r"""Warps an image or tensor from source into reference frame. Args: patch_src (torch.Tensor): The image or tensor to warp.

Inputs: batch1: actor_dim, 0th -> 0th actor is ego batch2: scene_dim, all the other agents under ith ego agent - h_states: Tensor of shape (b

X: b, T, 2 return: b, F

>>> Input: x_true: N, T_p, 2 x_hat: N, T_p, 2 f: N, f (128+16) >>> Output: x_hat_aft

Inputs: - h_states: Tensor of shape (num_layers, batch, h_dim) - seq_start_end: A list of tuples which delimit sequences with

X: b, T, 2 return: b, F

>>> Input: x_true: N, T_p, 2 x_hat: N, T_p, 2 f: N, f (128+16) >>> Output: x_hat_aft

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

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

load a list of files or folders from a system path parameters: folder_path: root to search ext_filter: a string to r

load data or string from text file