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.

Error while running Interpolate on CPU

Wang__Jie1
Beginner
636 Views

VINO Version: 2020.1.023

Tensorflow Version: 1.10.0

System: Ubuntu 18.04

Python: 3.6.5

First I use vino version  2019.3.376,  Model Optimizer faild to  generated IR. Then I download the latest version 2020.1.023,  Model Optimizer successfully generated IR, but my IE fails with the follow info:

terminate called after throwing an instance of 'InferenceEngine::details::InferenceEngineException'
  what():  Interpolate operation should be converted to Interp

 

Whan should I do to get rid of this error?

0 Kudos
3 Replies
Sahira_Intel
Moderator
636 Views

Hi Jie,

A few questions for you:

  1. Is this a Caffe or Tensorflow model? 
  2. Is this a custom trained model or a pretrained model? Can you please provide your model so I can look at it?
  3. Can you please provide the command you used to convert your model?

Best Regards,

Sahira 

0 Kudos
Wang__Jie1
Beginner
636 Views

Thanks for your reply.

1. It's a tensorflow model;

2. It's a custom trained model, I put the model in the attachment;

3. the command is:

python /opt/intel/openvino/deployment_tools/model_optimizer/mo_tf.py --input_model xx.pb --input input_0 --output output_0 --disable_nhwc_to_nchw  --input_shape [1,1024,1024,3]

Regards,

Jie

0 Kudos
johnny765123
Beginner
636 Views

I started getting this error when I did a new build of code and model that previously worked. I realised it was only with a debug build that I get this error.  Model is the default YOLOv3 in Darknet, converted via TensorFlow using the instructions in the documentation.  It was converted using the Model Optimizer in OpenVINO 2020.2.117, and run using that same release on macOS.  The only difference between a working build and one that gives the error above is that the working one links to:

@rpath/libinference_engine_legacy.dylib (compatibility version 0.0.0, current version 0.0.0)
@rpath/libinference_engine.dylib (compatibility version 0.0.0, current version 0.0.0)
@rpath/libinference_engine_c_api.dylib (compatibility version 0.0.0, current version 0.0.0)
@rpath/libinference_engine_nn_builder.dylib (compatibility version 0.0.0, current version 0.0.0)

...and the failing one links to (notice the "d" after each library name)

@rpath/libinference_engine_legacyd.dylib (compatibility version 0.0.0, current version 0.0.0)
@rpath/libinference_engined.dylib (compatibility version 0.0.0, current version 0.0.0)
@rpath/libinference_engine_c_apid.dylib (compatibility version 0.0.0, current version 0.0.0)
@rpath/libinference_engine_nn_builderd.dylib (compatibility version 0.0.0, current version 0.0.0)

 

0 Kudos
Reply