Recover from quantized flow. Args: dx (ndarray): Quantized dx. dy (ndarray): Quantized dy. max_val (float): Maximum

Params: imgs: BGR image

Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py

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

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

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

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

r"""Fills the input Tensor with values drawn from a truncated normal distribution. From: https://github.com/rwightman/pytorch-image-models

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

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Arguments:

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

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

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

3x3 convolution with padding

cubic function used for calculate_weights_indices.

Initialize network weights. Args: module_list (list[nn.Module] | nn.Module): Modules to be initialized. scale (float): Scale in

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

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

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:

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

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

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

Generate Gaussian noise. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. sigma (float): Noise s

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

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

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

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

Function: ---------- get reference 5 key points according to crop settings: 0. Set default crop_size: if def

Function: ---------- Find Similarity Transform Matrix 'trans': u = src_pts[:, 0] v = src_pts[:, 1]

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None

Make dirs for experiments.

Performs Non-Maximum Suppression (NMS) on inference results Returns: detections with shape: nx6 (x1, y1, x2, y2, conf, cls)

Generate paired paths from folders. Args: folders (list[str]): A list of folder path. The order of list should be [input_

Generate paired paths from lmdb files. Contents of lmdb. Taking the `lq.lmdb` for example, the file structure is: lq.lmdb ├── data.

Pixel unshuffle. Args: x (Tensor): Input feature with shape (b, c, hh, hw). scale (int): Downsample ratio. Returns: