pyiqa.archs.unique_arch
=======================

.. py:module:: pyiqa.archs.unique_arch

.. autoapi-nested-parse::

   LIQE Model

   github repo link: https://github.com/zwx8981/UNIQUE

   Cite as:
   @article{zhang2021uncertainty,
     title   = {Uncertainty-aware blind image quality assessment in the laboratory and wild},
     author  = {Zhang, Weixia and Ma, Kede and Zhai, Guangtao and Yang, Xiaokang},
     journal = {IEEE Transactions on Image Processing},
     volume  = {30},
     pages   = {3474--3486},
     month   = {Mar.},
     year    = {2021}
   }







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

.. py:data:: default_model_urls

.. py:class:: Normalize(mean, std)

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


   Channel-wise normalization module.


   .. py:method:: forward(x)


.. py:class:: BCNN(thresh=1e-08, is_vec=True, input_dim=512)

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


   Bilinear CNN pooling block used in UNIQUE.


   .. py:method:: forward(x)


.. py:class:: UNIQUE

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


   UNIQUE no-reference image quality model.

   :param No runtime arguments. The model loads the default pretrained:
   :param ``'mix'`` checkpoint.:


   .. py:method:: forward(x)

      Predict quality score using UNIQUE.

      :param x: Input tensor with shape ``(N, 3, H, W)``.
      :type x: torch.Tensor

      :returns: Predicted mean quality score with shape ``(N,)``.
      :rtype: torch.Tensor