mindspore.nn.GELU

class mindspore.nn.GELU(approximate=True)

Gaussian error linear unit activation function.

Applies GELU function to each element of the input. The input is a Tensor with any valid shape.

GELU is defined as:

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

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

The picture about GELU looks like this GELU.

Parameters

approximate (bool) –

Whether to enable approximation. Default: True.

If approximate is True, The gaussian error linear activation is:

$0.5\ast x\ast (1+tanh(sqrt(2/pi)\ast (x+0.044715\ast x^3)))$

else, it is:

$x\ast P(X<=x)=0.5\ast x\ast (1+erf(x/sqrt(2)))$, where P(X) ~ N(0, 1).

Inputs:

• x (Tensor) - The input of GELU with data type of float16 or float32. The shape is $(N,\ast )$ where $\ast$ means, any number of additional dimensions.

Outputs:

Tensor, with the same type and shape as the x.

Raises

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

Supported Platforms:

Ascend GPU CPU

Examples

>>> x = Tensor(np.array([[-1.0, 4.0, -8.0], [2.0, -5.0, 9.0]]), mindspore.float32)
>>> gelu = nn.GELU()
>>> output = gelu(x)
>>> print(output)
[[-1.5880802e-01  3.9999299e+00 -3.1077917e-21]
 [ 1.9545976e+00 -2.2918017e-07  9.0000000e+00]]
>>> gelu = nn.GELU(approximate=False)
>>> # CPU not support "approximate=False", using "approximate=True" instead
>>> output = gelu(x)
>>> print(output)
[[-1.5865526e-01  3.9998732e+00 -0.0000000e+00]
 [ 1.9544997e+00 -1.4901161e-06  9.0000000e+00]]