Module: orbit.utils

View source on GitHub

Defines exported symbols for the orbit.utils package.

Classes

class EpochHelper: A helper class handle bookkeeping of epochs in custom training loops.

class LoopFnWithSummaries: Implements a two-program approach for optimizing summaries on TPU.

class OptionalSummariesFunction: Wrapper that provides versions of a function with and without summaries.

class SummaryManager: A utility class for managing summary writing.

class SummaryManagerInterface: A utility interface for managing summary writing.

Functions

create_global_step(...): Creates a tf.Variable suitable for use as a global step counter.

create_loop_fn(...): Creates a loop function driven by a Python while loop.

create_tf_while_loop_fn(...): Creates a loop function compatible with TF's AutoGraph loop conversion.

get_value(...): Returns input values, converting any TensorFlow values to NumPy values.

make_distributed_dataset(...): A utility function to help create a tf.distribute.DistributedDataset.

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 2025年04月18日 UTC.