pyiqa.archs.qrealign_arch
=========================

.. py:module:: pyiqa.archs.qrealign_arch

.. autoapi-nested-parse::

   Q-ReAlign: a modern, model-agnostic Q-Align visual-quality scorer.

   Q-ReAlign reproduces the Q-Align recipe on a Qwen3.5-VL backbone (``model_type:
   qwen3_5``): the model is asked to rate quality, and the probability mass it places
   on the discrete words ``excellent / good / fair / poor / bad`` is collapsed -- via
   the fixed weighting ``[1.0, 0.75, 0.5, 0.25, 0.0]`` -- into a single scalar in
   ``[0, 1]`` (higher = better).

   Three public checkpoints (selected with ``model=``):
       mini -> q-future/Q-ReAlign-Mini-0.8B   (fast, throughput champion)
       lite -> q-future/Q-ReAlign-Lite-4B
       pro  -> q-future/Q-ReAlign-Pro-9B       (best average SRCC/PLCC)

   Requires ``transformers>=5.0`` (native qwen3_5 from 5.2; 5.0/5.1 run via the
   vendored modeling + shim in ``pyiqa.archs.qrealign``).

   Reference:
       Wu et al., "Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined
       Levels", arXiv:2312.17090. Q-ReAlign: https://github.com/Q-Future/Q-ReAlign







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

.. py:data:: LEVELS
   :value: ['excellent', 'good', 'fair', 'poor', 'bad']


.. py:data:: WEIGHTS
   :value: [1.0, 0.75, 0.5, 0.25, 0.0]


.. py:data:: MODELS

.. py:data:: TASKS

.. py:class:: QReAlign(model='mini', dtype='auto', task='quality')

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


   Q-ReAlign multimodal visual-quality scorer (Qwen3.5-VL backbone).

   :param model: one of ``'mini'`` / ``'lite'`` / ``'pro'`` (see ``MODELS``),
                 or any HuggingFace repo id / local path to a Q-ReAlign checkpoint.
   :type model: str
   :param dtype: torch dtype passed to ``from_pretrained`` (default ``'auto'``
                 -> bfloat16 weights).
   :type dtype: str
   :param task: default scoring task, ``'quality'`` (IQA) or ``'aesthetic'`` (IAA).
   :type task: str


   .. py:method:: forward(x, task_=None)

      Score a batch of images.

      :param x: ``(B, 3, H, W)`` in ``[0, 1]``.
      :type x: torch.Tensor
      :param task_: override the default task for this call.
      :type task_: str

      :returns: shape ``(B,)`` quality scores in ``[0, 1]`` (higher = better).
      :rtype: torch.Tensor