[Bug]: Trilu second input must be a scalar

[jikechao]

OpenVINO Version

openvino-nightly 2023.2.0.dev20231101

Operating System

Ubuntu 18.04 (LTS)

Device used for inference

CPU

Framework

ONNX

Model used

https://github.com/jikechao/onnx_models/blob/main/Trilu.onnx

Issue description

OpenVINO converts the ONNX model failed and threw "Trilu second input must be a scalar".

However, the given ONNX model is a valid model which can execute inference well.
Thus, we hope OpenVINO can also support it rather than crash!

Step-by-step reproduction

import openvino as ov
onnx_model_path = 'Trilu.onnx'
ov_model = ov.convert_model(onnx_model_path)

Relevant log output

Traceback (most recent call last):
  File "test.py", line 15, in <module>
    ov_model = ov.convert_model(onnx_model_path)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert.py", line 101, in convert_model
    ov_model, _ = _convert(cli_parser, params, True)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 524, in _convert
    raise e
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 476, in _convert
    ov_model = driver(argv, {"conversion_parameters": non_default_params})
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 226, in driver
    ov_model = moc_emit_ir(prepare_ir(argv), argv)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 172, in prepare_ir
    ov_model = moc_pipeline(argv, moc_front_end)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\moc_frontend\pipeline.py", line 247, in moc_pipeline
    ov_model = moc_front_end.convert(input_model)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\frontend\frontend.py", line 18, in convert
    converted_model = super().convert(model)
RuntimeError: Check 'error_message.empty()' failed at src\frontends\onnx\frontend\src\frontend.cpp:124:
Errors during ONNX translation: 
Check '(inputs[1].get_partial_shape().compatible({}))' failed at src\frontends\onnx\frontend\src\op\trilu.cpp:30:
While validating ONNX node '<Node(Trilu): y>':
Trilu second input must be a scalar

Issue submission checklist

• I'm reporting an issue. It's not a question.
• I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
• There is reproducer code and related data files such as images, videos, models, etc.

[rkazants]

Hi @jikechao,

According to the Trilu specification (https://github.com/onnx/onnx/blob/main/docs/Changelog.md#Trilu-14), the second input is 0D tensor (or scalar). I think it is a bug in either software creating such ONNX model (PyTorch export to onnx, for example) or ONNX specification. I am leaning the first one.

@gkrivor, anyway let us fix it in OV side because the fix should be easy.

Best regards,
Roman

[jikechao]

@rkazants @gkrivor Thanks for your plan to fix the bug in the OV side. It can increase the robustness of OV.