Returns ceil(x / y) as int

Creates a stack of filters used for computation of phase congruensy maps Args: - x: Tensor. Shape :math:`(N, 1, H, W)`. - scales:

Extracts patches and positional embedding lookup indexes for a given image. Args: image: the input image of shape [n_crops, c, h, w] p

Return an activation function given a string

Wraps `torchvision.models.inception_v3` Skips default weight inititialization if supported by torchvision version. See https://github.com/msei

Initialize the best metric results dict for recording the best metric value and iteration.

r"""Compute Phase Congruence for a batch of greyscale images Args: x: Tensor. Shape :math:`(N, 1, H, W)`. scales: Number of wavele

read image from lmdb with key (w/ and w/o fixed size) size: (C, H, W) tuple

Apply the CCM matrix.

Convert a BGR image to YCbCr image. The bgr version of rgb2ycbcr. It implements the ITU-R BT.601 conversion for standard-definition telev

r"""blockproc function like matlab Difference: - Partial blocks is discarded (if exist) for fast GPU process. Args: x (tenso

Build loss from options. Args: opt (dict): Configuration. It must contain: type (str): Model type.

Build model from options. Args: opt (dict): Configuration. It must contain: model_type (str): Model type.

Build model from options. Args: opt (dict): Configuration. It must contain: model_type (str): Model type.

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_

Calculate weights and indices, used for imresize function. Args: in_length (int): Input length. out_length (int): Output length.

Calculate weights and indices, used for imresize function. Args: in_length (int): Input length. out_length (int): Output length.

Calculate weights and indices, used for imresize function. Args: in_length (int): Input length. out_length (int): Output length.

clip preprocess function with tensor input. NOTE: Results are slightly different with original preprocess function with PIL image input, because

cubic function used for calculate_weights_indices.

cubic function used for calculate_weights_indices.

cubic function used for calculate_weights_indices.

Discrete Cosine Transform, Type II (a.k.a. the DCT) For the meaning of the parameter `norm`, see: https://docs.scipy.org/doc/scipy-0.14.0

dict to string for printing options. Args: opt (dict): Option dict. indent_level (int): Indent level. Default: 1. Return:

dict to string for printing options. Args: opt (dict): Option dict. indent_level (int): Indent level. Default: 1. Return:

dict to string for printing options. Args: opt (dict): Option dict. indent_level (int): Indent level. Default: 1. Return:

r"""Differentiable round.

Downsamping with Gaussian kernel used in the DUF official code. Args: x (Tensor): Frames to be downsampled, with shape (b, t, c, h, w).

Estimate AGGD (Asymmetric Generalized Gaussian Distribution) paramters. Args: block (ndarray): 2D Image block. Returns: tupl

Estimate AGGD (Asymmetric Generalized Gaussian Distribution) parameters. Args: block (ndarray): 2D Image block. Returns: tuple

r'''Fit the scale of predict scores to MOS scores using logistic regression suggested by VQEG. The function with 4 params is more commonly used.

Simulate wblfit function in matlab. ref: https://github.com/mlosch/python-weibullfit/blob/master/weibull/backend_pytorch.py Fits a 2-paramet

Fixes the network by setting all parameters to not require gradients. Args: model (nn.Module): The model to fix.

Args: pred (Tensor): of shape (N, C, H, W). Predicted tensor. target (Tensor): of shape (N, C, H, W). Ground truth te

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2

Generate depth map using HuggingFace depth estimation model img: numpy array, shape (H, W, C), BGR format returns: numpy arra

Generate an index list for reading `num_frames` frames from a sequence of images. Args: crt_idx (int): Current center index.

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

Get the backbone features for the input tensor. Args: x (torch.Tensor): The input tensor. Returns:

Get environment information. Currently, only log the software version.