Inputs: -tensor: 2D tensor of any shape -num_reps: Number of times to repeat each row Outpus: -repeat_tensor:

print a string to a log file parameters: print_str: a string to print log: a opened file to save the log same_line:

return clustering ncluster of x. Args: x (Tensor): B, K, 2 ncluster (int, optional): Number of clusters. Defaults to 20. iter (int, option

convert path to a valid OS format, e.g., empty string '' to '.', remove redundant '/' at the end from 'aa/' to 'aa' parameters: input_pa

if '.' exists in the subfolder, the function still justifies it as a folder. e.g., /mnt/dome/adhoc_0.5x/abc is a folder if '.' exists after all sla

This function is just like np.linspace, but will create linearly spaced vectors from a start to end vector. Inputs: a - Start vector.

copy a list to the buffer for use parameters: input_data: a list outputs: safe_data: a copy of input data

Creates a rotation matrix out of angles in degrees Args: angle: (torch.Tensor): tensor of angles in degrees, any shape. Returns:

As the input is a map and the warp_affine works on an image coordinate system we would have to flip the y axis updown, negate the ang

r"""Function that converts points from homogeneous to Euclidean space. Examples:: >>> input = torch.rand(2, 4, 3) # BxNx3 >>> out

r"""Function that converts points from Euclidean to homogeneous space. Examples:: >>> input = torch.rand(2, 4, 3) # BxNx3 >>> out

Generates a coordinate grid for an image. When the flag `normalized_coordinates` is set to True, the grid is normalized to be in the range [-1

r"""Function that converts angles from degrees to radians. Args: tensor (torch.Tensor): Tensor of arbitrary shape. Returns: to

given two time frame arrays, find then min dist

given two time frame arrays, find then min dist (time)

Returns rotated patches of each map around the transformed scene points. ___________________ | | | |

r"""Calculates an affine matrix of 2D rotation. The function calculates the following matrix: .. math:: \begin{bmatrix} \a