Device with "CPU" name is not registered in the InferenceEngine on CPU

[Yutkin__Dmitry]

I try to run inside Docker classification example on Python:

python dldt/inference-engine/ie_bridges/python/sample/classification_sample/classification_sample.py -m inceptionv3-int8-tf-0001.xml -i cat.jpg 

and get:

[ INFO ] Creating Inference Engine
[ INFO ] Loading network files:
	inceptionv3-int8-tf-0001.xml
	inceptionv3-int8-tf-0001.bin
Traceback (most recent call last):
  File "classification_sample.py", line 135, in <module>
    sys.exit(main() or 0)
  File "classification_sample.py", line 68, in main
    supported_layers = ie.query_network(net, "CPU")
  File "ie_api.pyx", line 101, in openvino.inference_engine.ie_api.IECore.query_network
RuntimeError: Device with "CPU" name is not registered in the InferenceEngine

Although, I run it on Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz.

Dockerfile:

FROM python:3.7

RUN apt-get update && apt-get install -y --no-install-recommends \
	wget \
	git \
	build-essential \
            cmake \
            curl \
            wget \
            libssl-dev \
            ca-certificates \
            git \
            libboost-regex-dev \
            gcc-multilib \
            g++-multilib \
            libgtk2.0-dev \
            pkg-config \
            unzip \
            automake \
            libtool \
            autoconf \
            libcairo2-dev \
            libpango1.0-dev \
            libglib2.0-dev \
            libgtk2.0-dev \
            libswscale-dev \
            libavcodec-dev \
            libavformat-dev \
            libgstreamer1.0-0 \
            gstreamer1.0-plugins-base \
            libusb-1.0-0-dev \
            libopenblas-dev \
            libpng-dev 

WORKDIR /opt

ARG OPENCV_VERSION="4.2.0"
ENV OPENCV_VERSION $OPENCV_VERSION

RUN pip install numpy

RUN curl -Lo opencv.zip https://github.com/opencv/opencv/archive/${OPENCV_VERSION}.zip && \
            unzip -q opencv.zip && \
            curl -Lo opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/${OPENCV_VERSION}.zip && \
            unzip -q opencv_contrib.zip && \
            rm opencv.zip opencv_contrib.zip && \
            cd opencv-${OPENCV_VERSION} && \
            mkdir build && cd build && \
            cmake -D CMAKE_BUILD_TYPE=RELEASE \
                  -D CMAKE_INSTALL_PREFIX=/usr/local \
                  -D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib-${OPENCV_VERSION}/modules \
                  -D WITH_JASPER=OFF \
                  -D BUILD_DOCS=OFF \
                  -D BUILD_EXAMPLES=OFF \
                  -D BUILD_TESTS=OFF \
                  -D BUILD_PERF_TESTS=OFF \
                  -D BUILD_opencv_java=NO \
                  -D BUILD_opencv_python=YES \
                  -D BUILD_opencv_python2=NO \
                  -D BUILD_opencv_python3=YES \
                  -D PYTHON3_EXECUTABLE=$(which python3.7) \
                  -D PYTHON_INCLUDE_DIR=/usr/local/include/python3.7m \
                  -D PYTHON_LIBRARY=/usr/local/lib/libpython3.7m.so \
                  -D PYTHON3_NUMPY_INCLUDE_DIRS=/usr/local/lib/python3.7/site-packages/numpy/core/include/ \
                  -D OPENCV_GENERATE_PKGCONFIG=ON .. && \
            make -j $(nproc --all) && \
            make preinstall && make install && ldconfig && \
            cd / && rm -rf opencv*

RUN git clone https://github.com/opencv/dldt.git && \
	cd dldt && \
	cd inference-engine && \
	git submodule init && \
	git submodule update --recursive

RUN pip install -r dldt/inference-engine/ie_bridges/python/requirements.txt

RUN cd dldt/inference-engine && \
	mkdir build && cd build && \
	cmake \
	-DCMAKE_BUILD_TYPE=Release \
	-DENABLE_CLDNN=OFF \
	-DENABLE_MKL_DNN=OFF \
	-DENABLE_PYTHON=ON \
	-DPYTHON_EXECUTABLE=`which python3.7` \
	-DPYTHON_LIBRARY=/usr/local/lib/libpython3.7m.so \
	-DPYTHON_INCLUDE_DIR=/usr/local/include/python3.7m .. && \
	make --jobs=$(nproc --all)

RUN export PYTHONPATH="$PYTHONPATH:/opt/dldt/inference-engine/bin/intel64/Release/lib/python_api/python3.7"

What am I doing wrong?

[Yutkin__Dmitry]

Output of hello_query_device.py:

python hello_query_device/hello_query_device.py
Available devices:

[Yutkin__Dmitry · Accepted solution]

Replacement of -DENABLE_MKL_DNN=OFF on -DENABLE_MKL_DNN=ON helped.