|View source on GitHub|
Pruning Schedule with a PolynomialDecay function.
__init__( initial_sparsity, final_sparsity, begin_step, end_step, power=3, frequency=100 )
Initializes a Pruning schedule with a PolynomialDecay function.
Pruning rate grows rapidly in the beginning from initial_sparsity, but then plateaus slowly to the target sparsity. The function applied is
current_sparsity = final_sparsity + (initial_sparsity - final_sparsity) * (1 - (step - begin_step)/(end_step - begin_step)) ^ exponent
which is a polynomial decay function. See paper.
initial_sparsity: Sparsity (%) at which pruning begins.
final_sparsity: Sparsity (%) at which pruning ends.
begin_step: Step at which to begin pruning.
end_step: Step at which to end pruning.
power: Exponent to be used in the sparsity function.
frequency: Only apply pruning every
Returns the sparsity(%) to be applied.
If the returned sparsity(%) is 0, pruning is ignored for the step.
step: Current step in graph execution.
Sparsity (%) that should be applied to the weights for the step.
from_config( cls, config )
PruningSchedule from its config.
config: Output of