Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices into

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices into

deprecation

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Compute the noise coefficient along the path

Function to reshape time t to broadcastable dimension of x Args: t: [batch_dim,], time vector x: [batch_dim,...], data point

Scan a directory to find the interested files. Args: dir_path (str): Path of the directory. suffix (str | tuple(str), optional):

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)

Take the mean over all non-batch dimensions.

Take the mean over all non-batch dimensions.

We always output sde according to score parametrization;

Get bare model, especially under wrapping with DistributedDataParallel or DataParallel.

Convert the type and range of the input image. It converts the input image to np.float32 type and range of [0, 1]. It is mainly used for pre-

Convert the type and range of the image according to dst_type. It converts the image to desired type and range. If `dst_type` is np.uint8, im

Calculate Gram matrix. Args: x (torch.Tensor): Tensor with shape of (n, c, h, w). Returns: torch.Tensor: Gra

Compute the data coefficient along the path

Args: pred (Tensor): of shape (N, C, H, W). Predicted tensor. target (Tensor): of shape (N, C, H, W). Ground truth te

Compute the KL divergence between two gaussians. Shapes are automatically broadcasted, so batches can be compared to scalars, among other

Args: clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W) mean (tuple): pixel RGB mean. Size is (3) st

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which takes

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which takes

Generate samples from the model. :param model: the model module. :param shape: the shape of the samples, (N, C, H, W).

Compute the mean and variance of the diffusion posterior: q(x_{t-1} | x_t, x_0)

Compute the mean and variance of the diffusion posterior: q(x_{t-1} | x_t, x_0)

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

forward loop of sde

Change to Y channel of YCbCr. Args: img (ndarray): Images with range [0, 255]. Returns: (ndarray): Images with range [0, 255

Loss for training the score model Args: - model: backbone model; could be score, noise, or velocity - x1: datapoint -