Input: pch_res: pch_size x pch_size x 3, [0,1] index_infos: (h_start, h_end, w_start, w_end)

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Create a 1D, 2D, or 3D convolution module.

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb.

PyTorch version of cv2.filter2D Args: img (Tensor): (b, c, h, w) kernel (Tensor): (b, k, k)

Compute the output image given the features. Args: lqs (tensor): Input low quality (LQ) sequence with shape (n, t

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

Augment: horizontal flips OR rotate (0, 90, 180, 270 degrees). We use vertical flip and transpose for rotation implementation. All the images

Paired random crop. Support Numpy array and Tensor inputs. It crops lists of lq and gt images with corresponding locations. Args: im

Save networks. Args: net (nn.Module | list[nn.Module]): Network(s) to be saved. net_label (str): Network label.

Scan a directory to find the interested files. Args: dir_path (str): Path of the directory. suffix (str | tuple(str), optional):

get the image data and update pbar.

Make layers by stacking the same blocks. Args: basic_block (nn.module): nn.module class for basic block. num_basic_block (int): n

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Warp an image or feature map with optical flow. Args: x (Tensor): Tensor with size (n, c, h, w). flow (Tensor): Tensor with size

Create a linear module.

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

Load network. Args: load_path (str): The path of networks to be loaded. net (nn.Module): Network. strict

Read a sequence of images from a given folder path. Args: path (list[str] | str): List of image paths or image folder path. requi

Zero out the parameters of a module and return it.

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

Zero out the parameters of a module and return it.

reduce loss dict. In distributed training, it averages the losses among different GPUs . Args: loss_dict (OrderedDict):

2D sinc filter Reference: https://dsp.stackexchange.com/questions/58301/2-d-circularly-symmetric-low-pass-filter Args: cutoff (float

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

Model to device. It also warps models with DistributedDataParallel or DataParallel. Args: net (nn.Module)

Print the str and parameter number of a network. Args: net (nn.Module)

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