[Good First Issue]: Align behavior of ONNX Frontend function ReduceL2-11, 13, 18 with original framework

[gkrivor]

Context

Neural networks are graphs consisting of nodes called operators. Each operator corresponds to a mathematical function, usually described in framework's documentation or an AI standard, such as ONNX.
OpenVINO ONNX Frontend is a component responsible for working with ONNX graphs and requires implementation of different ONNX operators in order to use ONNX models.
This task requires alignment between OpenVINO ONNX Frontend and original framework implementations of ReduceL2 for next list of opsets: opset 11, opset 13, opset 18
Necessary help will be provided by ONNX Fronted team.

What needs to be done?

First of all, please, take a look on ReduceMax PR for a reference.

Operator details can be found in ONNX Operators
More details can be found in ONNX Changelog: opset 11, opset 13, opset 18

1. Function already has a common implementation in OpenVINO. First of all, you need to review a documentation and prepare a table with differences between versions. It could be, for instance, a missing property, extended/reduced coverage of existing property, etc...
2. Copy existing implementation here to make it aligned with original framework (extend or reduce coverage of a common implementation). Copy of modified implementation should be in a defined opset, or in opset 1 in case it implements oldest implementation. Example of multi-opset operation.
3. Register the function in ops_bridge.cpp while keeping alphabetical order
4. Create test model(s) in ONNX models directory. OpenVINO test infrastructure then converts prototxt files to ONNX models - you will use those models later in tests
5. Add tests covering all use cases here
6. Check Python xfailed tests to find a test marked as a xfailed for added functionality. If any exist - remove corresponding lines and try to verify by using cmdline "python -m pytest -k name_of_test".
   More details in adding operators to ONNX Frontend guide

Example Pull Requests

No response

Resources

• Contribution guide - start here!
• Intel DevHub Discord channel - engage in discussions, ask questions and talk to OpenVINO developers
• What is OpenVINO?
• User documentation
• Guides on ONNX Frontend architecture and ONNX Frontend tests are also available
• You can also see a blog post on contributing to OpenVINO

Contact points

@gkrivor

Ticket

No response

[LucaTamSapienza]

.take

[github-actions]

Thank you for looking into this issue! Please let us know if you have any questions or require any help.

[LucaTamSapienza]

Version	Changes
ReduceL2-1	initial version
ReduceL2-11	axes range is now [-r, -r-1], r = rank(data)
ReduceL2-13	added support for T: tensor(bfloat16)
ReduceL2-18	axes attributes is now noop_with_empty_axes : int (default is 0) now the inputs can be non-differentiable axes (optional, non-differentiable) : tensor(int64)

[LucaTamSapienza]

Hi, currently I'm adding namespaces set_11, 13, 18 inside reduce.cpp and reduce.hpp. I have registered the functions inside ops_bridge.cpp. Before creating the tests, I would like to have some feedback to know if I am proceeding in the right way. I have some questions about how to implement the changes that I've mentioned above.

[mlukasze]

you can prepare draft PR to show us changes you've prepared - it may make discussion easier :)

[LucaTamSapienza]

I apologize for the delay; I had some work to do. Here is my draft PR #22741

[mlukasze]

No worries, thanks for the draft.