Fetch and check data from one item of data_batch and predictions. Args: data_batch (dict): One item of data_batch. predictions (d

Get dataloader size of current loop. In `MultiValLoop` and `MultiTestLoop`, we use `total_length` instead of `len(dataloader)` to deno

Init save dir.

Setup env for wandb.

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

Add Gaussian noise. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. sigma (float): Noise scale (meas

Add Gaussian noise (PyTorch version). Args: img (Tensor): Shape (b, c, h, w), range[0, 1], float32. scale (float | Tensor): Noise

Record the image to Tensorboard. Additional support upload gif files. Args: name (str): The image identifier.

Record the image to wandb. Additional support upload gif files. Args: name (str): The image identifier. image (np.nda

Add poisson noise. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. scale (float): Noise scale. Defau

Add poisson noise to a batch of images (PyTorch version). Args: img (Tensor): Input image, shape (b, c, h, w), range [0, 1], float32.

Record the scalars to Pavi. The scalar dict will be written to the default and specified files if ``file_path`` is specified.

Visualize samples after test iteration. Args: runner (Runner): The runner of the training process. batch_idx (int): T

Visualize samples after train iteration. Args: runner (Runner): The runner of the training process. batch_idx (int):

This is the function to perform after each training iteration. Args: runner (Runner): runner to drive the pipeline ba

:class:`VisualizationHook` do not support visualize during validation. Args: runner (Runner): The runner of the training

This is the function perform before each run. Args: runner (Runner): runner used to drive the whole pipeline Raises:

Convert a BGR image to grayscale image. Args: img (ndarray): The input image. keepdim (bool): If False (by default), then return

Build module from config or return the module itself. Args: module (Union[dict, nn.Module]): The module to build. builder (Regist

Calculate the CDF of the standard bivariate Gaussian distribution. Used in skewed Gaussian distribution. Args: d_matrix (ndarrasy)

Compute the metrics from processed results. Args: results (List): The processed results of each batch. Returns: