运行语音命令识别的实例报错 error code: RKNN_ERR_MODEL_INVALID

[复制链接] · 发表于 2019-6-12 09:18:51

[root@localhost sc]# python3 test_zhuan.py
/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
done
--> Building model
done

[root@localhost sc]# python3 test.py
/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
load_rknn done
--> Init runtime environment
E RKNNAPI: rknn_init,  input_reorder == INPUT_REORDER_NA when n_dims==3!
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
[root@localhost sc]#

只看该作者 · 发表于 2019-6-12 09:57:05

本帖最后由 zsf 于 2019-6-12 09:58 编辑

在板子上的安装的是rknn_toolkit-1.0.0-cp36-cp36m-linux_aarch64.whl这个版本在调用rknn.init_runtime()时出异常。

只看该作者 · 发表于 2020-3-26 16:41:52

zsf 发表于 2019-6-12 09:57
在板子上的安装的是rknn_toolkit-1.0.0-cp36-cp36m-linux_aarch64.whl这个版本在调用rknn.init ...

你好，请教一下这个问题你解决了吗