pyiqa.archs.paq2piq_arch
========================

.. py:module:: pyiqa.archs.paq2piq_arch

.. autoapi-nested-parse::

   Paq2piq metric, proposed by

   Ying, Zhenqiang, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, and Alan Bovik.
   "From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality."
   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3575-3585. 2020.

   Ref url: https://github.com/baidut/paq2piq/blob/master/paq2piq/model.py
   Modified by: Chaofeng Chen (https://github.com/chaofengc)







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

.. py:data:: default_model_urls

.. py:class:: AdaptiveConcatPool2d(sz=None)

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


   Concatenate adaptive max and average pooling outputs.


   .. py:method:: forward(x)


.. py:class:: PAQ2PIQ(backbone='resnet18', pretrained=True, pretrained_model_path=None)

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


   PaQ-2-PiQ no-reference image quality predictor.

   :param backbone: Backbone name. Currently ``'resnet18'`` is supported.
   :type backbone: str
   :param pretrained: Whether to load pretrained PaQ-2-PiQ weights.
   :type pretrained: bool
   :param pretrained_model_path: Optional local checkpoint path.
   :type pretrained_model_path: str | None


   .. py:method:: forward(x)

      Predict quality score from image tensor.

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

      :returns: Predicted scores with shape ``(N, 1)``.
      :rtype: torch.Tensor