Error converting a model

KDeep · ‎03-13-2019

Hi

I am trying to convert a model (20180402-114759.pb )using mo_tf.py but the following error is occurred could u help me with that

ERROR:

Common parameters:

- Path to the Input Model: /opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/20180402-114759.pb

- Path for generated IR: /home/icsltd/Desktop/FP16

- IR output name: 20180402-114759

- 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: [127,127,127]

- Scale values: Not specified

- Scale factor: 256.0

- Precision of IR: FP16

- 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

- Offload unsupported operations: 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: 1.5.12.49d067a0

[ ERROR ] -------------------------------------------------

[ ERROR ] ----------------- INTERNAL ERROR ----------------

[ ERROR ] Unexpected exception happened.

[ ERROR ] Please contact Model Optimizer developers and forward the following information:

[ ERROR ] After re-inference of Mul1_13841 node, old and new shapes do not match. Old shapes: [array([], dtype=int64)], new shapes: [array([1])].

[ ERROR ] Traceback (most recent call last):

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/main.py", line 325, in main

return driver(argv)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/main.py", line 267, in driver

mean_scale_values=mean_scale)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/pipeline/tf.py", line 316, in tf2nx

scale_input(graph, scale)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/infer.py", line 338, in scale_input

action=lambda graph, match: _scale_input_action_mul(graph, match, scale)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 95, in apply_pattern

action(graph, match)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/infer.py", line 338, in <lambda>

action=lambda graph, match: _scale_input_action_mul(graph, match, scale)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/infer.py", line 318, in _scale_input_action_mul

mul_node.create_node_with_data(inputs=[mul_input, mul_data], data_nodes=toutput)

File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/ops/op.py", line 204, in create_node_with_data

[data_node.shape for data_node in data_nodes])

AssertionError: After re-inference of Mul1_13841 node, old and new shapes do not match. Old shapes: [array([], dtype=int64)], new shapes: [array([1])].

[ ERROR ] ---------------- END OF BUG REPORT --------------

[ ERROR ] -------------------------------------------------

Thanks&regards

Deepika

MartyG · ‎03-13-2019

Although I do not have direct experience of model conversion with mo_tf, the guide by Intel I have linked to below may be useful to check your process against to see if something has been missed.

https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow#inpage-nav-5