[Good First Issue]: Extend ONNX Frontend with Function Mish-18

[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 extending OpenVINO ONNX Frontend with Function Mish.
Necessary help will be provided by ONNX Fronted team.

What needs to be done?

Operator details can be found in ONNX Operators
More details can be found in ONNX Changelog

1. Create .hpp and .cpp files here
2. Prepare an implementation of this operator in form of a function. Mish-18 should be placed in opset 1 namespace.
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

• ONNX Unique op support #15076
• ONNX CastLike operator tests #14936
• [ONNX FE] Extend ONNX FE for operation GenerateProposals #12510
• [ONNX] Extend ONNX Frontend with BlackmanWindow, HammingWindow and HannWindow operators #19428

Resources

• What is OpenVINO?
• Contribution guide
• Blog post on contributing to 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

[urbalke]

Hello, why do You have *Windows in 1st ToDo? Is this platform specific?

[ilya-lavrenov]

Hello, why do You have *Windows in 1st ToDo? Is this platform specific?

No, OpenVINO is cross platform product and steps are the same for all the systems.
Corrected description.

[sydarb]

Hey @p-wysocki I would like to work on this.

[p-wysocki]

Hello @sydarb, are you still working on this? I see that the PR is nearly finished.

Also, I am happy to announce that we have created a channel dedicated to Good First Issues support on our Intel DevHub Discord server! Join it to receive support, engage in discussions, ask questions and talk to OpenVINO developers.

[kshitij01042002]

Hi @p-wysocki is this issue up for grab? Also I tried joining the discord channel via the link provided but it says invalid link, can you please double check? Thanks.

[p-wysocki]

Hi @kshitij01042002, you can pick it up, thanks for taking a look!

The correct Discord link is https://discord.com/invite/7pVRxUwdWG, it has been corrected everywhere but in the issues created before we realized that the link is dead. Sorry for that! :)

[PRATHAM-SPS]

Hi @p-wysocki , it's nice to see you again! Could you please assign me this task? I'd like to do it.

[kshitij01042002]

Hi @p-wysocki I am currently working on #20562. You can assign this issue to @PRATHAM-SPS

[p-wysocki]

Hello, I assigned the task to @PRATHAM-SPS. :)

[PRATHAM-SPS]

Hello , please review the pull request I've created at the following link:-#22833. Your feedback would be greatly appreciated, @gkrivor and @p-wysocki.

[mitruska]

Hello @PRATHAM-SPS, thank you for this contribution.
I've reviewed the mentioned PR #22833, please take a look at the comments there.

[PRATHAM-SPS]

Hello @p-wysocki, can I get more such operators to wotk on ??

[p-wysocki]

Hi @PRATHAM-SPS, @mitruska mentioned she might have something for you. :) Let's wait for a response.

[mitruska]

Hello @PRATHAM-SPS, let me answer:)
Of course you can! Great to see your willing to continue contributing to OpenVINO.

Feel free to take any ticket from the Good First Issue Board ("Contributors Needed" column).
If you are looking for a similar task, I can recommend to try the following:

• [Good First Issue]: Extend ONNX Frontend with Multinomial-7 operator #21789

[PRATHAM-SPS]

Thankyou, @p-wysocki and @mitruska , I've taken responsibility for this task.