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 int

Build submodule.

Take the mean over all non-batch dimensions.

Build attention.

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

Zero out the parameters of a module and return it.

Return a tensor where each element has the absolute value taken from the, corresponding element of a, with sign taken from the corresponding

Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0.

Build dataset by the given config.

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

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

Multiply quaternion(s) q with quaternion(s) r. Expects two equally-sized tensors of shape (*, 4), where * denotes any number of dimen

Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This allow

Build framework.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloade

Build loss.

Convert a version string into a tuple of integers. This method is usually used for comparing two versions. For pre-release versions: alpha < b

Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part

Scatter function. Args: inputs (Tensor): Input Tensor. kwargs (dict): Args for ``mmcv.parallel.scatte

Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

A fast approximation of the cumulative distribution function of the standard normal.

Params: -- activation: num_samples x dim_feat Returns: -- mu: dim_feat -- sigma: dim_feat x dim_feat

Check whether a file or a directory exists at the expected path. Args: path_str (str): Path to check. path_type (Lite

Check whether the suffix of the path is allowed. Args: path_str (str): Path to check. allowed_suffix (List[str], opti

Collect the information of the running environments.

Params: -- matrix1: N1 x D -- matrix2: N2 x D Returns: -- dist: N1 x N2 dist[i, j] == distance(matrix

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

Convert quaternion(s) q to Euler angles. Expects a tensor of shape (*, 4), where * denotes any number of dimensions. Returns a tensor of

Rotate vector(s) v about the rotation described by quaternion(s) q. Expects a tensor of shape (*, 4) for q and a tensor of shape (*, 3) for v

Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as tens

Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten

Set requies_grad for all the networks. Args: nets (nn.Module | list[nn.Module]): A list of networks or a single network.

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

Zero out the parameters of a module and return it.

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

Convert rotations given as axis/angle to quaternions. Args: axis_angle: Rotations given as a vector in axis angle form,

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Build multiple optimizers from configs. If `cfgs` contains several dicts for optimizers, then a dict for each constructed optimizers will be r

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2