Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
6059 Discussions

OPENVINO-2022 Please contact Model Optimizer developers and forward the following information

efnna
Beginner
511 Views

Hey,

I am trying to use MO on a tf 1.4 model,
but i get an error 

 

 

[ 2022-03-29 11:05:37,251 ] [ DEBUG ] [ infer:168 ] Outputs:
[ 2022-03-29 11:05:37,252 ] [ DEBUG ] [ infer:19 ] output[0]: shape = [1], value = [0]
[ 2022-03-29 11:05:37,272 ] [ DEBUG ] [ infer:343 ] Executed reverse infer for node 'probability'
[ 2022-03-29 11:05:37,274 ] [ DEBUG ] [ infer:347 ] --------------------
[ 2022-03-29 11:05:37,275 ] [ DEBUG ] [ infer:348 ] Reverse infer for probability
[ 2022-03-29 11:05:37,275 ] [ DEBUG ] [ infer:349 ] Op: Identity
[ 2022-03-29 11:05:37,275 ] [ DEBUG ] [ infer:350 ] Outputs:
[ 2022-03-29 11:05:37,275 ] [ DEBUG ] [ infer:19 ] outputs[0]: shape = <UNKNOWN>, value = <UNKNOWN>
[ 2022-03-29 11:05:37,275 ] [ DEBUG ] [ infer:353 ] Inputs:
[ 2022-03-29 11:05:37,275 ] [ DEBUG ] [ infer:19 ] inputs[0]: shape = <UNKNOWN>, value = <UNKNOWN>
[ 2022-03-29 11:05:37,276 ] [ DEBUG ] [ infer:343 ] Executed reverse infer for node 'cond_2/pred_id'
[ 2022-03-29 11:05:37,276 ] [ DEBUG ] [ infer:347 ] --------------------
[ 2022-03-29 11:05:37,277 ] [ DEBUG ] [ infer:348 ] Reverse infer for cond_2/pred_id
[ 2022-03-29 11:05:37,277 ] [ DEBUG ] [ infer:349 ] Op: Identity
[ 2022-03-29 11:05:37,277 ] [ DEBUG ] [ infer:350 ] Outputs:
[ 2022-03-29 11:05:37,277 ] [ DEBUG ] [ infer:19 ] outputs[0]: shape = <UNKNOWN>, value = <UNKNOWN>
[ 2022-03-29 11:05:37,277 ] [ DEBUG ] [ infer:353 ] Inputs:
[ 2022-03-29 11:05:37,277 ] [ DEBUG ] [ infer:19 ] inputs[0]: shape = <UNKNOWN>, value = <UNKNOWN>
[ 2022-03-29 11:05:37,278 ] [ DEBUG ] [ infer:343 ] Executed reverse infer for node 'cond_2/switch_t'
[ 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 'openvino.tools.mo.middle.PartialInfer.PartialInfer'>)":
[ ERROR ] Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/utils/class_registration.py", line 276, in apply_transform
replacer.find_and_replace_pattern(graph)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/middle/PartialInfer.py", line 41, in find_and_replace_pattern
partial_infer(graph)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/middle/passes/infer.py", line 113, in partial_infer
reverse_infer(graph, nodes)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/middle/passes/infer.py", line 344, in reverse_infer
node.reverse_infer(node)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/ops/identity.py", line 20, in <lambda>
'reverse_infer': lambda node: reverse_bypass_infer(node, in_ports=[0]),
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/front/common/partial_infer/utils.py", line 332, in reverse_bypass_infer
assert node.is_out_port_connected(0)
AssertionError

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

Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/main.py", line 533, in main
ret_code = driver(argv)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/main.py", line 489, in driver
graph, ngraph_function = prepare_ir(argv)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/main.py", line 407, in prepare_ir
graph = unified_pipeline(argv)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/pipeline/unified.py", line 17, in unified_pipeline
class_registration.ClassType.BACK_REPLACER
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/utils/class_registration.py", line 328, in apply_replacements
apply_replacements_list(graph, replacers_order)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/utils/class_registration.py", line 318, in apply_replacements_list
num_transforms=len(replacers_order))
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/utils/logger.py", line 112, in wrapper
function(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/openvino/tools/mo/utils/class_registration.py", line 306, in apply_transform
)) from err
Exception: Exception occurred during running replacer "REPLACEMENT_ID (<class 'openvino.tools.mo.middle.PartialInfer.PartialInfer'>)":

[ ERROR ] ---------------- END OF BUG REPORT --------------
[ ERROR ] -------------------------------------------------
OpenVino export failure: Command 'mo --saved_model_dir models/aocr-model --log_level=DEBUG' returned non-zero exit status 1.

0 Kudos
6 Replies
Zulkifli_Intel
Moderator
399 Views

Hello Efnna,


Thank you for reaching out to us.


Please provide your model, MO command used, and your Operating System to us. This information will help us to investigate this issue further.


Sincerely,

Zulkifli


efnna
Beginner
354 Views

I'm using Ubuntu 20.04.3 LTS, ocr tflite model.

Снимок экрана 2022-04-04 в 14.54.14.png

 

 

 

 

 

Tried submitting input shape [1] but it didn't work at the input of the model:

2022-04-04 15.22.30.jpg

Help me please

Zulkifli_Intel
Moderator
335 Views

Hello Efnna,

 

Model Optimizer does not support .tflite file to IR format conversion natively. Model Optimizer currently only supports a few frozen quantized topologies hosted on TensorFlow Lite site.

 

This information is available in the subsection "Supported Frozen Quantized Topologies" under the section Supported Topologies.

 

However, the frozen model file (.pb file) is required for conversion to IR format by Model Optimizer.


Sincerely,

Zulkifli


efnna
Beginner
326 Views

My model consists of a special directory with a .pb file and several subfolders: variables, assets

 

Sincerely,

Efnna

Zulkifli_Intel
Moderator
303 Views

Hello Efnna,


Please share with us your model for replication purposes.


Sincerely,

Zulkifli


Zulkifli_Intel
Moderator
242 Views

Hello Efnna,


Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.


Sincerely,

Zulkifli


Reply