pyiqa.archs.arniqa_arch
=======================

.. py:module:: pyiqa.archs.arniqa_arch

.. autoapi-nested-parse::

   ARNIQA: Learning Distortion Manifold for Image Quality Assessment

   @inproceedings{agnolucci2024arniqa,
     title={ARNIQA: Learning Distortion Manifold for Image Quality Assessment},
     author={Agnolucci, Lorenzo and Galteri, Leonardo and Bertini, Marco and Del Bimbo, Alberto},
     booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
     pages={189--198},
     year={2024}
   }

   Reference:
       - Arxiv link: https://www.arxiv.org/abs/2310.14918
       - Official Github: https://github.com/miccunifi/ARNIQA







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

.. py:data:: DATASET_INFO

.. py:data:: default_model_urls

.. py:class:: ARNIQA(regressor_dataset: str = 'koniq')

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


   ARNIQA model implementation.

   This class implements the ARNIQA model for image quality assessment, which combines a ResNet50 encoder
   with a regressor network for predicting image quality scores.

   :param regressor_dataset: The dataset to use for the regressor. Default is "koniq".
   :type regressor_dataset: str, optional

   .. attribute:: regressor_dataset

      The dataset to use for the regressor.

      :type: str

   .. attribute:: encoder

      The ResNet50 encoder.

      :type: nn.Module

   .. attribute:: feat_dim

      The feature dimension of the encoder.

      :type: int

   .. attribute:: regressor

      The regressor network.

      :type: nn.Module

   .. attribute:: default_mean

      The mean values for normalization.

      :type: torch.Tensor

   .. attribute:: default_std

      The standard deviation values for normalization.

      :type: torch.Tensor


   .. py:method:: forward(x: torch.Tensor) -> float

      Forward pass of the ARNIQA model.

      :param x: The input tensor.
      :type x: torch.Tensor

      :returns: The predicted quality score.
      :rtype: float