mindspore.ops.HShrink

class mindspore.ops.HShrink(lambd=0.5)

Applies the hard shrinkage function element-wise, each element complies with the following function:

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

Parameters

lambd (float) – The value for the HardShrink formulation. Default: 0.5

Inputs:

• input_x (Tensor) - The input of HardShrink with data type of float16 or float32.

Outputs:

Tensor, the same shape and data type as the input.

Supported Platforms:

Ascend

Raises

• TypeError – If lambd is not a float.

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

Examples

>>> import mindspore as ms
>>> import mindspore.ops as ops
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> input_x = Tensor(np.array([[0.5,  1,  2.0], [0.0533, 0.0776, -2.1233]]), ms.float32)
>>> hshrink = ops.HShrink()
>>> output = hshrink(input_x)
>>> print(output)
[[ 0.      1.      2.    ]
[ 0.      0.     -2.1233]]