Missing method clear_non_cond_mem_around_input

[tonydavis629]

SAM2VideoPredictor is missing a method self._clear_obj_non_cond_mem_around_input that is referenced in propagate_in_video.

if self.clear_non_cond_mem_around_input:
# clear non-conditioning memory of the surrounding frames
self._clear_obj_non_cond_mem_around_input(
inference_state, frame_idx, obj_idx)

I ask because SAM2VideoPredictor's inference_state grows endlessly with video length, I am trying to reduce memory consumption on inference_state, and it seems like this was considered but maybe forgotten?