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

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

Write the sequence of args, with no separators, to the console and output files (if you've configured an output file).

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

Take the mean over all non-batch dimensions.

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

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

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

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.

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

Loss function for body fitting

find the quaternion used to rotate v0 to v1

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

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

Angle prior that penalizes unnatural bending of the knees and elbows

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