tf.compat.v1.linalg.l2_normalize
bookmark_border Stay organized with collections Save and categorize content based on your preferences.

Normalizes along dimension axis using an L2 norm. (deprecated arguments)

Compat aliases for migration

tf.compat.v1.linalg.l2_normalize(
    x, axis=None, epsilon=1e-12, name=None, dim=None
)

For a 1-D tensor with axis = 0, computes

output = x / sqrt(max(sum(x**2), epsilon))

For x with more dimensions, independently normalizes each 1-D slice along dimension axis.

Args
`x`	A `Tensor`.
`axis`	Dimension along which to normalize. A scalar or a vector of integers.
`epsilon`	A lower bound value for the norm. Will use `sqrt(epsilon)` as the divisor if `norm < sqrt(epsilon)`.
`name`	A name for this operation (optional).
`dim`	Deprecated alias for axis.

Returns
A `Tensor` with the same shape as `x`.

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 2021-02-18 UTC.

tf.compat.v1.linalg.l2_normalize bookmark_borderbookmark Stay organized with collections Save and categorize content based on your preferences.