mindspore.ops.hardswish

mindspore.ops.hardswish(x)[source]

Applies hswish-type activation element-wise. The input is a Tensor with any valid shape.

Hard swish is defined as:

\[\text{hswish}(x_{i}) = x_{i} * \frac{ReLU6(x_{i} + 3)}{6}\]

where \(x_i\) is an element of the input Tensor.

Parameters

x (Tensor) – The input to compute the Hard Swish.

Returns

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

Raises

TypeError – If x is not a Tensor.
TypeError – If dtype of x is not int or float.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([-1, -2, 0, 2, 1]), mindspore.float16)
>>> output = ops.hardswish(x)
>>> print(output)
[-0.3333  -0.3333  0  1.666  0.6665]