neural_compressor.experimental.pruning

Pruning module.

Module Contents

Classes

Pruning

This is base class of pruning object.

TfPruningCallback

Class that contains callback functions.
class neural_compressor.experimental.pruning.Pruning(conf_fname_or_obj=None)[source]

This is base class of pruning object.

Since DL use cases vary in the accuracy metrics (Top-1, MAP, ROC etc.), loss criteria (<1% or <0.1% etc.) and pruning objectives (performance, memory footprint etc.). Pruning class provides a flexible configuration interface via YAML for users to specify these parameters.

Parameters:

conf_fname_or_obj (string or obj) – The path to the YAML configuration file or PruningConf class containing accuracy goal, pruning objective and related dataloaders etc.

conf[source]

A config dict object. Contains pruning setting parameters.

pruners[source]

A list of Pruner object.

class neural_compressor.experimental.pruning.TfPruningCallback(nc_model, input_model, hooks)[source]

Class that contains callback functions.

Parameters:

  • nc_model – A neural compression model object.

  • hooks – A dict. Contains pure-defined hooks.