mindspore.ops.gelu

mindspore.ops.gelu(input_x, approximate='none')

Gaussian Error Linear Units activation function.

GeLU is described in the paper Gaussian Error Linear Units (GELUs). And also please refer to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

When approximate argument is none, GeLU is defined as follows:

$$GELU(x_i)=x_i\ast P(X<x_i),$$

where $P$ is the cumulative distribution function of the standard Gaussian distribution, $x_i$ is the input element.

When approximate argument is tanh, GeLU is estimated with:

$$GELU(x_i)=0.5\ast x_i\ast (1+tanh(\sqrt{(}2/\pi )\ast (x_i+0.044715\ast x_i^3)))$$

Parameters

• input_x (Tensor) – The input of the activation function GeLU, the data type is float16, float32 or float64.

• approximate (str) – the gelu approximation algorithm to use. Acceptable vaslues are ‘none’ and ‘tanh’. Default: ‘none’.

Returns

Tensor, with the same type and shape as input_x.

Raises

• TypeError – If input_x is not a Tensor.

• TypeError – If dtype of input_x is not float16, float32 or float64.

• ValueError – If approximate value is neither none or tanh.

Supported Platforms:

Ascend GPU CPU

Examples

>>> x = Tensor([1.0, 2.0, 3.0], mindspore.float32)
>>> result = ops.gelu(x)
>>> print(result)
[0.841192 1.9545976 2.9963627]