pyiqa.archs.wadiqam_arch
========================

.. py:module:: pyiqa.archs.wadiqam_arch

.. autoapi-nested-parse::

   WaDIQaM model.

   Reference:
       Bosse, Sebastian, Dominique Maniry, Klaus-Robert Müller, Thomas Wiegand,
       and Wojciech Samek. "Deep neural networks for no-reference and full-reference
       image quality assessment." IEEE Transactions on image processing 27, no. 1
       (2017): 206-219.

   Created by: https://github.com/lidq92/WaDIQaM
   Modified by: Chaofeng Chen (https://github.com/chaofengc)
   Refer to:
       Official code from https://github.com/dmaniry/deepIQA









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

.. py:data:: default_model_urls

.. py:function:: make_layers(cfg: List[Union[str, int]]) -> torch.nn.Sequential

.. py:class:: WaDIQaM(metric_type='FR', model_name='wadiqam_fr_kadid', pretrained=True, weighted_average=True, train_patch_num=32, pretrained_model_path=None, load_feature_weight_only=False, eps=1e-08)

   Bases: :py:obj:`torch.nn.Module`


   WaDIQaM model.
   :param metric_type: Choose metric mode.
   :type metric_type: String
   :param weighted_average: Average the weight.
   :type weighted_average: Boolean
   :param train_patch_num: Number of patch trained. Default: 32.
   :type train_patch_num: int
   :param pretrained_model_path: The pretrained model path.
   :type pretrained_model_path: String
   :param load_feature_weight_only: Only load featureweight.
   :type load_feature_weight_only: Boolean
   :param eps: Constant value.
   :type eps: float


   .. py:method:: load_pretrained_network(model_path, load_feature_weight_only=False)


   .. py:method:: get_patches(x, y=None)


   .. py:method:: extract_features(patches)


   .. py:method:: forward(x, y=None)

      WaDIQaM model.
      :param x: An input tensor. Shape :math:`(N, C, H, W)`.
      :param y: A reference tensor. Shape :math:`(N, C, H, W)`.