:orphan:

:py:mod:`neural_compressor.tensorflow.utils.utility`
====================================================

.. py:module:: neural_compressor.tensorflow.utils.utility


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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.tensorflow.utils.utility.CpuInfo
   neural_compressor.tensorflow.utils.utility.Statistics
   neural_compressor.tensorflow.utils.utility.CaptureOutputToFile
   neural_compressor.tensorflow.utils.utility.LazyImport



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.tensorflow.utils.utility.version1_lt_version2
   neural_compressor.tensorflow.utils.utility.version1_gt_version2
   neural_compressor.tensorflow.utils.utility.version1_eq_version2
   neural_compressor.tensorflow.utils.utility.version1_gte_version2
   neural_compressor.tensorflow.utils.utility.version1_lte_version2
   neural_compressor.tensorflow.utils.utility.register_algo
   neural_compressor.tensorflow.utils.utility.deep_get
   neural_compressor.tensorflow.utils.utility.itex_installed
   neural_compressor.tensorflow.utils.utility.dump_elapsed_time
   neural_compressor.tensorflow.utils.utility.combine_histogram
   neural_compressor.tensorflow.utils.utility.get_all_fp32_data
   neural_compressor.tensorflow.utils.utility.get_tensor_histogram
   neural_compressor.tensorflow.utils.utility.Dequantize
   neural_compressor.tensorflow.utils.utility.dequantize_weight
   neural_compressor.tensorflow.utils.utility.dump_data_to_local
   neural_compressor.tensorflow.utils.utility.load_data_from_pkl
   neural_compressor.tensorflow.utils.utility.singleton
   neural_compressor.tensorflow.utils.utility.disable_random
   neural_compressor.tensorflow.utils.utility.valid_keras_format



.. py:function:: version1_lt_version2(version1, version2)

   Check whether version1 is less than version2.


.. py:function:: version1_gt_version2(version1, version2)

   Check whether version1 is greater than version2.


.. py:function:: version1_eq_version2(version1, version2)

   Check whether version1 is equal to version2.


.. py:function:: version1_gte_version2(version1, version2)

   Check whether version1 is greater than version2 or is equal to it.


.. py:function:: version1_lte_version2(version1, version2)

   Check whether version1 is less than version2 or is equal to it.


.. py:function:: register_algo(name)

   Decorator function to register algorithms in the algos_mapping dictionary.

   Usage example:
       @register_algo(name=example_algo)
       def example_algo(model: tf.keras.Model, quant_config: StaticQuantConfig) -> tf.keras.Model:
           ...
   :param name: The name under which the algorithm function will be registered.
   :type name: str

   :returns: The decorator function to be used with algorithm functions.
   :rtype: decorator


.. py:function:: deep_get(dictionary, keys, default=None)

   Get the dot key's item in nested dict
      eg person = {'person':{'name':{'first':'John'}}}
      deep_get(person, "person.name.first") will output 'John'.

   :param dictionary: The dict object to get keys
   :type dictionary: dict
   :param keys: The deep keys
   :type keys: dict
   :param default: The return item if key not exists
   :type default: object

   :returns: the item of the deep dot keys
   :rtype: item


.. py:function:: itex_installed()

   Check if the Intel® Extension for TensorFlow has been installed.


.. 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:: combine_histogram(old_hist, arr)

   Collect layer histogram for arr and combine it with old histogram.


.. py:function:: get_all_fp32_data(data)

   Get all the fp32 data.


.. py:function:: get_tensor_histogram(tensor_data, bins=2048)

   Get the histogram of the tensor data.


.. py:function:: Dequantize(data, scale_info)

   Dequantize the data with the scale_info.


.. py:function:: dequantize_weight(weight_tensor, min_filter_tensor, max_filter_tensor)

   Dequantize the weight with min-max filter tensors.


.. py:function:: dump_data_to_local(data, path, filename)

   Dump data to local as pkl file.

   :param data: Data used to dump
   :param path: The directory to save data
   :param filename: The filename to dump

   :returns: loaded data


.. py:function:: load_data_from_pkl(path, filename)

   Load data from local pkl file.

   :param path: The directory to load data
   :param filename: The filename to load


.. py:function:: singleton(cls)

   Not displayed in API Docs.

   Singleton decorator.


.. py:function:: disable_random(seed=1)

   A Decorator to disable tf random seed.


.. py:function:: valid_keras_format(model)

   Check if the input model is Sequential or Functional model.


.. py:class:: CpuInfo




   Get CPU Info.


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


   The statistics printer.


.. py:class:: CaptureOutputToFile(tmp_file_path, stream=sys.stderr)




   Not displayed in API Docs.

   Capture the output to file.


.. py:class:: LazyImport(module_name)




   Lazy import python module till use.