Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

TfLiteQuantization

#include <common.h>

Structure specifying the quantization used by the tensor, if-any.

Summary

Public attributes
`params`	`void *` Holds an optional reference to a quantization param structure.
`type`	`TfLiteQuantizationType` The type of quantization held by params.

void * TfLiteQuantization::params

Holds an optional reference to a quantization param structure.

The actual type depends on the value of the type field (see the comment there for the values and corresponding types).

TfLiteQuantizationType TfLiteQuantization::type

The type of quantization held by params.

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.

Last updated 2024-05-10 UTC.