neural_compressor.experimental.pruner_legacy.pruner

Pattern lock pruner.

Module Contents

Classes

Pruner

The base clase of Pruner.

Functions

pruner_registry(cls)

The class decorator used to register all Pruners subclasses.

neural_compressor.experimental.pruner_legacy.pruner.pruner_registry(cls)

The class decorator used to register all Pruners subclasses.

Parameters:

cls (class) – The class of register.

Returns:

The class of register.

Return type:

cls

class neural_compressor.experimental.pruner_legacy.pruner.Pruner(model, local_config, global_config)

The base clase of Pruner.

Parameters:

• model (object) – The original model (currently PyTorchModel instance).

• local_config (Conf) – configs specific for this pruning instance.

• global_config (Conf) – global configs which may be overwritten by local_config.