neural_compressor.common.utils.utility
======================================

.. py:module:: neural_compressor.common.utils.utility

.. autoapi-nested-parse::

   The utility of common module.



Classes
-------

.. autoapisummary::

   neural_compressor.common.utils.utility.LazyImport
   neural_compressor.common.utils.utility.CpuInfo
   neural_compressor.common.utils.utility.ProcessorType
   neural_compressor.common.utils.utility.Statistics


Functions
---------

.. autoapisummary::

   neural_compressor.common.utils.utility.singleton
   neural_compressor.common.utils.utility.dump_elapsed_time
   neural_compressor.common.utils.utility.set_random_seed
   neural_compressor.common.utils.utility.set_workspace
   neural_compressor.common.utils.utility.get_workspace
   neural_compressor.common.utils.utility.set_resume_from
   neural_compressor.common.utils.utility.set_tensorboard
   neural_compressor.common.utils.utility.log_process
   neural_compressor.common.utils.utility.call_counter
   neural_compressor.common.utils.utility.detect_processor_type_based_on_hw


Module Contents
---------------

.. py:function:: singleton(cls)

   Singleton decorator.


.. py:class:: LazyImport(module_name)



   Lazy import python module till use.


.. py:class:: CpuInfo



   Get CPU Info.


.. py:function:: dump_elapsed_time(customized_msg='')

   Get the elapsed time for decorated functions.

   :param customized_msg: The parameter passed to decorator. Defaults to None.
   :type customized_msg: string, optional


.. py:function:: set_random_seed(seed: int)

   Set the random seed in config.


.. py:function:: set_workspace(workspace: str)

   Set the workspace in config.


.. py:function:: get_workspace()

   Get the workspace in config.


.. py:function:: set_resume_from(resume_from: str)

   Set the resume_from in config.


.. py:function:: set_tensorboard(tensorboard: bool)

   Set the tensorboard in config.


.. py:function:: log_process(mode=Mode.QUANTIZE)

   Decorator function that logs the stage of process.

   :param mode: The mode of the process.
   :type mode: Mode

   :returns: The decorated function.


.. py:function:: call_counter(func)

   A decorator that keeps track of the number of times a function is called.

   :param func: The function to be decorated.

   :returns: The decorated function.


.. py:class:: ProcessorType



   The processor type.


.. py:function:: detect_processor_type_based_on_hw()

   Detects the processor type based on the hardware configuration.

   :returns: The detected processor type (Server or Client).
   :rtype: ProcessorType


.. py:class:: Statistics(data, header, field_names, output_handle=logger.info)

   The statistics printer.