sudo python3 mo_tf.py --input_model /home/shradhak/PythonML/convert-h5-to-pb/output_graph.pb --input_shape [1,3,28,28]
Model Optimizer arguments:
- Path to the Input Model: /home/shradhak/PythonML/convert-h5-to-pb/output_graph.pb
- Path for generated IR: /opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/.
- IR output name: output_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: [1,3,28,28]
- 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: 2019.1.1-83-g28dfbfd
[ ERROR ] Error while emitting attributes for layer strided_slice_1 (id = 29). It usually means that there is unsupported pattern around this node or unsupported combination of attributes.
I have got an error while converting a tensorflow model to openvino model. We had a model in the .meta and .index type of file which worked fine in my program so we converted it to a keras model which has an extension (.h5). Later on, we converted the keras model to tensorflow model with an extension (.pb). Now we want to run the file in an openvino application, for that we require the file to be converted to IR format. While doing that I got the above error.
How do I solve the error?
Dear Karnawat, Shradha,
Model Optimizer version: 2019.1.1-83-g28dfbfd is extremely old. Can you kindly upgrade to the latest 2019R2.01 and try again ? Pretty soon we are going to release R3 also.