标题: 运行rknn_toolkit中的example时候报错 [打印本页] 作者: sunxing 时间: 2019-5-5 19:35 标题: 运行rknn_toolkit中的example时候报错 (rknn) root@d5b771b0883d:~/rknn-toolkit/rknn-toolkit/example/mobilenet-ssd# python3 ssd.py
--> Loading model
done
--> Building model
E Catch exception when building RKNN model!
T Traceback (most recent call last):
T File "rknn/api/rknn_base.py", line 459, in rknn.api.rknn_base.RKNNBase.build
T File "rknn/api/rknn_base.py", line 952, in rknn.api.rknn_base.RKNNBase._quantize
T File "rknn/base/RKNNlib/app/tensorzone/workspace.py", line 231, in rknn.base.RKNNlib.app.tensorzone.workspace.Workspace.load_data
T File "rknn/base/RKNNlib/app/tensorzone/graph.py", line 32, in rknn.base.RKNNlib.app.tensorzone.graph.Graph.load_data
T File "rknn/base/RKNNlib/RKNNnet.py", line 379, in rknn.base.RKNNlib.RKNNnet.RKNNNet.load_data
T File "rknn/base/RKNNlib/RKNNnet.py", line 391, in rknn.base.RKNNlib.RKNNnet.RKNNNet._load_old_data
T File "rknn/base/RKNNlib/RKNNnet.py", line 392, in rknn.base.RKNNlib.RKNNnet.RKNNNet._load_old_data
T File "/root/rknn-toolkit/rknn-toolkit/rknn/lib/python3.6/site-packages/numpy/lib/npyio.py", line 447, in load
T pickle_kwargs=pickle_kwargs)
T File "/root/rknn-toolkit/rknn-toolkit/rknn/lib/python3.6/site-packages/numpy/lib/format.py", line 692, in read_array
T raise ValueError("Object arrays cannot be loaded when "
T ValueError: Object arrays cannot be loaded when allow_pickle=False
done
E RKNN model data is None, please load model first!
--> Init runtime environment
done
--> Running model
E RKNN model is None, please load model first!
done
inference result: None
Traceback (most recent call last):
File "ssd.py", line 88, in <module>
predictions = outputs[1].reshape((1, NUM_RESULTS, 4))
TypeError: 'NoneType' object is not subscriptable
我直接在PC上跑
有人遇到这个问题吗?
说明:
1、我是在docker中,安装了cuda以及cudnn
2、系统:
(rknn) root@d5b771b0883d:~/rknn-toolkit/rknn-toolkit/example/mobilenet-ssd# uname -a
Linux d5b771b0883d 4.18.0-18-generic #19~18.04.1-Ubuntu SMP Fri Apr 5 10:22:13 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux