tf.nn.gelu

Compute the Gaussian Error Linear Unit (GELU) activation function.

tf.nn.gelu(
    features, approximate=False, name=None
)

Gaussian error linear unit (GELU) computes x * P(X <= x), where P(X) ~ N(0, 1). The (GELU) nonlinearity weights inputs by their value, rather than gates inputs by their sign as in ReLU.

For example:

x = tf.constant([-3.0, -1.0, 0.0, 1.0, 3.0], dtype=tf.float32)
y = tf.nn.gelu(x)
y.numpy()
array([-0.00404951, -0.15865529,  0.        ,  0.8413447 ,  2.9959507 ],
    dtype=float32)
y = tf.nn.gelu(x, approximate=True)
y.numpy()
array([-0.00363752, -0.15880796,  0.        ,  0.841192  ,  2.9963627 ],
    dtype=float32)

features A Tensor representing preactivation values.
approximate An optional bool. Defaults to False. Whether to enable approximation.
name A name for the operation (optional).

A Tensor with the same type as features.

References:

Gaussian Error Linear Units (GELUs).