neural_compressor.compression.pruner.pruners

Pruning patterns.

Submodules

• neural_compressor.compression.pruner.pruners.base
• neural_compressor.compression.pruner.pruners.basic
• neural_compressor.compression.pruner.pruners.block_mask
• neural_compressor.compression.pruner.pruners.mha
• neural_compressor.compression.pruner.pruners.pattern_lock
• neural_compressor.compression.pruner.pruners.progressive
• neural_compressor.compression.pruner.pruners.retrain_free

Package Contents

Functions

parse_valid_pruner_types()	Get all valid pruner names.
get_pruner(config, modules[, framework])	Get registered pruner class.

neural_compressor.compression.pruner.pruners.parse_valid_pruner_types()

Get all valid pruner names.

neural_compressor.compression.pruner.pruners.get_pruner(config, modules, framework='pytorch')

Get registered pruner class.

Get a Pruner object from PRUNERS.

Parameters:

• modules – A dict {“module_name”: Tensor} that stores the pruning modules’ weights.

• config – A config dict object that contains the pruner information.

Returns:

A Pruner object.

Raises: AssertionError: Currently only support pruners that have been registered in PRUNERS.