pyiqa.archs.func_util
=====================

.. py:module:: pyiqa.archs.func_util






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

.. py:data:: EPS

.. py:function:: preprocess_rgb(x, test_y_channel, data_range: float = 1, color_space='yiq')

   Preprocesses an RGB image tensor.

   :param - x: The input RGB image tensor.
   :type - x: torch.Tensor
   :param - test_y_channel: Whether to test the Y channel.
   :type - test_y_channel: bool
   :param - data_range: The data range of the input tensor. Default is 1.
   :type - data_range: float
   :param - color_space: The color space of the input tensor. Default is "yiq".
   :type - color_space: str

   :returns: The preprocessed RGB image tensor.
   :rtype: torch.Tensor


.. py:function:: extract_2d_patches(x, kernel, stride=1, dilation=1, padding='same')

   Extracts 2D patches from a 4D tensor.

   :param - x: Input tensor of shape (batch_size, channels, height, width).
   :type - x: torch.Tensor
   :param - kernel: Size of the kernel to be used for patch extraction.
   :type - kernel: int
   :param - stride: Stride of the kernel. Default is 1.
   :type - stride: int
   :param - dilation: Dilation rate of the kernel. Default is 1.
   :type - dilation: int
   :param - padding: Type of padding to be applied. Can be "same" or "none". Default is "same".
   :type - padding: str

   :returns: Extracted patches tensor of shape (batch_size, num_patches, channels, kernel, kernel).
   :rtype: torch.Tensor


.. py:function:: torch_cov(tensor, rowvar=True, bias=False)

   Estimate a covariance matrix (np.cov)
   Ref: https://gist.github.com/ModarTensai/5ab449acba9df1a26c12060240773110


.. py:function:: safe_sqrt(x: torch.Tensor) -> torch.Tensor

   Safe sqrt with EPS to ensure numeric stability.

   :param x: should be non-negative
   :type x: torch.Tensor


.. py:function:: diff_round(x: torch.Tensor) -> torch.Tensor

   Differentiable round.


.. py:function:: normalize_img_with_gauss(img: torch.Tensor, kernel_size: int = 7, sigma: float = 7.0 / 6, C: int = 1, padding: str = 'same')

.. py:function:: scharr_filter() -> torch.Tensor

   Utility function that returns a normalized 3x3 Scharr kernel in X direction
   :returns: Tensor with shape (1, 3, 3)
   :rtype: kernel


.. py:function:: gradient_map(x: torch.Tensor, kernels: torch.Tensor) -> torch.Tensor

   Compute gradient map for a given tensor and stack of kernels.
   :param x: Tensor with shape (N, C, H, W).
   :param kernels: Stack of tensors for gradient computation with shape (k_N, k_H, k_W)

   :returns: Gradients of x per-channel with shape (N, C, H, W)


.. py:function:: similarity_map(map_x: torch.Tensor, map_y: torch.Tensor, constant: float, alpha: float = 0.0) -> torch.Tensor

   Compute similarity_map between two tensors using Dice-like equation.
   :param map_x: Tensor with map to be compared
   :param map_y: Tensor with map to be compared
   :param constant: Used for numerical stability
   :param alpha: Masking coefficient. Subtracts - `alpha` * map_x * map_y from denominator and nominator


.. py:function:: ifftshift(x: torch.Tensor) -> torch.Tensor

   Similar to np.fft.ifftshift but applies to PyTorch Tensors


.. py:function:: get_meshgrid(size: Tuple[int, int]) -> torch.Tensor

   Return coordinate grid matrices centered at zero point.
   :param size: Shape of meshgrid to create


.. py:function:: estimate_ggd_param(x: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]

   Estimate general gaussian distribution.

   :param x: shape (b, 1, h, w)
   :type x: Tensor


.. py:function:: estimate_aggd_param(block: torch.Tensor, return_sigma=False) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]

   Estimate AGGD (Asymmetric Generalized Gaussian Distribution) parameters.
   :param block: Image block with shape (b, 1, h, w).
   :type block: Tensor

   :returns: alpha, beta_l and beta_r for the AGGD distribution
             (Estimating the parames in Equation 7 in the paper).
   :rtype: Tensor