pyiqa.archs.hypernet_arch
=========================

.. py:module:: pyiqa.archs.hypernet_arch

.. autoapi-nested-parse::

   HyperNet Metric

   @InProceedings{hyperiqa,
       author = {Su, Shaolin and Yan, Qingsen and Zhu, Yu and Zhang, Cheng and Ge, Xin and Sun, Jinqiu and Zhang, Yanning},
       title = {Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network},
       booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
       month = {June},
       year = {2020}
   }

   Ref url: https://github.com/SSL92/hyperIQA
   Re-implemented by: Chaofeng Chen (https://github.com/chaofengc)







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

.. py:data:: default_model_urls

.. py:class:: HyperNet(base_model_name='resnet50', num_crop=25, pretrained=True, pretrained_model_path=None, default_mean=[0.485, 0.456, 0.406], default_std=[0.229, 0.224, 0.225])

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


   HyperIQA self-adaptive hyper network for no-reference IQA.

   :param base_model_name: Backbone model name supported by :mod:`timm`.
   :type base_model_name: str
   :param num_crop: Number of test-time crops for inference averaging.
   :type num_crop: int
   :param pretrained: Whether to load pretrained HyperIQA weights.
   :type pretrained: bool
   :param pretrained_model_path: Optional local checkpoint path.
   :type pretrained_model_path: str | None
   :param default_mean: Input normalization mean.
   :type default_mean: list[float]
   :param default_std: Input normalization std.
   :type default_std: list[float]

   Reference:
       Su, Shaolin, Qingsen Yan, Yu Zhu, Cheng Zhang, Xin Ge,
       Jinqiu Sun, and Yanning Zhang. "Blindly assess image
       quality in the wild guided by a self-adaptive hyper network."
       In Proceedings of the IEEE/CVF Conference on Computer Vision
       and Pattern Recognition (CVPR), pp. 3667-3676. 2020.



   .. py:method:: preprocess(x)

      Resize to 224x224 if needed and apply ImageNet normalization.



   .. py:method:: forward_patch(x)

      Predict quality for one 224x224 patch batch.



   .. py:method:: forward(x)

      Compute HyperNet quality score.

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

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