pyiqa.archs.metaiqa_arch
========================

.. py:module:: pyiqa.archs.metaiqa_arch

.. autoapi-nested-parse::

   MetaIQA Model wrapper for pyiqa.
   Reference: Zhu, Hancheng, et al. "MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment." CVPR 2020.
   Re-implemented and optimized for pyiqa ecosystem.







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

.. py:data:: default_model_urls

.. py:class:: BaselineModel1(num_classes=1, keep_probability=0.5, inputsize=1000)

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


   .. py:method:: forward(x)


.. py:class:: MetaIQA(pretrained=True, pretrained_model_path=None, **kwargs)

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


   .. py:method:: preprocess(x)


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