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

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

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

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

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), optiona

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

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

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

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

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

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

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

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

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

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

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)

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

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

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

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

Set up schedulers.

Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 np.array

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

Build pretrained InceptionV3. Args: output_blocks (list[int]): Indices of blocks to return features of. Possi

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 p

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,

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

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

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

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

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

Convert a BGR image to YCbCr image. The bgr version of rgb2ycbcr. It implements the ITU-R BT.601 conversion for standard-definition t

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

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

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