tfmot.sparsity.keras.ConstantSparsity

Pruning schedule with constant sparsity(%) throughout training.

Inherits From: PruningSchedule

target_sparsity A scalar float representing the target sparsity value.
begin_step Step at which to begin pruning.
end_step Step at which to end pruning. -1 by default. -1 implies continuing to prune till the end of training.
frequency Only apply pruning every frequency steps.

Methods

from_config

View source

Instantiates a PruningSchedule from its config.

Args
config Output of get_config().

Returns
A PruningSchedule instance.

get_config

View source

__call__

View source

Returns the sparsity(%) to be applied.

If the returned sparsity(%) is 0, pruning is ignored for the step.

Args
step Current step in graph execution.

Returns
Sparsity (%) that should be applied to the weights for the step.