MSE loss. Args: pred (Tensor): Prediction Tensor with shape (n, c, h, w). target ([type]): Target Tensor with shape (n, c, h, w).

Calculate PDF of the bivariate Gaussian distribution. Args: sigma_matrix (ndarray): with the shape (2, 2) grid (ndarray): generate

Prepare for the pre-calculating items of the metric. Defaults to do nothing. Args: module (nn.Module): Model to evaluate.

Print colored log with default logger. Args: msg (str): Message to log. level (int): The root logger level. Note that only the pr

Propagate the latent features throughout the sequence. Args: feats dict(list[tensor]): Features from previous branches. Each

Calculate PSNR (Peak Signal-to-Noise Ratio). Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio Args: img1 (ndarray): Ima

Randomly generate mixed kernels. Args: kernel_list (tuple): a list name of kernel types, support ['iso', 'aniso', 'skew', 'gen

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

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 the

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

Launch validation. The evaluation process consists of four steps. 1. Prepare pre-calculated items for all metrics by calling :meth

Iterate one mini-batch and feed the output to corresponding `metrics`. Args: idx (int): Current idx for the input data.

Iterate one mini-batch and feed the output to corresponding `metrics`. Args: idx (int): Current idx for the input data.

Save image information along with polygon shapes and xy coordinates to a JSON file. If the JSON file already exists, append the new m

set or change pre-defined key-value pairs in ``data_field`` by parameter ``data``. Args: data (dict): A dict contains ann

Set the seed for reproducibility