I have trained my ssdlite_mobilenet_v3 in tensorflow and export as frozen_inference_graph.pb. I am able to run it. Now I would like to convert to openvino Inference Engine files (.xml and .bin). But I encounter following errors. I include my command line below and also you may download my model files in a sample_model_inference.zip here. Could anyone help me to find out what's missing? or how to fix it. Thanks a lot.
Command line:
mo_tf.py --input_model ../sample_model_inference/frozen_inference_graph.pb --transformations_config /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/ssd_v2_support.json --tensorflow_object_detection_api_pipeline_config ../sample_model_inference/pipeline.config
Error messages:
(openvino) paul@tensor:~/tf1.15/models/research/object_detection/samples/sample_model_ir$ mo_tf.py --input_model ../sample_model_inference/frozen_inference_graph.pb --transformations_config /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/ssd_v2_support.json --tensorflow_object_detection_api_pipeline_config ../sample_model_inference/pipeline.config
Model Optimizer arguments:
Common parameters:
- Path to the Input Model: /home/paul/tf1.15/models/research/object_detection/samples/sample_model_ir/../sample_model_inference/frozen_inference_graph.pb
- Path for generated IR: /home/paul/tf1.15/models/research/object_detection/samples/sample_model_ir/.
- 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: /home/paul/tf1.15/models/research/object_detection/samples/sample_model_ir/../sample_model_inference/pipeline.config
- Operations to offload: None
- Patterns to offload: None
- Use the config file: None
Model Optimizer version: 2020.1.0-61-gd349c3ba4a
/home/paul/openvino/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:493: 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)])
/home/paul/openvino/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:494: 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)])
/home/paul/openvino/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:495: 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)])
/home/paul/openvino/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:496: 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)])
/home/paul/openvino/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:497: 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)])
/home/paul/openvino/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:502: 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)])
The Preprocessor block has been removed. Only nodes performing mean value subtraction and scaling (if applicable) are kept.
[ ERROR ] Failed to match nodes from custom replacement description with id 'ObjectDetectionAPISSDPostprocessorReplacement':
It means model and custom replacement description are incompatible.
Try to correct custom replacement description according to documentation with respect to model node names
[ ERROR ] Cannot infer shapes or values for node "Postprocessor/Cast_1".
[ ERROR ] 0
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function .
[ 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" (): Stopped shape/value propagation at "Postprocessor/Cast_1" 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.
