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

Module: mediapipe_model_maker.quantization

View source on GitHub

Libraries for post-training quantization.

View aliases

Main aliases

mediapipe_model_maker.face_stylizer.face_stylizer.face_stylizer_options.model_opt.loss_functions.model_util.quantization, mediapipe_model_maker.face_stylizer.face_stylizer.loss_functions.model_util.quantization, mediapipe_model_maker.face_stylizer.face_stylizer.model_opt.loss_functions.model_util.quantization, mediapipe_model_maker.face_stylizer.face_stylizer.model_util.quantization, mediapipe_model_maker.face_stylizer.face_stylizer_options.model_opt.loss_functions.model_util.quantization, mediapipe_model_maker.face_stylizer.model_options.loss_functions.model_util.quantization, mediapipe_model_maker.model_util.quantization

Modules

ds module: Common dataset for model training and evaluation.

Classes

class QuantizationConfig: Configuration for post-training quantization.

Other Members
DEFAULT_QUANTIZATION_STEPS	`500`
absolute_import	Instance of `__future__._Feature`
division	Instance of `__future__._Feature`
print_function	Instance of `__future__._Feature`

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 2024-05-07 UTC.