Model Optimizer error with Yolo_v3 model

[SC_Huang]

I was converting another yolo_v3 model with following arguments

/opt/intel/openvino/deployment_tools/model_optimizer$ python3 mo_tf.py --input_model ~/openvino_models/models/Customer/IONETWORK/frozen_darknet_yolov3_model.pb --tensorflow_use_custom_operations_config ./extensions/front/tf/yolo_v3.json --output_dir ~/openvino_models/models/Customer/IONETWORK/ --input_shape=[1,416,416,3] --data_type FP16

and get error like this

Model Optimizer version:     2019.1.1-83-g28dfbfd
/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/middle/passes/fusing/decomposition.py:65: RuntimeWarning: invalid value encountered in sqrt
  scale = 1. / np.sqrt(variance.value + eps)
[ ERROR ]  -------------------------------------------------
[ ERROR ]  ----------------- INTERNAL ERROR ----------------
[ ERROR ]  Unexpected exception happened.
[ ERROR ]  Please contact Model Optimizer developers and forward the following information:
[ ERROR ]  
[ ERROR ]  Traceback (most recent call last):
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/main.py", line 312, in main
    return driver(argv)
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/main.py", line 263, in driver
    is_binary=not argv.input_model_is_text)
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/pipeline/tf.py", line 141, in tf2nx
    graph_clean_up_tf(graph)
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/middle/passes/eliminate.py", line 186, in graph_clean_up_tf
    graph_clean_up(graph, ['TFCustomSubgraphCall', 'Shape'])
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/middle/passes/eliminate.py", line 181, in graph_clean_up
    add_constant_operations(graph)
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/middle/passes/eliminate.py", line 145, in add_constant_operations
    Const(graph, dict(value=node.value, shape=np.array(node.value.shape))).create_node_with_data(data_nodes=node)
  File "/opt/intel/openvino_2019.1.144/deployment_tools/model_optimizer/mo/ops/op.py", line 207, in create_node_with_data
    [np.array_equal(old_data_value[id], data_node.value) for id, data_node in enumerate(data_nodes)])
AssertionError
 
[ ERROR ]  ---------------- END OF BUG REPORT --------------
[ ERROR ]  -------------------------------------------------

What caused this problem?

Thank you.

[Shubha_R_Intel]

Dear SC Huang,

That is a strange error. Are you sure that you installed all the model optimizer pre-requisites ? What version of Tensorflow are you using ? My guess is that you did not perform Configure the Model Optimizer in your installation steps.

Thanks,

Shubha

[SC_Huang]

Shubha R. (Intel) wrote:

Dear SC Huang,

That is a strange error. Are you sure that you installed all the model optimizer pre-requisites ? What version of Tensorflow are you using ? My guess is that you did not perform Configure the Model Optimizer in your installation steps.

Thanks,

Shubha

Thanks Shubha,

But I'm sure I have installed those prequisites, I've successfully optimize most models downloaded from downloader.py before.

My tensorflow version is 1.12.0.

Retry after did MO config again, the Error is still the same.