跑官方历程出错

Init runtime environment
E Using device with adb mode to init runtime, but npu_transfer_proxy is running, it may cause conflict. Please terminate npu_transfer_proxy first.
E Catch exception when init runtime!
T Traceback (most recent call last):
T   File "rknn/api/rknn_base.py", line 643, in rknn.api.rknn_base.RKNNBase.init_runtime
T   File "rknn/api/rknn_runtime.py", line 130, in rknn.api.rknn_runtime.RKNNRuntime.__init__
T   File "rknn/api/rknn_platform_utils.py", line 263, in rknn.api.rknn_platform_utils.start_ntp_or_adb
T Exception: Init runtime environment failed!

按照提示，把后台的npu_transfer_proxy进程先杀掉再试试

杀死npu_transfer_proxy进程之后出了新的错误：


[toybrick@localhost mobilenet_v2]$ 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 f`np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
--> config model
done
--> Loading model
done
--> Building model
done
--> Export RKNN model
done
--> Init runtime environment
E Connect to Device Failure (-1)
E Catch exception when init runtime!
T Traceback (most recent call last):
T   File "rknn/api/rknn_base.py", line 643, in rknn.api.rknn_base.RKNNBase.init_runtime
T   File "rknn/api/rknn_runtime.py", line 130, in rknn.api.rknn_runtime.RKNNRuntime.__init__
T   File "rknn/api/rknn_platform_utils.py", line 269, in rknn.api.rknn_platform_utils.start_ntp_or_adb

troy 发表于 2019-9-3 14:56
按照提示，把后台的npu_transfer_proxy进程先杀掉再试试

杀死npu_transfer_proxy进程之后出了新的错误：


[toybrick@localhost mobilenet_v2]$ 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 f`np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
--> config model
done
--> Loading model
done
--> Building model
done
--> Export RKNN model
done
--> Init runtime environment
E Connect to Device Failure (-1)
E Catch exception when init runtime!
T Traceback (most recent call last):
T   File "rknn/api/rknn_base.py", line 643, in rknn.api.rknn_base.RKNNBase.init_runtime
T   File "rknn/api/rknn_runtime.py", line 130, in rknn.api.rknn_runtime.RKNNRuntime.__init__
T   File "rknn/api/rknn_platform_utils.py", line 269, in rknn.api.rknn_platform_utils.start_ntp_or_adb

跑的官方例程是： rknn-toolkit-V1.1.0/example/mobilenet_v2

jiangjuncmy 发表于 2019-9-3 17:51
跑的官方例程是： rknn-toolkit-V1.1.0/example/mobilenet_v2

确认下计算棒是否连接，计算棒是否为slave模式。确认计算棒是否连接可以看是否识别到一个优盘设备。

troy 发表于 2019-9-3 17:56
确认下计算棒是否连接，计算棒是否为slave模式。确认计算棒是否连接可以看是否识别到一个优盘设备。 ...

我用的不是计算棒，用的是开发板rk3399pro

hisping 发表于 2019-9-4 08:33
你是在3399prod上直接跑的是吧？是否按照wiki上安装了环境，rknn-toolkit下的用例我们都有验证过的 ...

我也是3399prod上跑的出了一样的错误，rknn-toolkit用的rknn-toolkit-V1.1.0

确认下版本是否适配
版本确认：
[toybrick@localhost build]$ rpm -qa rknn-api npuservice
rknn-api-0.9.8-1.rockchip.fc28.aarch64
npuservice-1.0.4-1.rockchip.fc28.aarch64
运行时版本打印如下：
D RKNNAPI: ==============================================
D RKNNAPI: RKNN VERSION:
D RKNNAPI:   API: 0.9.8 (e0c7840 build: 2019-06-28 10:49:53)
D RKNNAPI:   DRV: 0.9.8 (943f8e8 build: 2019-07-03 17:51:17)
D RKNNAPI: ==============================================