Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6403 Discussions

Supported primitive descriptors list is empty for node: Mean

He__Zhenwei
Beginner
492 Views

I am porting a pyhong cv program into c++. It includes two models.

When I run my ported program with first model, it works fine.

Anyway, when I trying to run it with a second model, an error occured:

 

terminate called after throwing an instance of 'InferenceEngine::details::InferenceEngineException'
  what():  Supported primitive descriptors list is empty for node: Mean
/teamcity/work/scoring_engine_build/releases_2018_R5/src/mkldnn_plugin/mkldnn_node.cpp:232
/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/inference_engine/include/details/ie_exception_conversion.hpp:71

 

it happens in this code line:
    result.exe_net = plugin.LoadNetwork(cnn_network, {});

 

I looked everywhere else but seems no one experienced same issue.

Some one told me to use latest openvino, but I am already using it. (using file: l_openvino_toolkit_p_2019.1.094.tgz)

 

Also I am guesssing that maybe something wrong with my xml file, so i post the "Mean part" here see if anyone can see something into it.


        <layer id="1" name="Mean" precision="FP32" type="Pooling">
            <data exclude-pad="true" kernel="40,140,1" pads_begin="0,0,0" pads_end="0,0,0" pool-method="avg" rounding-type="ceil" strides="1,1,1"/>
            <input>
                <port id="0">
                    <dim>1</dim>
                    <dim>1</dim>
                    <dim>40</dim>
                    <dim>140</dim>
                </port>
            </input>
            <output>
                <port id="1">
                    <dim>1</dim>
                    <dim>1</dim>
                    <dim>1</dim>
                    <dim>1</dim>
                </port>
            </output>
        </layer>

 

 

Any thought or suggestion ?

Thanks a lot!

0 Kudos
0 Replies
Reply