pyiqa.archs.dbcnn_arch
======================

.. py:module:: pyiqa.archs.dbcnn_arch

.. autoapi-nested-parse::

   DBCNN Metric

   Reference:
       Zhang, Weixia, et al. "Blind image quality assessment using
       a deep bilinear convolutional neural network." IEEE Transactions
       on Circuits and Systems for Video Technology 30.1 (2018): 36-47.

   Ref url: https://github.com/zwx8981/DBCNN-PyTorch/blob/master/DBCNN.py
   Re-implemented by: Chaofeng Chen (https://github.com/chaofengc)







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

.. py:data:: default_model_urls

.. py:class:: SCNN(use_bn=True)

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


   Network branch for synthetic distortions.

   :param use_bn: Whether to use batch normalization.
   :type use_bn: bool

   Modified from https://github.com/zwx8981/DBCNN-PyTorch/blob/master/SCNN.py


   .. py:method:: forward(X)

      Forward pass for the SCNN.

      :param X: Input tensor with shape (N, C, H, W).
      :type X: torch.Tensor

      :returns: Output tensor after processing through the network.
      :rtype: torch.Tensor



.. py:class:: DBCNN(fc=True, use_bn=True, pretrained_scnn_path=None, pretrained=True, pretrained_model_path=None, default_mean=[0.485, 0.456, 0.406], default_std=[0.229, 0.224, 0.225])

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


   Full DBCNN network.

   :param fc: Whether to initialize the fc layers.
   :type fc: bool
   :param use_bn: Whether to use batch normalization.
   :type use_bn: bool
   :param pretrained_scnn_path: Pretrained SCNN path.
   :type pretrained_scnn_path: str
   :param pretrained: Whether to load pretrained weights.
   :type pretrained: bool
   :param pretrained_model_path: Pretrained model path.
   :type pretrained_model_path: str
   :param default_mean: Default mean value.
   :type default_mean: list
   :param default_std: Default std value.
   :type default_std: list


   .. py:method:: preprocess(x)

      Preprocess the input tensor.

      :param x: Input tensor with shape (N, C, H, W).
      :type x: torch.Tensor

      :returns: Preprocessed tensor.
      :rtype: torch.Tensor



   .. py:method:: forward(X)

      Compute IQA using DBCNN model.

      :param X: An input tensor with (N, C, H, W) shape. RGB channel order for colour images.
      :type X: torch.Tensor

      :returns: Value of DBCNN model.
      :rtype: torch.Tensor