tf.keras.backend.dropout

Sets entries in x to zero at random, while scaling the entire tensor.

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.backend.dropout, `tf.compat.v2.keras.backend.dropout`

tf.keras.backend.dropout(
    x, level, noise_shape=None, seed=None
)

Arguments
`x`	tensor
`level`	fraction of the entries in the tensor that will be set to 0.
`noise_shape`	shape for randomly generated keep/drop flags, must be broadcastable to the shape of `x`
`seed`	random seed to ensure determinism.

Returns
A tensor.

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.

Arguments