mindspore.ops.hardswish

mindspore.ops.hardswish(x)

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

Hard swish is defined as:

$$\text{hswish}(x_i)=x_i\ast \frac{ReLU6(x_i+3)}{6}$$

where $x_i$ is an element of the input Tensor.

HSwish Activation Function Graph:

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]