pyiqa.archs.compare2score_arch
==============================

.. py:module:: pyiqa.archs.compare2score_arch

.. autoapi-nested-parse::

   Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare

   Reference:
   @inproceedings{zhu2024adaptive,
     title={Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare},
     author={Zhu, Hanwei and Wu, Haoning and Li, Yixuan and Zhang, Zicheng and Chen, Baoliang and Zhu, Lingyu and Fang, Yuming and Zhai, Guangtao and Lin, Weisi and Wang, Shiqi},
     booktitle={Conference on Neural Information Processing Systems},
     year={2024},
   }

   Reference url: https://github.com/Q-Future/Compare2Score







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

.. py:function:: expand2square(pil_img)

   Pad a PIL image to square with CLIP-mean background color.

   :param pil_img: Input image.
   :type pil_img: PIL.Image.Image

   :returns: Square padded image.
   :rtype: PIL.Image.Image


.. py:class:: Compare2Score(dtype='fp16')

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


   Compare2Score large multimodal IQA model wrapper.

   :param dtype: Inference precision mode. Supported values are
                 ``'fp16'``, ``'4bit'``, and ``'8bit'``.
   :type dtype: str

   .. rubric:: Notes

   Current implementation supports batch size ``1`` in preprocessing.


   .. py:method:: preprocess(x)

      Convert a single-image tensor batch to PIL image.

      :param x: Input tensor with shape ``(1, 3, H, W)``.
      :type x: torch.Tensor

      :returns: Converted image.
      :rtype: PIL.Image.Image

      :raises AssertionError: If batch size is not ``1``.



   .. py:method:: forward(x)

      Run Compare2Score model inference.

      :param x: Input image tensor with shape ``(1, 3, H, W)``.
      :type x: torch.Tensor

      :returns: Predicted quality score.
      :rtype: torch.Tensor