Community
cancel
Showing results for 
Search instead for 
Did you mean: 
137 Views

2019 R1 Calibration Tool Error

Hi

I converted my Caffe model to IR using the latest version (2019 R1). Now I'm trying to use the calibration tool sample to convert my FP32 model to INT8. I'm able to load the model as FP32 and get the accuracy but it throws an error while loading the model for the first iteration of INT8, precisely in this line:

ExecutableNetwork executable_network = _pluginI8C.LoadNetwork(network, { { CONFIG_KEY(EXCLUSIVE_ASYNC_REQUESTS), CONFIG_VALUE(YES) } });

The message on the console:

[ INFO ] InferenceEngine:
        API version ............ 1.6
        Build .................. 22443
[ INFO ] Parsing input parameters
[ INFO ] Loading plugin

        API version ............ 1.6
        Build .................. 22443
        Description ....... MKLDNNPlugin
[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Collecting accuracy metric in FP32 mode to get a baseline, collecting activation statistics
Progress: [....................] 100.00% done
  FP32 Accuracy: 95.45%
[ INFO ] Verification of network accuracy if all possible layers converted to INT8
Validate int8 accuracy, threshold for activation statistics = 100.00
[ ERROR ] Inference problem:
Supported primitive descriptors list is empty for node: Mul_722/FusedScaleShift_
..\src\mkldnn_plugin\mkldnn_node.cpp:224
f:\intelswtools\openvino_2019.1.087\deployment_tools\inference_engine\include\details\ie_exception_conversion.hpp:71

Please let me know how to resolve this issue.

Thanks,

Indrajit

0 Kudos
9 Replies
Shubha_R_Intel
Employee
137 Views

Dear  Indrajit, before using the calibration tool, please use one of the openvino samples and run inference on your model. Does it work ? 

Thanks,

Shubha

 

 

137 Views

Hi Shubha Yes, I get proper results when inference is run with the FP32 model. Thanks Indrajit
Shubha_R_Intel
Employee
137 Views

Dear  Indrajit,

Thank you verifying. Is this Caffe model available in the public domain ? Or is it your personal one ? If it is your model, please send it to me over PM. 

Thanks,

Shubha

137 Views

Shubha, 

Could you please send me a message so that I can reply to it.

Thanks,

Indrajit

Shubha_R_Intel
Employee
137 Views

Hi Indrajit, I just PM'd you. I hope you got the message ?

Thanks,

Shubha

Edward_S_Intel1
Employee
137 Views

Hi Indrajit,

1. Firstly, can you rerun calibration tool with additional command line arguments (CPU extension), please:

-l C:\Users\sdramani\Documents\Intel\OpenVINO\inference_engine_samples_build_2017\intel64\Release\cpu_extension.dll

I hope everything should work with that.

2. Secondly, I would like to suggest to use Python Calibration Tool: https://docs.openvinotoolkit.org/latest/_inference_engine_tools_calibration_tool_README.html. Python Calibration Tool supports more datasets and topologies.

Best regards, Edward

Shubha_R_Intel
Employee
137 Views

Dear Indrajit, I already tried what Edward suggested (adding -l cpu_extension.dll). Still got the same error.  Does it work for you ? If  adding -l fails, it's a bug (which I've already filed).

Thanks,

Shubha

137 Views

Hi Edward,

Adding CPU extension didn't work.

Also, I have tried the python calibration tool which gives the same error.

Thanks

Indrajit

Shubha_R_Intel
Employee
137 Views

Dear Indrajit, 

can you kindly supply the full Python calibrate.py command you used here ?

Thanks,

Shubha

Reply