Performs data augmentation of the input image Input: image: a cv2 (OpenCV) image mode: int. Choice of transformation to apply

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

Dequantize an array. Args: arr (ndarray): Input array. min_val (scalar): Minimum value to be clipped. max_val (scalar): M

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

Generate Gaussian kernel used in `duf_downsample`. Args: kernel_size (int): Kernel size. Default: 13. sigma (float): Sigma of the

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

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

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

Calculate NIQE (Natural Image Quality Evaluator) metric. Ref: Making a "Completely Blind" Image Quality Analyzer. This implementation could p

Support OrderedDict for yaml. Returns: yaml Loader and Dumper.

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

Quantize an array of (-inf, inf) to [0, levels-1]. Args: arr (ndarray): Input array. min_val (scalar): Minimum value to be clippe

Quantize flow to [0, 255]. After this step, the size of flow will be much smaller, and can be dumped as jpeg images. Args: flow

read image by cv2 or from lmdb return: Numpy float32, HWC, BGR, [0,1]

read image by cv2 or from lmdb return: Numpy float32, HWC, BGR, [0,1]

Read image worker. Args: path (str): Image path. key (str): Image key. compress_level (int): Compress level when encoding

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are 'none', 'mean' and 'sum'.

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

Reload the optimizers and schedulers for resumed training. Args: resume_state (dict): Resume state.

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

Set random seeds.

Set up schedulers.

Update learning rate. Args: current_iter (int): Current iteration. warmup_iter (int)： Warmup iter numbers. -1 for no

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights. Default

Format logging message. Args: log_vars (dict): It contains the following keys: epoch (int): Epoch number.