deprecation

This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches

deprecation

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb.

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

Load network. Args: load_path (str): The path of networks to be loaded. net (nn.Module): Network. strict

mkdirs. If path exists, rename it with timestamp and create a new one. Args: path (str): Folder path.

Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). :param x_start: the initial

Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). :param x_start: the initial

Save networks and training state.

Save networks. Args: net (nn.Module | list[nn.Module]): Network(s) to be saved. net_label (str): Network label.

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portio

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

Performs a random temporal crop on a video sequence. This function randomly selects a continuous frame sequence of length `size` from a vide

TODO: generalize here by adding all private functions ending with steps to it

Get the last step function of the SDE solver

Construct a PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int)

Applies basic cleaning and formatting to a text string.

Get the initial lr, which is set by the scheduler.

Initialize slurm distributed training environment. If argument ``port`` is not specified, then the master port will be system environment var

Initialize the best metric results dict for recording the best metric value and iteration.

Loads and preprocesses an image from a file path.

Print keys with different name or different size when loading models. 1. Print keys with different names. 2. If strict=False, print t

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

Set learning rate for warmup. Args: lr_groups_l (list): List for lr_groups, each for an optimizer.

Calculate SSIM (structural similarity) for one channel images. It is called by func:`calculate_ssim`. Args: img (ndarray): Images wi