Instantiate object from config

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

Reset the losses to 0.

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

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

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.

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

Update the loss and return the weighted loss.

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

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

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

Get object from string

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

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

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

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

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

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

Mean per-joint position error (i.e. mean Euclidean distance) often referred to as "Protocol #1" in many papers.

Recursively find all files in the specified directory. Args: base (str): The base directory to start the search. Returns:

get global offsets given a skeleton

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

INPUT: smplx_data: (bs, frames, 322) RETURN: vertices: joints: pose: faces:

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

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

Recover joint positions from the given motion capture data using root rotation information. Args: data (torch.Tensor): Input motion

Recover root rotation and position from the given motion capture data. Args: data (torch.Tensor): Input motion capture data with sha

固定随机种子以确保结果可复现 参数: seed (int): 随机种子，默认为42

load T2M text encoder and motion encoder for evaluating

load T2M text encoder and motion encoder for evaluating

load T2M text encoder and motion encoder for evaluating

使用多线程并行加载数据

Convert AMASS SMPL-X motion data to pose representation and save joint positions. Args: src_motion (torch.Tensor): Input SMPL-X moti

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

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

Computes a similarity transform (sR, t) that takes a set of 3D points S1 (3 x N) closest to a set of 3D points S2, where R is an 3x3 rota

Mean joint acceleration error often referred to as "Protocol #1" in many papers.