Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.

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

yu__jia
Beginner
181 Views

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
181 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