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

Loss function for camera optimization.

Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See co

Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See co

If comm is provided, average all numerical stats across that comm

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

look for all file in save directory in the pattent of model{number}.pt and return the one with the highest step number. TODO: Imp

Local pose

Geman-McClure error function

Copy model parameters into a (differently-shaped) list of full-precision parameters.

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

This function computes the perspective projection of a set of points. Input: points (bs, N, 3): 3D points rotation (bs, 3, 3)

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

Enforce quaternion continuity across the time dimension by selecting the representation (q or -q) with minimal distance (or, equivalently, ma

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

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

Take the sum over all non-batch dimensions.

should be called from wrappers of model classes such as ClassifierFreeSampleModel

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

Converts 6D rotation representation by Zhou et al. [1] to euler angles using Gram--Schmidt orthogonalisation per Section B of [1]. :para

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 = [

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