:orphan: :py:mod:`neural_compressor.conf.config` ======================================= .. py:module:: neural_compressor.conf.config Module Contents --------------- Classes ~~~~~~~ .. autoapisummary:: neural_compressor.conf.config.PrunerV2 neural_compressor.conf.config.Conf neural_compressor.conf.config.Quantization_Conf neural_compressor.conf.config.Pruning_Conf neural_compressor.conf.config.Graph_Optimization_Conf neural_compressor.conf.config.MixedPrecision_Conf neural_compressor.conf.config.Benchmark_Conf neural_compressor.conf.config.Distillation_Conf neural_compressor.conf.config.NASConfig .. py:class:: PrunerV2(target_sparsity=None, pruning_type=None, pattern=None, op_names=None, excluded_op_names=None, start_step=None, end_step=None, pruning_scope=None, pruning_frequency=None, min_sparsity_ratio_per_op=None, max_sparsity_ratio_per_op=None, sparsity_decay_type=None, pruning_op_types=None, reg_type=None, criterion_reduce_type=None, parameters=None, resume_from_pruned_checkpoint=None) Similar to torch optimizer's interface. .. py:class:: Conf(cfg_fname) Config parser. :param cfg_fname: The path to the configuration file. :type cfg_fname: string .. py:class:: Quantization_Conf(cfg=None) Config parser. :param cfg: The path to the configuration file or DotDict object or None. .. py:class:: Pruning_Conf(cfg=None) Config parser. :param cfg: The path to the configuration file or DotDict object or None. .. py:class:: Graph_Optimization_Conf(cfg=None) Config parser. :param cfg: The path to the configuration file or DotDict object or None. .. py:class:: MixedPrecision_Conf(cfg=None) Config parser. :param cfg: The path to the configuration file or DotDict object or None. .. py:class:: Benchmark_Conf(cfg=None) Config parser. :param cfg: The path to the configuration file or DotDict object or None. .. py:class:: Distillation_Conf(cfg=None) Config parser. :param cfg: The path to the configuration file or DotDict object or None. .. py:class:: NASConfig(approach=None, search_space=None, search_algorithm=None) Config parser. :param approach: The approach of the NAS. :param search_algorithm: The search algorithm for NAS procedure.