pyiqa.archs.laion_aes_arch
==========================

.. py:module:: pyiqa.archs.laion_aes_arch

.. autoapi-nested-parse::

   LAION-Aesthetics Predictor

   Introduced by: https://github.com/christophschuhmann/improved-aesthetic-predictor







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

.. py:data:: default_model_urls

.. py:class:: MLP(input_size, xcol='emb', ycol='avg_rating')

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


   Regression head used by LAION-Aesthetics predictor.


   .. py:method:: forward(x)

      Predict scalar aesthetics score from normalized image embeddings.



.. py:class:: LAIONAes(pretrained=True, pretrained_model_path=None)

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


   LAION-Aesthetics predictor based on CLIP ViT-L/14 embeddings.

   :param pretrained: Whether to load pretrained MLP weights.
   :type pretrained: bool
   :param pretrained_model_path: Optional local checkpoint path.
   :type pretrained_model_path: str | None


   .. py:method:: forward(x)

      Predict aesthetics score.

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

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