Args: obj_encoding: Tensor of shape [B, O, D]. part_pose: Tensor of shape [B, M, P] part_presence: Tensor of shape [B, M] or None; if it exists, it indicates which input parts exist. Returns: A bunch of stuff.
(self,
obj_encoding: torch.Tensor,
part_pose: torch.Tensor,
part_presence: torch.Tensor = None)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected