:py:mod:`neural_compressor`
===========================

.. py:module:: neural_compressor

.. autoapi-nested-parse::

   Intel® Neural Compressor: An open-source Python library supporting popular model compression techniques.



Subpackages
-----------
.. toctree::
   :titlesonly:
   :maxdepth: 3

   algorithm/index.rst
   contrib/index.rst
   data/index.rst
   experimental/index.rst
   metric/index.rst
   model/index.rst
   pruner/index.rst
   strategy/index.rst
   utils/index.rst
   ux/index.rst


Submodules
----------
.. toctree::
   :titlesonly:
   :maxdepth: 1

   benchmark/index.rst
   config/index.rst
   mix_precision/index.rst
   objective/index.rst
   quantization/index.rst
   training/index.rst
   version/index.rst


Package Contents
----------------

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.Benchmark
   neural_compressor.DistillationConfig
   neural_compressor.PostTrainingQuantConfig
   neural_compressor.WeightPruningConfig
   neural_compressor.QuantizationAwareTrainingConfig



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.set_random_seed
   neural_compressor.set_tensorboard
   neural_compressor.set_workspace



.. py:class:: Benchmark(conf_fname_or_obj)

   Bases: :py:obj:`object`

   Benchmark class can be used to evaluate the model performance.

   With the objective setting, user can get the data of what they configured in yaml.

   :param conf_fname_or_obj: The path to the YAML configuration file or
                             Benchmark_Conf class containing accuracy goal, tuning objective and preferred
                             calibration & quantization tuning space etc.
   :type conf_fname_or_obj: string or obj

   .. py:method:: dataloader(dataset, batch_size=1, collate_fn=None, last_batch='rollover', sampler=None, batch_sampler=None, num_workers=0, pin_memory=False, shuffle=False, distributed=False)

      Set dataloader for benchmarking.


   .. py:method:: metric(name, metric_cls, **kwargs)

      Set the metric class and Neural Compressor will initialize this class when evaluation.

      Neural Compressor has many built-in metrics, but users can set specific metrics through
      this api. The metric class should take the outputs of the model or
      postprocess (if have) as inputs. Neural Compressor built-in metrics always take
      (predictions, labels) as inputs for update,
      and user_metric.metric_cls should be a sub_class of neural_compressor.metric.metric
      or an user-defined metric object

      :param metric_cls: Should be a sub_class of neural_compressor.metric.BaseMetric,
                         which takes (predictions, labels) as inputs
      :type metric_cls: cls
      :param name: Name for metric. Defaults to 'user_metric'.
      :type name: str, optional


   .. py:method:: postprocess(name, postprocess_cls, **kwargs)

      Set postprocess class and neural_compressor will initialize this class when evaluation.

      The postprocess function should take the outputs of the model as inputs, and
      outputs (predictions, labels) as inputs for metric updates.

      Args:
      name (str, optional): Name for postprocess.
      postprocess_cls (cls): Should be a sub_class of neural_compressor.data.transforms.postprocess.




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

   Set the random seed in config.


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

   Set the tensorboard in config.


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

   Set the workspace in config.


.. py:class:: DistillationConfig(teacher_model=None, criterion=criterion, optimizer={'SGD': {'learning_rate': 0.0001}})

   Config of distillation.

   :param teacher_model: Teacher model for distillation. Defaults to None.
   :type teacher_model: Callable
   :param features: Teacher features for distillation, features and teacher_model are alternative.
                    Defaults to None.
   :type features: optional
   :param criterion: Distillation loss configure.
   :type criterion: Callable, optional
   :param optimizer: Optimizer configure.
   :type optimizer: dictionary, optional

   .. py:property:: criterion

      Get criterion.

   .. py:property:: optimizer

      Get optimizer.

   .. py:property:: teacher_model

      Get teacher_model.


.. py:class:: PostTrainingQuantConfig(device='cpu', backend='default', quant_format='default', inputs=[], outputs=[], approach='static', calibration_sampling_size=[100], op_type_list=None, op_name_list=None, reduce_range=None, excluded_precisions=[], quant_level=1, tuning_criterion=tuning_criterion, accuracy_criterion=accuracy_criterion)

   Bases: :py:obj:`_BaseQuantizationConfig`

   Config Class for Post Training Quantization.

   .. py:property:: approach

      Get approach.

   .. py:property:: tuning_criterion

      Get tuning_criterion.


.. py:class:: WeightPruningConfig(pruning_configs=[{}], target_sparsity=0.9, pruning_type='snip_momentum', pattern='4x1', op_names=[], excluded_op_names=[], start_step=0, end_step=0, pruning_scope='global', pruning_frequency=1, min_sparsity_ratio_per_op=0.0, max_sparsity_ratio_per_op=0.98, sparsity_decay_type='exp', pruning_op_types=['Conv', 'Linear'], **kwargs)

   Similiar to torch optimizer's interface.

   .. py:property:: weight_compression

      Get weight_compression.


.. py:class:: QuantizationAwareTrainingConfig(device='cpu', backend='default', inputs=[], outputs=[], op_type_list=None, op_name_list=None, reduce_range=None, excluded_precisions=[], quant_level=1)

   Bases: :py:obj:`_BaseQuantizationConfig`

   Config Class for Quantization Aware Training.

   .. py:property:: approach

      Get approach.