neural_compressor.torch.quantization.quantize
=============================================

.. py:module:: neural_compressor.torch.quantization.quantize

.. autoapi-nested-parse::

   Intel Neural Compressor Pytorch quantization base API.



Functions
---------

.. autoapisummary::

   neural_compressor.torch.quantization.quantize.need_apply
   neural_compressor.torch.quantization.quantize.quantize
   neural_compressor.torch.quantization.quantize.prepare
   neural_compressor.torch.quantization.quantize.convert
   neural_compressor.torch.quantization.quantize.finalize_calibration


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

.. py:function:: need_apply(configs_mapping: Dict[Tuple[str, callable], neural_compressor.common.base_config.BaseConfig], algo_name)

   Check whether to apply this algorithm according to configs_mapping.

   :param configs_mapping: configs mapping
   :type configs_mapping: Dict[Tuple[str, callable], BaseConfig]
   :param algo_name: algo name
   :type algo_name: str

   :returns: True or False.
   :rtype: Bool


.. py:function:: quantize(model: torch.nn.Module, quant_config: neural_compressor.common.base_config.BaseConfig, run_fn: Callable = None, run_args: Any = None, inplace: bool = True, example_inputs: Any = None) -> torch.nn.Module

   The main entry to quantize model with static mode.

   :param model: a float model to be quantized.
   :param quant_config: a quantization configuration.
   :param run_fn: a calibration function for calibrating the model. Defaults to None.
   :param run_args: positional arguments for `run_fn`. Defaults to None.
   :param example_inputs: used to trace torch model.

   :returns: The quantized model.


.. py:function:: prepare(model: torch.nn.Module, quant_config: neural_compressor.common.base_config.BaseConfig, inplace: bool = True, example_inputs: Any = None)

   Prepare the model for calibration.

   Insert observers into the model so that it can monitor the input and output tensors during calibration.

   :param model: origin model
   :type model: torch.nn.Module
   :param quant_config: path to quantization config
   :type quant_config: BaseConfig
   :param inplace: It will change the given model in-place if True.
   :type inplace: bool, optional
   :param example_inputs: used to trace torch model.
   :type example_inputs: tensor/tuple/dict, optional

   :returns: prepared and calibrated module.


.. py:function:: convert(model: torch.nn.Module, quant_config: neural_compressor.common.base_config.BaseConfig = None, inplace: bool = True)

   Convert the prepared model to a quantized model.

   :param model: the prepared model
   :type model: torch.nn.Module
   :param quant_config: path to quantization config
   :type quant_config: BaseConfig, optional
   :param inplace: It will change the given model in-place if True.
   :type inplace: bool, optional

   :returns: The quantized model.


.. py:function:: finalize_calibration(model)

   Generate and save calibration info.