mindspore.ops.softshrink

mindspore.ops.softshrink(x, lambd=0.5)

Applies the Softshrink function element-wise.

$$\begin{array}{r}\text{SoftShrink}(x)=\{\begin{array}{ll}x-\lambda ,& \text{ if }x>\lambda \\ x+\lambda ,& \text{ if }x<-\lambda \\ 0,& \text{ otherwise }\end{array}\end{array}$$

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 GPU CPU

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.softshrink(x)
>>> print(output)
[[ 0.02979  0.287    0.676  ]
 [ 0.2837   0.1216  -0.6543 ]]