tf.zeros  |  TensorFlow v2.16.1 (original) (raw)

tf.zeros

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

Creates a tensor with all elements set to zero.

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.zeros

tf.zeros(
    shape,
    dtype=tf.dtypes.float32,
    name=None,
    layout=None
)

Used in the notebooks

Used in the guide Used in the tutorials
Introduction to modules, layers, and models Multilayer perceptrons for digit recognition with Core APIs Better performance with the tf.data API Training checkpoints Optimizers with Core APIs Custom layers Learned data compression Using DTensors with Keras Integrated gradients Multilevel Modeling Primer in TensorFlow Probability

See also tf.zeros_like, tf.ones, tf.fill, tf.eye.

This operation returns a tensor of type dtype with shape shape and all elements set to zero.

tf.zeros([3, 4], tf.int32) <tf.Tensor: shape=(3, 4), dtype=int32, numpy= array([[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]], dtype=int32)>

Args
shape A list of integers, a tuple of integers, or a 1-D Tensor of type int32.
dtype The DType of an element in the resulting Tensor.
name Optional string. A name for the operation.
layout Optional, tf.experimental.dtensor.Layout. If provided, the result is a DTensor with the provided layout.
Returns
A Tensor with all elements set to zero.

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.