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

Rotate image. Args: img (ndarray): Image to be rotated. angle (float): Rotation angle in degrees. Positive values mean

Load file form http url, will download models if necessary. Reference: https://github.com/1adrianb/face-alignment/blob/master/face_alignment/util

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

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

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

Generate paired paths from an meta information file. Each line in the meta information file contains the image names and image shape (usually

Generate paths from folder. Args: folder (str): Folder path. Returns: list[str]: Returned path list.

Pixel unshuffle. Args: x (Tensor): Input feature with shape (b, c, hh, hw). scale (int): Downsample ratio. Returns:

R1 regularization for discriminator. The core idea is to penalize the gradient on real data alone: when the generator distribution pro

Get raw data (steps and values) from tensorboard events. Args: log_path (str): Path to the tensorboard log. tag (str): tag to be

Read data from txt with 1 returned values. Args: path (str): path to the txt file. pattern (str): re (regular expression) pattern

Read data from txt with 2 returned values (usually [step, value]). Args: path (str): path to the txt file. pattern (str): re (reg

Register the given object under the the name `obj.__name__`. Can be used as either a decorator or not. See docstring of this

Resize a flow according to ratio or shape. Args: flow (Tensor): Precomputed flow. shape [N, 2, H, W]. size_type (str): 'ratio' or

Convert a RGB image to YCbCr image. This function produces the same results as Matlab's `rgb2ycbcr` function. It implements the ITU-R BT.601

Save tensor as image.

Smooth data using 1st-order IIR low-pass filter (what tensorflow does). Reference: https://github.com/tensorflow/tensorboard/blob/f801ebf1f9fbfe

This implementation is slightly faster than tensor2img. It now only supports torch tensor with shape (1, c, h, w). Args: tensor (Tens

USM sharpening. Input image: I; Blurry image: B. 1. sharp = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > threshold, else: 0 3. Bl

Create a weighted version of a given loss function. To use this decorator, the loss function must have the signature like `loss_func(pred, ta

Convert a YCbCr image to BGR image. The bgr version of ycbcr2rgb. It implements the ITU-R BT.601 conversion for standard-definition telev

Convert a YCbCr image to RGB image. This function produces the same results as Matlab's ycbcr2rgb function. It implements the ITU-R BT.601 co