Args: optimizer (Optimizer): Wrapped optimizer. warmup_epochs (int): Maximum number of iterations for linear warmup

Called when epoch is passed as a param to the `step` function of the scheduler.

wgan loss. Args: input (Tensor): Input tensor. target (bool): Target label. Returns: Tensor: wga

wgan loss with soft plus. softplus is a smooth approximation to the ReLU function. In StyleGAN2, it is called: Logistic l

Generate attribute gabor function.

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2) i

Calculate NIQE (Natural Image Quality Evaluator) metric. ``Paper: Making a "Completely Blind" Image Quality Analyzer`` This implementation c

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

Calculate SSIM (structural similarity) (PyTorch version). ``Paper: Image quality assessment: From error visibility to structural similarity``

Crop borders of images. Args: imgs (list[ndarray] | ndarray): Images with shape (h, w, c). crop_border (int): Crop border for eac

Differentiable rounding function

Download files from google drive. Reference: https://stackoverflow.com/questions/25010369/wget-curl-large-file-from-google-drive Args:

Extract inception features. Args: data_generator (generator): A data generator. inception (nn.Module): Inception model. l

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

Read an optical flow map. Args: flow_path (ndarray or str): Flow path. quantize (bool): whether to read quantized pair, if set to

Write optical flow to file. If the flow is not quantized, it will be saved as a .flo file losslessly, otherwise a jpeg image which is lossy b