Make resampling kernel for UpFirDn. Args: k (list[int]): A list indicating the 1D resample kernel magnitude. Returns: Tensor

Generate the mesh grid, centering at zero. Args: kernel_size (int): Returns: xy (ndarray): with the shape (kernel_size, kern

mkdirs. If path exists, rename it with timestamp and create a new one. Args: path (str): Folder path.

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

Calculate the rotated sigma matrix (two dimensional matrix). Args: sig_x (float): sig_y (float): theta (float): Radian me

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Validation function. Args: dataloader (torch.utils.data.DataLoader): Validation dataloader. current_iter (int): Curre

Adaptive instance normalization. Adjust the reference features to have the similar color and illuminations as those in the degradate features.

Add JPG compression artifacts. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. quality (float): JPG

Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image

Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image

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

Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to

Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to t

Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to th

Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to th

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

Convolution with FFT Input: im: h1 x w1 x c numpy array weight: h2 x w2 numpy array Output: out: h1 x w1 x c nump

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

cubic function used for calculate_weights_indices.

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

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

This is a conditional (on the input) discriminator In Batch Normalization, the fake and real images are recommended to be in

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

Encode input_tensor into feature maps, can be overridden in derived classes Default: nearest downsampling of 2**5 = 32 times

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

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

Args: input (Tensor): The input for the loss module, i.e., the network prediction. target_is_real (bo

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

Add Gaussian noise (PyTorch version). Args: img (Tensor): Shape (b, c, h, w), range[0, 1], float32. scale (float | Tensor): Noise

Generate poisson noise. Reference: https://github.com/scikit-image/scikit-image/blob/main/skimage/util/noise.py#L37-L219 Args: img (

Generate a batch of poisson noise (PyTorch version) Args: img (Tensor): Input image, shape (b, c, h, w), range [0, 1], float32. s

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

Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (

Degradation pipeline, modified from Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN