- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
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!
Link Copied

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page