mindspore.Tensor.hardshrink

Tensor.hardshrink(lambd=0.5)[source]

Apply the Hard Shrink function for tensor. Calculates the output according to the input elements.

The formula is defined as follows:

\[\begin{split}\text{HardShrink}(x) = \begin{cases} x, & \text{ if } x > \lambda \\ x, & \text{ if } x < -\lambda \\ 0, & \text{ otherwise } \end{cases}\end{split}\]

Parameters

lambd (float) – The threshold \(\lambda\) defined by the Hard Shrink formula. Default: 0.5.

Returns

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

Raises

TypeError – If lambd is not a float.
TypeError – If dtype of the input tensor is neither float16 nor float32.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import numpy as np
>>> import mindspore as ms
>>> from mindspore import Tensor
>>> x = Tensor(np.array([[0.5,  1,  2.0], [0.0533, 0.0776, -2.1233]]), ms.float32)
>>> print(x.hardshrink())
[[ 0.      1.      2.    ]
[ 0.      0.     -2.1233]]