get the index of the node :param node_name: the name of the node :type node_name: string :rtype: int

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

Create more task primitives from a task for the plotter

Construct a skeleton state from rotation and root translation :param skeleton_tree: the skeleton tree :type skeleton_tree: S

Return homogeneous rotation matrix from quaternion. >>> M = quaternion_matrix([0.99810947, 0.06146124, 0, 0]) >>> numpy.allclose(M, rotation_

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

Convert 3d vector of axis-angle rotation to 4x4 rotation matrix Args: angle_axis (Tensor): tensor of 3d vector of axis-angle rotations.

quaternion multiplication

Return length, i.e. Euclidean norm, of ndarray along axis. >>> v = numpy.random.random(3) >>> n = vector_norm(v) >>> numpy.allclose(n, nu

Return length, i.e. Euclidean norm, of ndarray along axis. >>> v = numpy.random.random(3) >>> n = vector_norm(v) >>> numpy.allclose(n, nu

Pose should be batch_size x 72

Rotate a 3D vector with the 3D rotation

Return ndarray normalized by length, i.e. Euclidean norm, along axis. >>> v0 = numpy.random.random(3) >>> v1 = unit_vector(v0) >>> numpy.

Return ndarray normalized by length, i.e. Euclidean norm, along axis. >>> v0 = numpy.random.random(3) >>> v1 = unit_vector(v0) >>> numpy.

Create a 3D rotation from angle and axis of rotation. The rotation is counter-clockwise along the axis. The rotation can be interpreted as

Return multiplication of two quaternions. >>> q = quaternion_multiply([4, 1, -2, 3], [8, -5, 6, 7]) >>> numpy.allclose(q, [28, -44, -14, 48])

Return inverse of quaternion. >>> q0 = random_quaternion() >>> q1 = quaternion_inverse(q0) >>> numpy.allclose(quaternion_multiply(q0, q1)

Return homogeneous rotation matrix from quaternion. >>> M = quaternion_matrix([0.99810947, 0.06146124, 0, 0]) >>> numpy.allclose(M, rotation_

Construct an ordered dictionary from the object :rtype: OrderedDict

transform states before going into policy net

Get translation from transform

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

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

The inverse of the rotation

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

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

Construct a transform from a quaternion and 3D translation. Only one of them can be None.

Get rotation from transform