Read the object from an ordered dictionary :param dict_repr: the ordered dictionary that is used to construct the object :type dict_

1-D Gaussian filter. Parameters ---------- %(input)s sigma : scalar standard deviation for Gaussian kernel %(axis)s o

Retrieves param value for the given prop and attr from the sample.

Pose should be batch_size x 156

Local pose

Check if points are inside rectangles using vectorized operations. Args: points: torch.Tensor of shape [bs, 2] representing batched

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

Pose error: MPJPE after rigid alignment (scale, rotation, and translation), often referred to as "Protocol #2" in many papers.

Visualize a skeleton state :param skeleton_state: :param task_name: :type skeleton_state: SkeletonState :type task_name: string,

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

Construct identity 3D rotation with the same shape

Return quaternion from rotation matrix. If isprecise is True, the input matrix is assumed to be a precise rotation matrix and a faster algori

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 ten

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

Return uniform random unit quaternion. rand: array like or None Three independent random variables that are uniformly distributed

Get Forward Direction

Render the current simulation state to the screen or off-screen buffer. Call this in your main loop.

q: size(Bx4) Output: size(Bx3)

Step the environment forward.

Take the sum over all non-batch dimensions.

Construct an ordered dictionary from the object :rtype: OrderedDict

Write the object to a file (either .npy or .json) :param path: path of the file :type path: string

Inverse transformation

This method is called when the viewer is initialized and after every reset Optionally implement this method, if you need to tinker wi

should be called from wrappers of model classes such as ClassifierFreeSampleModel