tf.keras.activations.hard_sigmoid

Hard sigmoid activation function.

Compat aliases for migration

See Migration guide for more details.

tf.keras.activations.hard_sigmoid(
    x
)

Faster to compute than sigmoid activation.

Arguments
`x`	Input tensor.

Returns
Hard sigmoid activation: `0` if `x < -2.5` `1` if `x > 2.5` `0.2 * x + 0.5` if `-2.5 <= x <= 2.5`.

Returns

Hard sigmoid activation:

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.

Last updated 2020-10-01 UTC.