:orphan:

:py:mod:`neural_compressor.common.base_tuning`
==============================================

.. py:module:: neural_compressor.common.base_tuning


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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.common.base_tuning.EvaluationFuncWrapper
   neural_compressor.common.base_tuning.Evaluator
   neural_compressor.common.base_tuning.ConfigSet
   neural_compressor.common.base_tuning.Sampler
   neural_compressor.common.base_tuning.SequentialSampler
   neural_compressor.common.base_tuning.ConfigLoader
   neural_compressor.common.base_tuning.TuningConfig
   neural_compressor.common.base_tuning.TuningMonitor



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.common.base_tuning.init_tuning



Attributes
~~~~~~~~~~

.. autoapisummary::

   neural_compressor.common.base_tuning.default_sampler



.. py:class:: Evaluator


   Evaluator is a collection of evaluation functions.

   Note: will deprecate this class in the future.

   .. rubric:: Examples

   def eval_acc(model):
       ...

   def eval_perf(molde):
       ...

   # Usage
   user_eval_fns1 = eval_acc
   user_eval_fns2 = {"eval_fn": eval_acc}
   user_eval_fns3 = {"eval_fn": eval_acc, "weight": 1.0, "name": "accuracy"}
   user_eval_fns4 = [
       {"eval_fn": eval_acc, "weight": 0.5},
       {"eval_fn": eval_perf, "weight": 0.5, "name": "accuracy"},
       ]




.. py:class:: SequentialSampler(config_source: Sized)




   Samples elements sequentially, always in the same order.

   :param config_source: config set to sample from
   :type config_source: _ConfigSet




.. py:class:: TuningConfig(config_set: Union[neural_compressor.common.base_config.BaseConfig, List[neural_compressor.common.base_config.BaseConfig]] = None, sampler: Sampler = default_sampler, tolerable_loss=0.01, max_trials=100)


   Config for auto tuning pipeline.

   .. rubric:: Examples

   from neural_compressor.torch.quantization import TuningConfig
   tune_config = TuningConfig(
       config_set=[config1, config2, ...],
       max_trials=3,
       tolerable_loss=0.01)

   The tuning process stops when either of the following conditions is met:
       1) The number of trials reaches the maximum trials.
       2) The metric loss is within the tolerable loss.

   For condition 2), we calculate the metric loss as follows:
       relative_loss = (fp32_baseline - eval_result_of_q_model) / fp32_baseline
       If relative_loss <= tolerable_loss, we stop the tuning process.
       For example:
           tolerable_loss = 0.01
           fp32_baseline = 100
           eval_result_of_q_model = 99
           relative_loss = (100 - 99) / 100 = 0.01
           The metric loss is within the tolerable loss, so the tuning process is stopped.