tf.nn.gelu | TensorFlow v2.16.1 (original) (raw)
tf.nn.gelu
Stay organized with collections Save and categorize content based on your preferences.
Compute the Gaussian Error Linear Unit (GELU) activation function.
tf.nn.gelu(
features, approximate=False, name=None
)
Gaussian error linear unit (GELU) computesx * 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)
| Args | |
|---|---|
| features | A float Tensor representing preactivation values. |
| approximate | An optional bool. Defaults to False. Whether to enable approximation. |
| name | A name for the operation (optional). |
| Returns |
|---|
| A Tensor with the same type as features. |
| Raises | |
|---|---|
| ValueError | if features is not a floating point Tensor. |
| References |
|---|
| Gaussian Error Linear Units (GELUs). |
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.