rknn_batch_size问题

如题所示,当ret = rknn.build(do_quantization=do_quant, dataset=DATASET_PATH,rknn_batch_size=8).设定为8时推理部分的代码应该如何去进行改进才能正常进行推理呢?
当前报错:
Traceback (most recent call last):
  File "/home/admin/projects/rknn/rknn_model_zoo/examples/yolov7/python/yolov7.py", line 272, in <module>
    draw(img_p, co_helper.get_real_box(boxes), scores, classes)
  File "/home/admin/projects/rknn/rknn_model_zoo/examples/yolov7/python/yolov7.py", line 167, in draw
    print("%s @ (%d %d %d %d) %.3f" % (CLASSES[cl], top, left, right, bottom, score))
IndexError: tuple index out of range


多batchsize是否可以提高推理效率呢？

自己解决了这个推理问题,但是请问 RKNN的 多batchsize是否可以提高推理效率呢？ 我这边没有实际验证过