mindspore.ops.fast_gelu

mindspore.ops.fast_gelu(x)[source]

Fast Gaussian Error Linear Units activation function.

FastGeLU is defined as follows:

\[\text{output} = \frac {x} {1 + \exp(-1.702 * \left| x \right|)} * \exp(0.851 * (x - \left| x \right|)),\]

where \(x\) is the element of the input.

FastGelu function graph:

../../_images/FastGelu.png
Parameters

x (Tensor) – Input to compute the FastGeLU with data type of float16 or float32.

Returns

Tensor, with the same type and shape as x.

Raises

TypeError – If dtype of x is neither float16 nor float32.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([[-1.0, 4.0, -8.0], [2.0, -5.0, 9.0]]), mindspore.float32)
>>> output = ops.fast_gelu(x)
>>> print(output)
[[-1.5418735e-01  3.9921875e+00 -9.7473649e-06]
[ 1.9375000e+00 -1.0052517e-03  8.9824219e+00]]