:orphan:

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

.. py:module:: neural_compressor.onnxrt.utils.utility


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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.onnxrt.utils.utility.find_by_name
   neural_compressor.onnxrt.utils.utility.simple_progress_bar
   neural_compressor.onnxrt.utils.utility.register_algo
   neural_compressor.onnxrt.utils.utility.get_model_info
   neural_compressor.onnxrt.utils.utility.is_B_transposed
   neural_compressor.onnxrt.utils.utility.get_qrange_for_qType
   neural_compressor.onnxrt.utils.utility.quantize_data
   neural_compressor.onnxrt.utils.utility.check_model_with_infer_shapes



Attributes
~~~~~~~~~~

.. autoapisummary::

   neural_compressor.onnxrt.utils.utility.ONNXRT116_VERSION
   neural_compressor.onnxrt.utils.utility.ONNXRT1161_VERSION
   neural_compressor.onnxrt.utils.utility.algos_mapping
   neural_compressor.onnxrt.utils.utility.WHITE_MODULE_LIST
   neural_compressor.onnxrt.utils.utility.MAXIMUM_PROTOBUF
   neural_compressor.onnxrt.utils.utility.PRIORITY_RTN
   neural_compressor.onnxrt.utils.utility.PRIORITY_GPTQ
   neural_compressor.onnxrt.utils.utility.PRIORITY_AWQ
   neural_compressor.onnxrt.utils.utility.PRIORITY_SMOOTH_QUANT
   neural_compressor.onnxrt.utils.utility.dtype_mapping












.. py:function:: find_by_name(name, item_list)

   Helper function to find item by name in a list.


.. py:function:: simple_progress_bar(total, i)

   Progress bar for cases where tqdm can't be used.


.. 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: Union[onnx.ModelProto, Path, str],
                        quant_config: RTNConfig) -> onnx.ModelProto:
           ...

   :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:: is_B_transposed(node)

   Whether inuput B is transposed.


.. py:function:: get_qrange_for_qType(qType, reduce_range=False)

   Helper function to get the quantization range for a type.

   :param qType: data type
   :type qType: int
   :param reduce_range: use 7 bit or not. Defaults to False.
   :type reduce_range: bool, optional


.. py:function:: quantize_data(data, quantize_range, qType, scheme)

   Quantize data.

   To pack weights, we compute a linear transformation
       - when data type == uint8 mode, from [rmin, rmax] -> [0, 2^{b-1}] and
       - when data type == int8, from [-m , m] -> [-(2^{b-1}-1), 2^{b-1}-1] where
           m = max(abs(rmin), abs(rmax))
   and add necessary intermediate nodes to transform quantized weight to full weight
   using the equation r = S(q-z), where
       r: real original value
       q: quantized value
       S: scale
       z: zero point

   :param data: data to quantize
   :type data: array
   :param quantize_range: list of data to weight pack.
   :type quantize_range: list
   :param qType: data type to quantize to. Supported types UINT8 and INT8
   :type qType: int
   :param scheme: sym or asym quantization.
   :type scheme: string


.. py:function:: check_model_with_infer_shapes(model)

   Check if the model has been shape inferred.