nor float32.

  • ValueError – If lambd is less than 0.

Supported Platforms:

Ascend CPU GPU

Examples

>>> from mindspore import Tensor
>>> from mindspore import ops
>>> import numpy as np
>>> x = Tensor(np.array([[ 0.5297,  0.7871,  1.1754], [ 0.7836,  0.6218, -1.1542]]), mindspore.float32)
>>> output = ops.soft_shrink(x)
>>> print(output)
[[ 0.02979  0.287    0.676  ]
 [ 0.2837   0.1216  -0.6543 ]]