pyiqa.archs.maniqa_arch
=======================

.. py:module:: pyiqa.archs.maniqa_arch

.. autoapi-nested-parse::

   MANIQA proposed by

       MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
       Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao, Yuan Gong, Mingdeng Cao, Jiahao Wang and Yujiu Yang.
       CVPR Workshop 2022, winner of NTIRE2022 NRIQA challenge

   Reference:
       - Official github: https://github.com/IIGROUP/MANIQA







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

.. py:data:: default_model_urls

.. py:class:: TABlock(dim, drop=0.1)

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


   .. py:method:: forward(x)


.. py:class:: SaveOutput

   .. py:method:: clear()


.. py:class:: MANIQA(embed_dim=768, num_outputs=1, patch_size=8, drop=0.1, depths=[2, 2], window_size=4, dim_mlp=768, num_heads=[4, 4], img_size=224, num_tab=2, scale=0.13, test_sample=20, pretrained=True, pretrained_model_path=None, train_dataset='pipal', default_mean=None, default_std=None, **kwargs)

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


   Implementation of the MANIQA model for image quality assessment.

   :param - embed_dim: Embedding dimension for the model. Default is 768.
   :type - embed_dim: int
   :param - num_outputs: Number of output scores. Default is 1.
   :type - num_outputs: int
   :param - patch_size: Size of patches for the model. Default is 8.
   :type - patch_size: int
   :param - drop: Dropout rate for the model. Default is 0.1.
   :type - drop: float
   :param - depths: List of depths for the Swin Transformer blocks. Default is [2, 2].
   :type - depths: list
   :param - window_size: Window size for the Swin Transformer blocks. Default is 4.
   :type - window_size: int
   :param - dim_mlp: Dimension of the MLP for the Swin Transformer blocks. Default is 768.
   :type - dim_mlp: int
   :param - num_heads: List of number of heads for the Swin Transformer blocks. Default is [4, 4].
   :type - num_heads: list
   :param - img_size: Size of the input image. Default is 224.
   :type - img_size: int
   :param - num_tab: Number of TA blocks for the model. Default is 2.
   :type - num_tab: int
   :param - scale: Scale for the Swin Transformer blocks. Default is 0.13.
   :type - scale: float
   :param - test_sample: Number of test samples for the model. Default is 20.
   :type - test_sample: int
   :param - pretrained: Whether to use a pretrained model. Default is True.
   :type - pretrained: bool
   :param - pretrained_model_path: Path to the pretrained model. Default is None.
   :type - pretrained_model_path: str
   :param - train_dataset: Name of the training dataset. Default is 'pipal'.
   :type - train_dataset: str
   :param - default_mean: Default mean for the model. Default is None.
   :type - default_mean: torch.Tensor
   :param - default_std: Default standard deviation for the model. Default is None.
   :type - default_std: torch.Tensor

   :returns: Predicted quality score for the input image.
   :rtype: torch.Tensor


   .. py:method:: extract_feature(save_output)


   .. py:method:: forward(x)

      Forward pass of the MANIQA model.

      :param x: Input image tensor.
      :type x: torch.Tensor

      :returns: Predicted quality score for the input image.
      :rtype: torch.Tensor