in sam2/sam2_video_predictor.py [0:0]
def _obj_id_to_idx(self, inference_state, obj_id):
"""Map client-side object id to model-side object index."""
obj_idx = inference_state["obj_id_to_idx"].get(obj_id, None)
if obj_idx is not None:
return obj_idx
# This is a new object id not sent to the server before. We only allow adding
# new objects *before* the tracking starts.
allow_new_object = not inference_state["tracking_has_started"]
if allow_new_object:
# get the next object slot
obj_idx = len(inference_state["obj_id_to_idx"])
inference_state["obj_id_to_idx"][obj_id] = obj_idx
inference_state["obj_idx_to_id"][obj_idx] = obj_id
inference_state["obj_ids"] = list(inference_state["obj_id_to_idx"])
# set up input and output structures for this object
inference_state["point_inputs_per_obj"][obj_idx] = {}
inference_state["mask_inputs_per_obj"][obj_idx] = {}
inference_state["output_dict_per_obj"][obj_idx] = {
"cond_frame_outputs": {}, # dict containing {frame_idx: <out>}
"non_cond_frame_outputs": {}, # dict containing {frame_idx: <out>}
}
inference_state["temp_output_dict_per_obj"][obj_idx] = {
"cond_frame_outputs": {}, # dict containing {frame_idx: <out>}
"non_cond_frame_outputs": {}, # dict containing {frame_idx: <out>}
}
return obj_idx
else:
raise RuntimeError(
f"Cannot add new object id {obj_id} after tracking starts. "
f"All existing object ids: {inference_state['obj_ids']}. "
f"Please call 'reset_state' to restart from scratch."
)