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

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

Dynamically instantiate class. Args: modules (list[importlib modules]): List of modules from importlib files. cls_type (s

Mod crop images, used during testing. Args: img (ndarray): Input image. scale (int): Scale factor. Returns: ndarray:

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool) float32 (bool) Returns:

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

Save networks. Args: net (nn.Module): Network to be saved. net_label (str): Network label. current_iter (

Reorder images to 'HWC' order. If the input_order is (h, w), return (h, w, 1); If the input_order is (c, h, w), return (h, w, c); If the

Save training states during training, which will be used for resuming. Args: epoch (int): Current epoch. curr

Set up schedulers.

PyTorch model forward (single test), it is just a simple warpper Args: model (PyTorch model) inp (Tensor): inputs defined by the m

Create dataloader. Args: dataset (torch.utils.data.Dataset): Dataset. dataset_opt (dict): Dataset options. It contains the follow

Create dataset. Args: dataset_opt (dict): Configuration for dataset. It constains: name (str): Dataset name. type

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

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

Generate paired paths from an anno file. Annotation file is a txt file listing all paths of pairs. Each line contains the relative lq and gt

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

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

Tensor shift. Args: x (Tensor): the input tensor. The shape is [b, h, w, c]. shift (tuple): shift pixel. fill_val (float

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

Create model. Args: opt (dict): Configuration. It constains: model_type (str): Model type.

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

Convert to NoneDict, which returns None for missing keys. Args: opt (dict): Option dict. Returns: (dict): NoneDict for optio

Make dirs for experiments.

Make lmdb. Contents of lmdb. The file structure is: example.lmdb ├── data.mdb ├── lock.mdb ├── meta_info.txt The data.mdb an

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

Parse option file. Args: opt_path (str): Option file path. is_train (str): Indicate whether in training or not. Default: True.

Prepare image path list and keys for DIV2K dataset. Args: folder_path (str): Folder path. Returns: list[str]: Image path lis

Save networks and training state.

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

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

Get the initial lr, which is set by the scheduler.

Get the string and total parameters of the network

Print keys with differnet name or different size when loading models. 1. Print keys with differnet names. 2. If strict=False, print t

Set learning rate for warmup. Args: lr_groups_l (list): List for lr_groups, each for an optimizer.

Calculate SSIM (structural similarity) for one channel images. It is called by func:`calculate_ssim`. Args: img1, img2 (ndarray): Im

bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

Check resume states and pretrain_model paths. Args: opt (dict): Options. resume_iter (int): Resume iteration.

Create lmdb files for DIV2K dataset. Usage: Before run this script, please run `extract_subimages.py`. Typically, there are four

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

Get target label. Args: input (Tensor): Input tensor. target_is_real (bool): Whether the targe is real or fake.

Calculate gradient penalty for wgan-gp. Args: discriminator (nn.Module): Network for the discriminator. real_data (Tensor): Real