Model optimizer error: Exception occurred during running replacer "None"

[FVian]

Hi,

Environment:

Os: Ubuntu 18.04

Model Optimizer version: 2019.2.0-436-gf5827d4

I'm trying to convert EAST TensorFlow implementation model, that can be download in this link, to IR openvino model. This implementation can be found here. When I tried to run the following code:

python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo_tf.py --input_meta_graph east_icdar2015_resnet_v1_50_rbox/model.ckpt-49491.meta

The following error was presented:

Model Optimizer arguments:
Common parameters:
        - Path to the Input Model:      None
        - Path for generated IR:        /root/.
        - IR output name:       model.ckpt-49491
        - 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:        2019.2.0-436-gf5827d4
[ ERROR ]  Exception occurred during running replacer "None" (<class 'extensions.front.tf.assign_elimination.AssignSubElimination'>): Data flow edge coming out of AssignSub node model_1/resnet_v1_50/block3/unit_4/bottleneck_v1/conv2/BatchNorm/AssignMovingAvg

I've searched in the openvino forum to find a solution but I'm not able to solve. Can you help me?

Best regards,

Felipe Ximenes

[JesusE_Intel]

Hi Felipe,

The EAST model is currently not supported by the OpenVINO toolkit. However, there is a feature request for the development team to consider and potentially enable it in a future software release. We do have a text detection/recognition demo and models available, see the demo documentation here.

Please let me know if you have additional questions.

Regards,

Jesus 

[FVian]

Hi Jesus,

Thanks for your explanation. I am interested in porting EAST to openvino. Can I help development team to implement this feature, if possible? I don't know how exactly to do that but if you give me the directions, I can help. 

Regards,

Felipe Ximenes