Model Optimizer error when convert frozen Tensor Flow Model

[Sirisak_T_Intel]

Hi Team

I try to convert model from Tensor Flow with mo_tf.py and found error message as below. Please help to suggest for root cause. Thank you.

---------------------------------------------------------------------------------------------------------------------------------------------------

vino@vino-demo:/opt/intel/openvino/deployment_tools/model_optimizer$ python3 mo_tf.py --input_model /home/vino/Downloads/INTF/frozen_inference_graph.pb
Model Optimizer arguments:
Common parameters:
    - Path to the Input Model:     /home/vino/Downloads/INTF/frozen_inference_graph.pb
    - Path for generated IR:     /opt/intel/openvino_2020.1.023/deployment_tools/model_optimizer/.
    - IR output name:     frozen_inference_graph
    - Log level:     ERROR
    - Batch:     Not specified, inherited from the model
    - Input layers:     Not specified, inherited from the model
    - Output layers:     Not specified, inherited from the model
    - Input shapes:     Not specified, inherited from the model
    - Mean values:     Not specified
    - Scale values:     Not specified
    - Scale factor:     Not specified
    - Precision of IR:     FP32
    - Enable fusing:     True
    - Enable grouped convolutions fusing:     True
    - Move mean values to preprocess section:     False
    - Reverse input channels:     False
TensorFlow specific parameters:
    - Input model in text protobuf format:     False
    - Path to model dump for TensorBoard:     None
    - List of shared libraries with TensorFlow custom layers implementation:     None
    - Update the configuration file with input/output node names:     None
    - Use configuration file used to generate the model with Object Detection API:     None
    - Operations to offload:     None
    - Patterns to offload:     None
    - Use the config file:     None
Model Optimizer version:     2020.1.0-61-gd349c3ba4a
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
[ ERROR ]  Shape [-1 -1 -1  3] is not fully defined for output 0 of "image_tensor". Use --input_shape with positive integers to override model input shapes.
[ ERROR ]  Cannot infer shapes or values for node "image_tensor".
[ ERROR ]  Not all output shapes were inferred or fully defined for node "image_tensor". 
 For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #40. 
[ ERROR ]  
[ ERROR ]  It can happen due to bug in custom shape infer function <function Parameter.infer at 0x7f44f8310048>.
[ ERROR ]  Or because the node inputs have incorrect values/shapes.
[ ERROR ]  Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ]  Run Model Optimizer with --log_level=DEBUG for more information.
[ ANALYSIS INFO ]  Your model looks like TensorFlow Object Detection API Model.
Check if all parameters are specified:
    --tensorflow_use_custom_operations_config
    --tensorflow_object_detection_api_pipeline_config
    --input_shape (optional)
    --reverse_input_channels (if you convert a model to use with the Inference Engine sample applications)
Detailed information about conversion of this model can be found at
https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_Object_Detection_API_Models.html
[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "image_tensor" node. 
 For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #38. 
---------------------------------------------------------------------------------------------------------------------------------------------------

[JAIVIN_J_Intel]

Hi Sirisak,

Please use the required command line parameters as mentioned in documentation on how to convert TensorFlow Object Detection API Models.

Also, refer the list of TensorFlow*-Specific Conversion Parameters.

Regards,

Jaivin

[Sirisak_T_Intel]

Hi Jaivin

Thnank you for your comment. I quite new for this and can you help to specific more which parameters I should use for this error showing.

Thank you

Sirisak

[JAIVIN_J_Intel]

Hi Sirisak,

Which model are you using? Is it a Public model or custom trained model?

To convert a TensorFlow* Object Detection API model, go to the <INSTALL_DIR>/deployment_tools/model_optimizer directory and run the mo_tf.py script with the following required parameters:

• --input_model <path_to_frozen.pb> — File with a pre-trained model (binary or text .pb file after freezing)
• --transformations_config <path_to_subgraph_replacement_configuration_file.json> — A subgraph replacement configuration file with transformations description. For the models downloaded from the TensorFlow* Object Detection API zoo, you can find the configuration files in the <INSTALL_DIR>/deployment_tools/model_optimizer/extensions/front/tf directory. 
• --tensorflow_object_detection_api_pipeline_config <path_to_pipeline.config> — A special configuration file that describes the topology hyper-parameters and structure of the TensorFlow Object Detection API model. For the models downloaded from the TensorFlow* Object Detection API zoo, the configuration file is named pipeline.config.

Try running the mo_tf.py script along with the parameters mentioned.

Regards,

Jaivin