pyiqa.losses.iqa_losses
=======================

.. py:module:: pyiqa.losses.iqa_losses






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

.. py:function:: emd_loss(pred, target, r=2)

   :param pred: of shape (N, C). Predicted tensor.
   :type pred: Tensor
   :param target: of shape (N, C). Ground truth tensor.
   :type target: Tensor
   :param r: norm level, default l2 norm.
   :type r: float


.. py:class:: EMDLoss(loss_weight=1.0, r=2, reduction='mean')

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


   EMD (earth mover distance) loss.


   .. py:method:: forward(pred, target, weight=None, **kwargs)


.. py:function:: plcc_loss(pred, target)

   :param pred: of shape (N, 1). Predicted tensor.
   :type pred: Tensor
   :param target: of shape (N, 1). Ground truth tensor.
   :type target: Tensor


.. py:class:: PLCCLoss(loss_weight=1.0)

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


   PLCC loss, induced from Pearson’s Linear Correlation Coefficient.


   .. py:method:: forward(pred, target)


.. py:class:: RankLoss(detach=False, loss_weight=1.0)

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


   Monotonicity regularization loss, will be zero when rankings of pred and target are the same.

   Reference:
       - https://github.com/lidq92/LinearityIQA/blob/master/IQAloss.py



   .. py:method:: forward(pred, target)


.. py:function:: norm_loss_with_normalization(pred, target, p, q)

   :param pred: of shape (N, 1). Predicted tensor.
   :type pred: Tensor
   :param target: of shape (N, 1). Ground truth tensor.
   :type target: Tensor


.. py:class:: NiNLoss(loss_weight=1.0, p=1, q=2)

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


   NiN (Norm in Norm) loss

   Reference:

       - Dingquan Li, Tingting Jiang, and Ming Jiang. Norm-in-Norm Loss with Faster Convergence and Better
         Performance for Image Quality Assessment. ACMM2020.
       - https://arxiv.org/abs/2008.03889
       - https://github.com/lidq92/LinearityIQA

   This loss can be simply described as: l1_norm(normalize(pred - pred_mean), normalize(target - target_mean))



   .. py:method:: forward(pred, target)