`neural_compressor.compression.pruner.tf_criteria`

Tensorflow pruning criterion.

Module Contents

`PruningCriterion`	Pruning base criterion.
`MagnitudeCriterion`	Pruning criterion.

`register_criterion`(name)	Register a criterion to the registry.
`get_tf_criterion`(config, modules)	Get registered criterion class.

neural_compressor.compression.pruner.tf_criteria.register_criterion(name)[source]: Register a criterion to the registry.

neural_compressor.compression.pruner.tf_criteria.get_tf_criterion(config, modules)[source]: Get registered criterion class.

class neural_compressor.compression.pruner.tf_criteria.PruningCriterion(modules, config)[source]

Pruning base criterion.

Parameters:

config – A config dict object that includes information about pruner and pruning criterion.
modules – A dict {“module_name”: Tensor} that stores the pruning modules’ weights.

scores[source]: A dict {“module_name”: Tensor} that stores the scores of pruning modules.

class neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion(modules, config)[source]

Pruning criterion.

The magnitude criterion_class is derived from PruningCriterion. The magnitude value is used to score and determine if a weight is to be pruned.

Parameters:

config – A config dict object that includes information about pruner and pruning criterion.
modules – A dict {“module_name”: Tensor} that stores the pruning modules’ weights.

scores[source]: A dict {“module_name”: Tensor} that stores the scores of pruning modules.