Toybrick

标题: 加载rknn模型出错:RKNN_ERR_MODEL_INVALID [打印本页]

作者: jandriux    时间: 2019-10-10 14:04
标题: 加载rknn模型出错:RKNN_ERR_MODEL_INVALID
1、tensorflow生成的pb模型,在电脑上测试可以使用
2、pb模型转rknn模型时,可以转换,并且没有报错
3、推理时,加载rknn模型时,init_runtime,出现错误:
/usr/lib64/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
loading model
loading model done
init runtime environment
E RKNNAPI: rknn_init,  msg_load_ack fail, ack = 1, expect 0!
E Catch exception when init runtime!
T Traceback (most recent call last):
T   File "rknn/api/rknn_base.py", line 617, in rknn.api.rknn_base.RKNNBase.init_runtime
T   File "rknn/api/rknn_runtime.py", line 378, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
T Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
init runtime environment failed

请问大概是因为哪边出现了问题


作者: jefferyzhang    时间: 2019-10-10 14:55
1. 可能是rknn模型文件有问题,pb转完rknn是否做过模拟。
2. rknntoolkit和driver版本是否过低,dnf update到最新版本试试
3. rknntoolkit 1.2如果有问题,可以使用1.1尝试。




欢迎光临 Toybrick (https://t.rock-chips.com/) Powered by Discuz! X3.3