Module: tf.compat.v1.quantization.experimental

Public API for tf._api.v2.quantization.experimental namespace

Classes

class QuantizationComponentSpec: A ProtocolMessage

class QuantizationMethod: A ProtocolMessage

class QuantizationOptions: A ProtocolMessage

class TfRecordRepresentativeDatasetSaver: Representative dataset saver in TFRecord format.

class UnitWiseQuantizationSpec: A ProtocolMessage

Functions

quantize_saved_model(...): Quantizes the SavedModel with the given quantization options.

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 2024-01-23 UTC.

English
中文 – 简体