tf.math.floor  |  TensorFlow v2.16.1 (original) (raw)

tf.math.floor

Stay organized with collections Save and categorize content based on your preferences.

Returns element-wise largest integer not greater than x.

View aliases

Main aliases

tf.floor

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.floor

tf.math.floor(
    x, name=None
)

Used in the notebooks

Used in the tutorials
Scalable model compression

Both input range is (-inf, inf) and the output range consists of all integer values.

For example:

x = tf.constant([1.3324, -1.5, 5.555, -2.532, 0.99, float("inf")]) tf.floor(x).numpy() array([ 1., -2., 5., -3., 0., inf], dtype=float32)

Args
x A Tensor. Must be one of the following types: bfloat16, half,float32, float64.
name A name for the operation (optional).
Returns
A Tensor. Has the same type 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 2024-04-26 UTC.