Error While Trying to Convert my own Custom Model to (IR representation)

khadijaazhar · ‎12-08-2020

[ ERROR ] -------------------------------------------------
[ ERROR ] ----------------- INTERNAL ERROR ----------------
[ ERROR ] Unexpected exception happened.
[ ERROR ] Please contact Model Optimizer developers and forward the following information:
[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID (<class 'extensions.middle.TensorIteratorMerge.TensorIteratorMerge'>)": 0
[ ERROR ] Traceback (most recent call last):
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 288, in apply_transform
for_graph_and_each_sub_graph_recursively(graph, replacer.find_and_replace_pattern)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 58, in for_graph_and_each_sub_graph_recursively
func(graph)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/utils/replacement_pattern.py", line 27, in find_and_replace_pattern
apply_pattern(graph, **self.pattern(), action=self.replace_pattern) # pylint: disable=no-member
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 95, in apply_pattern
action(graph, match)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/extensions/middle/TensorIteratorMerge.py", line 123, in replace_pattern
cond_data = match['condition'].out_node(0)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/graph/graph.py", line 239, in out_node
return self.out_nodes(control_flow=control_flow)[key]
KeyError: 0

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/main.py", line 298, in main
ret_code = driver(argv)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/main.py", line 265, in driver
ret_res = emit_ir(prepare_ir(argv), argv)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/main.py", line 234, in prepare_ir
graph = unified_pipeline(argv)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/pipeline/unified.py", line 29, in unified_pipeline
class_registration.ClassType.BACK_REPLACER
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 334, in apply_replacements
apply_replacements_list(graph, replacers_order)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 324, in apply_replacements_list
num_transforms=len(replacers_order))
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/utils/logger.py", line 124, in wrapper
function(*args, **kwargs)
File "/opt/intel/openvino_2021.1.110/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 312, in apply_transform
)) from err
Exception: Exception occurred during running replacer "REPLACEMENT_ID (<class 'extensions.middle.TensorIteratorMerge.TensorIteratorMerge'>)": 0

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

Iffa_Intel · ‎12-09-2020

Greetings,

Could you clarify your:

Model (ONNX, Tensorflow,etc)
OS (ubuntu 18.04 etc)
OpenVINO version ( I believe you are using 2021.1)
Were you able to run the example after the setup as in here
Did you ensure that setupvars was initialized beforehand?

Sincerely,

Iffa

khadijaazhar · ‎12-09-2020

1. I have both models (onnx, Tensorflow) both are not working.

2. OS i have Ubuntu 18.04.5 LTS.

3. Openvino version (openvino_2021.1.110).

4. Yes i have 3 examples running on following models .

demo_security_barrier_camera.sh is running in demo folder of openvino.
downloaded ssd_mobilenet model and generated inference on my video (Optimization and inference).
downloaded tensorflow-yolo-v3 (Model Optimization).

5. Yes set up is initialized beforehand.

I have attached errors on my onnx and tensorflow model.

When i try other than any custom model OpenVino is working fine.

Iffa_Intel · ‎12-09-2020

Please help to refer this for Tensorflow conversion and this for ONNX.

Besides, ensure that your topology is listed there. Otherwise, it is not supported.

Sincerely,

Iffa

khadijaazhar · ‎12-10-2020

yes for both models i am following these links.

Tried many solutions but didn't figure out why its not working

Iffa_Intel · ‎12-10-2020

In that case, can you share your files to me so that I could replicate?

Sincerely,

Iffa

khadijaazhar · ‎12-11-2020

how can i send you my model files .pb and .onnx

as on this forms these files are not supported.

Can you send me your email .

khadijaazhar · ‎12-13-2020

model files are attached

khadijaazhar · ‎12-14-2020

both model files are attached here that i have been working on

onnx and tensor flow both are not working errors are also attached.

I have tried these models on 2019 ,2020, 2021 versions but they are not working.

Thankyou for your cooperation

Iffa_Intel · ‎12-14-2020

Hi,

I had tested your model. Since it is .onnx file, it means that this file is an ONNX model.

It seems that your model is incompatible.

I suggest you proceed with this model archive (squeezenet - supported public ONNX topology).

You may refer to my attachments and here for guidance.

I converted the model using model optimizer (mo.py) and I ran the IR with the classification sample.

Sincerely,

Iffa

Iffa_Intel · ‎12-13-2020

Hi, you can ty to zip your file and attach it

Sincerely,

Iffa

Iffa_Intel · ‎12-21-2020

Greetings,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question

Sincerely,

Iffa