Community
cancel
Showing results for 
Search instead for 
Did you mean: 
yu__jia
Beginner
110 Views

Deploy a custom model on NCS2 and report an error when converting the tf model to IR

I follow this link to freeze the model,http://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html#freeze-the-tensorflow-model

 but when I use :python mo_tf.py --input_meta_graph C:\Users\86178\PycharmProjects\python\cnn-1.ckpt.meta --input input/x-input --input_shape [100,784],

I got an error :[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.input_cut.InputCut'>): --input parameter was provided. Other inputs are needed for output computation. Provide more inputs or choose another place to cut the net.
 For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #27

what should I do?

 

0 Kudos
1 Reply
Shubha_R_Intel
Employee
110 Views

Dear yu, jia,

Perhaps your Tensorflow model is not supported. Please check The Model Optimizer Tensorflow Supported List to see which models have been validated by the OpenVino team.

Thanks,

Shubha

Reply