pyiqa.archs.liqe_arch
=====================

.. py:module:: pyiqa.archs.liqe_arch

.. autoapi-nested-parse::

   LIQE Model

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

   Cite as:
   @inproceedings{zhang2023liqe,
     title={Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective},
     author={Zhang, Weixia and Zhai, Guangtao and Wei, Ying and Yang, Xiaokang and Ma, Kede},
     booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages={14071--14081},
     year={2023}
   }







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

.. py:data:: qualitys
   :value: ['bad', 'poor', 'fair', 'good', 'perfect']


.. py:data:: scenes
   :value: ['animal', 'cityscape', 'human', 'indoor', 'landscape', 'night', 'plant', 'still_life', 'others']


.. py:data:: dists_map
   :value: ['jpeg2000 compression', 'jpeg compression', 'noise', 'blur', 'color', 'contrast',...


.. py:data:: default_model_urls

.. py:class:: LIQE(model_type='liqe', backbone='ViT-B/32', step=32, num_patch=15, pretrained=True, pretrained_model_path=None, mtl=False)

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


   LIQE no-reference quality predictor based on CLIP text-image matching.

   :param model_type: Output type name for compatibility.
   :type model_type: str
   :param backbone: CLIP backbone. Only ``'ViT-B/32'`` is supported.
   :type backbone: str
   :param step: Sliding stride for 224x224 patch extraction.
   :type step: int
   :param num_patch: Number of selected patches per image.
   :type num_patch: int
   :param pretrained: Whether to load pretrained weights. When set to
                      ``'mix'``, the multitask checkpoint is used.
   :type pretrained: bool | str
   :param pretrained_model_path: Optional local checkpoint path.
   :type pretrained_model_path: str | None
   :param mtl: Whether to enable multitask (quality/scene/distortion) text
               prompts.
   :type mtl: bool


   .. py:method:: get_text_features(x)

      Encode and normalize text features for prompt set.



   .. py:method:: forward(x)

      Predict LIQE quality score.

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

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

      :raises AssertionError: If the short image side is smaller than ``224``.