|
|
我在将onnx转换为量化后的rknn模型后，执行rknn.init_runtime时报错，内容如下
Loading RKNN model ../models/coco_tracking.rknn
done
--> init runtime
D target set by user is: rk3399pro
D Start adb...
D Connect to Device success!
D NPUTransfer: Transfer spec = local:transfer_proxy
D NPUTransfer: Transfer interface successfully opened, fd = 4
D NPUTransfer: The connection has been closed, socket read fd = 4
D NPUTransfer: Transfer client closed, fd = 4
E RKNNAPI: rknn_init, recv(MsgLoadAck) fail, -9(ERROR_PIPE) != 368!
E Catch exception when init runtime!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 1067, in rknn.api.rknn_base.RKNNBase.init_runtime
E File "rknn/api/rknn_runtime.py", line 326, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_DEVICE_UNAVAILABLE
如果不执行量化操作是没有这个问题的，但是将rknn.build中的do_quantization改为True后就报了该错误
希望能得到回答，谢谢
|
|
收藏
闽公网安备 35010202001061号