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.

The inverse of the rotation

Rotate a 3D vector with the 3D rotation

Construct 3D rotation from quaternion (the quaternion needs not to be normalized).

Take the mean over all non-batch dimensions.

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

Build dataset by the given config.

Observe humanoid body position, velocities, and angles.

Observe humanoid body position, velocities, and angles.

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.

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

Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re

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)

Combine two set of 3D rotations together using \**\* operator. The shape needs to be broadcastable

Run one epoch of evaluation.

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

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

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

Convert rotations given as Euler angles in radians to rotation matrices. Args: euler_angles: Euler angles in radians as tensor of sh

Convert rotations given as rotation matrices to Euler angles in radians. Args: matrix: Rotation matrices as tensor of shape (..., 3,

The (angle, axis) representation of the rotation. The axis is normalized to unit length. The angle is guaranteed to be between [0, pi].

The inverse of the rotation

quaternion multiplication

quaternion multiplication

Combine two set of 3D rotations together using \**\* operator. The shape needs to be broadcastable

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

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

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

Run one timestep of the environment's dynamics.

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.

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

Build attention.

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

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.

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mode

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

quaternion with its imaginary part negated

quaternion with its imaginary part negated