pyiqa.archs.ckdn_arch
=====================

.. py:module:: pyiqa.archs.ckdn_arch

.. autoapi-nested-parse::

   CKDN model introduced by

   Zheng, Heliang, Huan Yang, Jianlong Fu, Zheng-Jun Zha, and Jiebo Luo.
   "Learning conditional knowledge distillation for degraded-reference image quality assessment."
   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10242-10251. 2021.

   Ref url: https://github.com/researchmm/CKDN.
   Re-implemented by: Chaofeng Chen (https://github.com/chaofengc)









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

.. py:data:: default_model_urls

.. py:data:: model_urls

.. py:function:: conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1)

   3x3 convolution with padding


.. py:function:: conv1x1(in_planes, out_planes, stride=1)

   1x1 convolution


.. py:class:: BasicBlock(inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=None)

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


   .. py:method:: forward(x)


.. py:class:: Bottleneck(inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=None)

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


   .. py:method:: forward(x)


.. py:class:: ResNet(block, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=None)

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


   .. py:method:: forward(x, y)

      Forward pass for the ResNet model.

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

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



.. py:class:: CKDN(pretrained=True, pretrained_model_path=None, use_default_preprocess=True, default_mean=(0.485, 0.456, 0.406), default_std=(0.229, 0.224, 0.225), **kwargs)

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


   CKDN metric.

   :param pretrained_model_path: The model path.
   :type pretrained_model_path: str
   :param use_default_preprocess: Whether to use default preprocess, default: True.
   :type use_default_preprocess: bool
   :param default_mean: The mean value.
   :type default_mean: tuple
   :param default_std: The std value.
   :type default_std: tuple

   Reference:
       Zheng, Heliang, Huan Yang, Jianlong Fu, Zheng-Jun Zha, and Jiebo Luo.
       "Learning conditional knowledge distillation for degraded-reference image
       quality assessment." In Proceedings of the IEEE/CVF International Conference
       on Computer Vision (ICCV), pp. 10242-10251. 2021.


   .. py:method:: forward(x, y)

      Compute IQA using CKDN model.

      :param x: Input tensor with shape (N, C, H, W). RGB channel order for colour images.
      :type x: torch.Tensor
      :param y: Reference tensor with shape (N, C, H, W). RGB channel order for colour images.
      :type y: torch.Tensor

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