本人在将Yolov8的目标检测模型转换成,om格式后，利用华为给的yolov5的样例代码去跑，出现

[INFO] acl init success
[INFO] open device 0 success
[INFO] load model YOLOV8/model/EfficientNet/EfficientNet.om success
[INFO] create model description success

Traceback (most recent call last):
File "/home/HwHiAiUser/samples/YOLOV8/TEST.py", line 162, in <module>
infer_image(img_path, model, labels_dict, cfg)
File "/home/HwHiAiUser/samples/YOLOV8/TEST.py", line 78, in infer_image
draw_prediction(pred_all, image, class_names)
File "/home/HwHiAiUser/samples/YOLOV8/TEST.py", line 57, in draw_prediction
img_dw = draw_bbox(pred, image, (0, 255, 0), 2, labels)
File "/home/HwHiAiUser/samples/YOLOV8/TEST.py", line 36, in draw_bbox
img0 = cv2.putText(img0, str(idx) + ' ' + names[int(class_id)], (int(bbox[idx][0]), int(bbox[idx][1] + 16)),
KeyError: 8321
[INFO] unload model success, model Id is 1
[INFO] end to destroy context
[INFO] end to reset device is 0
[INFO] end to finalize acl

主要在于这个KeyError: 8321，不太明白为何出现标签字典超出这么多的情况，想请求大佬们的建议，抑或请提供一种可以实现npu推理的方法，万分感谢。