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

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

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

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

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

Get bare model, especially under wrapping with DistributedDataParallel or DataParallel.

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

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

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

Change to Y channel of YCbCr. Args: img (ndarray): Images with range [0, 255]. Returns: (ndarray): Images with range [0, 255

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

Convert the type and range of the input image. It converts the input image to np.float32 type and range of [0, 1]. It is mainly used for pre-

Convert the type and range of the image according to dst_type. It converts the image to desired type and range. If `dst_type` is np.uint8, im

Calculate Gram matrix. Args: x (torch.Tensor): Tensor with shape of (n, c, h, w). Returns: torch.Tensor: Gra

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

Build dataset from options. Args: dataset_opt (dict): Configuration for dataset. It must contain: name (str): Dataset name.

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

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

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

Convert RGB images to YCbCr images (PyTorch version). It implements the ITU-R BT.601 conversion for standard-definition television. See more deta

Save networks and training state.

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

Set up schedulers.

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

Calculate attribute gradient.

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

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

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

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

Make dirs for experiments.

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

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

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

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

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

Calculate metric from data and options. Args: opt (dict): Configuration. It must contain: type (str): Model type.

Calculate PSNR (Peak Signal-to-Noise Ratio). Reference: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio Args: img (ndarray)

Calculate SSIM (structural similarity). ``Paper: Image quality assessment: From error visibility to structural similarity`` The results are

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

cubic function used for calculate_weights_indices.

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

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

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

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