Wind River Support Network

HomeDefectsLIN1021-221
Not to be fixed

LIN1021-221 : openvino: model convert fail

Created: May 23, 2021    Updated: Nov 3, 2021
Resolved Date: Nov 3, 2021
Previous ID: LINCD-5509
Found In Version: 10.21.20.1
Severity: Standard
Applicable for: Wind River Linux LTS 21
Component/s: Userspace

Description

Environment
======================
WRLinux Version: LTS21
Workbench Version:
Binary/FS From:
BSP/Configuration: intel-x86-64 + glibc-std
HOST OS:

Log location
======================

7. Symptom Details
****************************
root@intel-x86-64:/opt/wr-test/testcases/userspace/openvino_auto# /usr/share/openvino/open-model-zoo/tools/downloader/converter.py --name googlenet-v3 --mo /usr/share/openvino/model-optimizer/mo.py -d /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test -o /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test_converted
========== Converting googlenet-v3 to IR (FP16)
Conversion command: /usr/bin/python3 – /usr/share/openvino/model-optimizer/mo.py -framework=tf --data_type=FP16 --output_dir=/opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test_converted/public/googlenet-v3/FP16 --model_name=googlenet-v3 --reverse_input_channels 'input_shape=[1,299,299,3]' --input=input 'mean_values=input[127.5,127.5,127.5]' '-scale_values=input[127.5]' --output=InceptionV3/Predictions/Softmax --input_model=/opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test/public/googlenet-v3/inception_v3_2016_08_28_frozen.pb

/usr/share/openvino/model-optimizer/mo/main.py:89: SyntaxWarning: "is" with a literal. Did you mean "=="?
if op is 'k':
Model Optimizer arguments:
Common parameters:

    Path to the Input Model: /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test/public/googlenet-v3/inception_v3_2016_08_28_frozen.pb
    Path for generated IR: /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test_converted/public/googlenet-v3/FP16
    IR output name: googlenet-v3
    Log level: ERROR
    Batch: Not specified, inherited from the model
    Input layers: input
    Output layers: InceptionV3/Predictions/Softmax
    Input shapes: [1,299,299,3]
    Mean values: input[127.5,127.5,127.5]
    Scale values: input[127.5]
    Scale factor: Not specified
    Precision of IR: FP16
    Enable fusing: True
    Enable grouped convolutions fusing: True
    Move mean values to preprocess section: None
    Reverse input channels: True
    TensorFlow specific parameters:
    Input model in text protobuf format: False
    Path to model dump for TensorBoard: None
    List of shared libraries with TensorFlow custom layers implementation: None
    Update the configuration file with input/output node names: None
    Use configuration file used to generate the model with Object Detection API: None
    Use the config file: None
    [ WARNING ]
    Detected not satisfied dependencies:
    test-generator: installed: 0.1.2, required: == 0.1.1

Please install required versions of components or use install_prerequisites script
/usr/share/openvino/model-optimizer/install_prerequisites/install_prerequisites_tf2.sh
Note that install_prerequisites scripts may install additional components.
[ ERROR ] Error while emitting attributes for layer InceptionV3/InceptionV3/Conv2d_1a_3x3/Relu (id = 9). It usually means that there is unsupported pattern around this node or unsupported combination of attributes.
[ WARNING ] Could not find the Inference Engine Python API. At this moment, the Inference Engine dependency is not required, but will be required in future releases.
[ WARNING ] Consider building the Inference Engine Python API from sources or try to install OpenVINO (TM) Toolkit using "install_prerequisites.sh"
Model Optimizer version: unknown version
FAILED:
googlenet-v3

root@intel-x86-64:/opt/wr-test/testcases/userspace/openvino_auto# /usr/share/openvino/open-model-zoo/tools/downloader/converter.py --name googlenet-v2 --mo /usr/share/openvino/model-optimizer/mo.py -d /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test -o /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test_converted
========== Converting googlenet-v2 to IR (FP16)
Conversion command: /usr/bin/python3 – /usr/share/openvino/model-optimizer/mo.py -framework=caffe --data_type=FP16 --output_dir=/opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test_converted/public/googlenet-v2/FP16 --model_name=googlenet-v2 'input_shape=[1,3,224,224]' --input=data '-mean_values=data[104.0,117.0,123.0]' --output=prob --input_model=/opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test/public/googlenet-v2/googlenet-v2.caffemodel --input_proto=/opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test/public/googlenet-v2/googlenet-v2.prototxt

Model Optimizer arguments:
Common parameters:

    Path to the Input Model: /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test/public/googlenet-v2/googlenet-v2.caffemodel
    Path for generated IR: /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test_converted/public/googlenet-v2/FP16
    IR output name: googlenet-v2
    Log level: ERROR
    Batch: Not specified, inherited from the model
    Input layers: data
    Output layers: prob
    Input shapes: [1,3,224,224]
    Mean values: data[104.0,117.0,123.0]
    Scale values: Not specified
    Scale factor: Not specified
    Precision of IR: FP16
    Enable fusing: True
    Enable grouped convolutions fusing: True
    Move mean values to preprocess section: None
    Reverse input channels: False
    Caffe specific parameters:
    Path to Python Caffe* parser generated from caffe.proto: /usr/share/openvino/model-optimizer/mo/front/caffe/proto
    Enable resnet optimization: True
    Path to the Input prototxt: /opt/wr-test/testcases/userspace/openvino_auto/tmp/model_for_test/public/googlenet-v2/googlenet-v2.prototxt
    Path to CustomLayersMapping.xml: Default
    Path to a mean file: Not specified
    Offsets for a mean file: Not specified
    [ WARNING ]
    Detected not satisfied dependencies:
    test-generator: installed: 0.1.2, required: == 0.1.1

Please install required versions of components or use install_prerequisites script
/usr/share/openvino/model-optimizer/install_prerequisites/install_prerequisites_caffe.sh
Note that install_prerequisites scripts may install additional components.
[ ERROR ] Error while emitting attributes for layer conv1/7x7_s2/bn/sc/relu (id = 7). It usually means that there is unsupported pattern around this node or unsupported combination of attributes.
[ WARNING ] Could not find the Inference Engine Python API. At this moment, the Inference Engine dependency is not required, but will be required in future releases.
[ WARNING ] Consider building the Inference Engine Python API from sources or try to install OpenVINO (TM) Toolkit using "install_prerequisites.sh"
Model Optimizer version: unknown version
FAILED:
googlenet-v2

Steps to Reproduce

8. Steps To Reproduce
****************************
Refer to:
https://gitlab.devstar.cloud/wrlx/wrlinux-testing/testcases/-/blob/master/wr-testing/userspace/Documentation/testApproach_LINUXEXEC-7854_openvino.txt
Live chat
Online