View source on GitHub
|
Module containing sparsity code built on Keras abstractions.
Classes
class ConstantSparsity: Pruning schedule with constant sparsity(%) throughout training.
class PolynomialDecay: Pruning Schedule with a PolynomialDecay function.
class PrunableLayer: Abstract Base Class for making your own keras layer prunable.
class PruneForLatencyOnXNNPack: Specifies to prune only 1x1 Conv2D layers in the model.
class PruningPolicy: Specifies what layers to prune in the model.
class PruningSchedule: Specifies when to prune layer and the sparsity(%) at each training step.
class PruningSummaries: A Keras callback for adding pruning summaries to tensorboard.
class UpdatePruningStep: Keras callback which updates pruning wrappers with the optimizer step.
Functions
prune_low_magnitude(...): Modify a tf.keras layer or model to be pruned during training.
prune_scope(...): Provides a scope in which Pruned layers and models can be deserialized.
strip_pruning(...): Strip pruning wrappers from the model.