Get the position from a period list. It will return the index of the right-closest number in the period list. For example, the cumulative_per

Sinusoid position encoding table

Generate a soft mask based on alpha value using sigmoid approximation.

Get target label. Args: input (Tensor): Input tensor. target_is_real (bool): Whether the target is real or fake.

imresize function same as MATLAB. It now only supports bicubic. The same scale applies for both height and width. Args: img (Ten

We now only use wandb to sync tensorboard log.

Insert bn layer after each conv. Args: names (list): The list of layer names. Returns: list: The list of layer names with bn

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

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

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

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

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

Set random seeds.

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

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

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

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

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