tfmot.sparsity.keras.UpdatePruningStep

Keras callback which updates pruning wrappers with the optimizer step.

tfmot.sparsity.keras.UpdatePruningStep()

Used in the guide
Pruning comprehensive guide Sparsity and cluster preserving quantization aware training (PCQAT) Keras example Pruning preserving quantization aware training (PQAT) Keras example Sparsity preserving clustering Keras example Pruning for on-device inference w/ XNNPACK

This callback must be used when training a model which needs to be pruned. Not doing so will throw an error.

model.fit(x, y,
    callbacks=[UpdatePruningStep()])

Methods

set_model(
    model
)

set_params(
    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 2023-05-26 UTC.