[ERROR] converting TF model with OpenVINO

[Selotkin__Vlad]

I'm trying to use the model optimizer to convert custom Unet like model. I'm using this command

python mo_tf.py --input_model ~/model/frozen_model.pb

But I receive an error:

[ ERROR ] Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

You can find my frozen model in the attachments.

Thank you in advance.

[JesusE_Intel]

Hi Vlad,

Which base model did you use to custom train your model? The OpenVINO toolkit supports Unet from this particular repository: https://github.com/kkweon/UNet-in-Tensorflow

Also, how did you freeze the model?

Regards,

Jesus