openvino : R3
when I run demo_squeezenet_download_convert_run.bat I got this error:
target = CPU
target_precision = FP16
ECHO is off.
###############|| Build Inference Engine samples using MS Visual Studio (MSBuild.exe) ||###############
Waiting for 0 seconds, press a key to continue ...
C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\MSBuild\15.0\Bin\MSBuild.exe" Samples.sln /p:Configuration=Release /t:classification_sample_async /clp:ErrorsOnly /m
Microsoft (R) Build Engine version 15.9.21+g9802d43bc3 for .NET Framework
Copyright (C) Microsoft Corporation. All rights reserved.
Waiting for 6 seconds, press a key to continue ...
###############|| Run Inference Engine classification sample ||###############
Waiting for 2 seconds, press a key to continue ...
1 file(s) copied.
classification_sample_async.exe -i "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\demo\\car.png" -m "C:\Users\two\Documents\Intel\OpenVINO\openvino_models\ir\FP16\public\squeezenet1.1\squeezenet1.1.xml" -d CPU
[ INFO ] InferenceEngine:
API version ............ 2.1
Build .................. 30677
Description ....... API
[ INFO ] Parsing input parameters
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ] Creating Inference Engine
MKLDNNPlugin version ......... 2.1
Build ........... 30677
[ INFO ] Loading network files
[ ERROR ] Error loading xmlfile: C:\Users\two\Documents\Intel\OpenVINO\openvino_models\ir\FP16\public\squeezenet1.1\squeezenet1.1.xml... File was not found at line: 1 pos: 0
And I read this print info I found that convert model is not execute, so, I delete the exist squeezenet1.1 folder, and try again. This time I got another error like this:
AttributeError: 'Graph' object has no attribute 'node'
What can I do to fix this bug? How can I know I have install openvino successful
Warning: please expect that Model Optimizer conversion might be slow.
You can boost conversion speed by installing protobuf-*.egg located in the
"model-optimizer\install_prerequisites" folder or building protobuf library from sources.
For more information please refer to Model Optimizer FAQ, question #80.
I found I have this warning, Does this have relation to this bug?
When we tried out from our end, it worked without these errors.
Can you please provide the below details :
1. OpenVINO Version (You can check for which Intel Distribution of OpenVINO is installed, from Windows Control Panel Program list).
2. Are you trying with CPU only or is any VPU device connected to system? Which is your processor, with generation?
3. Run the demo_security_barrier_camera.bat demo also. Did you get the same error?
Please provide the complete console output/screenshot of the error.
I have try the three OpenVINO version:w_openvino_toolkit_p_2019.1.148, w_openvino_toolkit_p_2019.2.275,w_openvino_toolkit_p_2019.3.334 and when I run demo_squeezenet_download_convert_run.bat, I got the same error: AttributeError: 'Graph' object has no attribute 'node'.
I'm now only run with CPU and may be run with NCS2 in the future. My processor is inter Core I7-4790,
I can run demo_security_barrier_camera.bat successful.
Also, I have try with the docker. I run docker in my win10 system, and I also get the same error: AttributeError: 'Graph' object has no attribute 'node'. and when I run again, I got the error:squeezenet1.1\squeezenet1.1.xml, File was not found at line: 1 pos: 0
Here is my Dockerfile:
RUN apt-get update && apt-get install -y --no-install-recommends \
lsb-release && \
rm -rf /var/lib/apt/lists/*
RUN mkdir -p $TEMP_DIR
COPY ./l_openvino_toolkit_p_2019.3.334.solitairetheme8 $TEMP_DIR/l_openvino_toolkit_p_2019.3.334.tgz
RUN cd $TEMP_DIR && \
tar xf l_openvino_toolkit*.tgz && \
cd l_openvino_toolkit* && \
sed -i 's/decline/accept/g' silent.cfg && \
./install.sh -s silent.cfg && \
rm -rf $TEMP_DIR
# build Inference Engine samples
RUN mkdir $INSTALL_DIR/deployment_tools/inference_engine/samples/build && cd $INSTALL_DIR/deployment_tools/inference_engine/samples/build && \
/bin/bash -c "source $INSTALL_DIR/bin/setupvars.sh && cmake .. && make -j1"
And now I'm suspect my steps is wrong, Here is my steps:
- run setupvars.bat
- run install_prerequisites_caffe.bat and install_prerequisites_tf.bat
- run demo_squeezenet_download_convert_run.bat
Have any steps I have forgot?
There may be a compatibility issue with the networkx package. Could you try and install version 2.3 using the command "pip3 install networkx==2.3". Try to run the demo again and let me know if it works.
Intel Customer Support Technician
A Contingent Worker at Intel