Refactor onnx graph ops function & registry

[alifahrri]

Type of changes

Please check the type of change your PR introduces: - [ ] Bugfix - [x] Feature - [ ] Code style update (formatting, renaming) - [ ] Refactoring (no functional changes, no api changes) - [ ] Build related changes - [ ] Documentation content changes - [ ] Other (please describe): ## What is the current behavior?

• close #95

Related issues :

What is the new behavior?

-

-

Checklist

• [ ] Unit tests pass locally with my changes
• [ ] I have added tests that prove my fix is effective or that my feature works
• [ ] I have added necessary documentation (if appropriate)
• [ ] Any dependent changes have been merged and published in downstream modules
• [ ] I have filled the [Unreleased] Changelog

[triwahyuu]

there is a good implementation for registry in mmdetection which use mmcv here https://github.com/open-mmlab/mmcv/blob/master/mmcv/utils/registry.py

example usage:

• https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/builder.py
• https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/detectors/yolo.py

might be a nice reference implementation for a more general registry

[alifahrri]

there is a good implementation for registry in mmdetection which use mmcv here https://github.com/open-mmlab/mmcv/blob/master/mmcv/utils/registry.py

example usage:

* https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/builder.py

* https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/detectors/yolo.py

might be a nice reference implementation for a more general registry

ok

[triwahyuu]

maybe in different PR for that, I have temporarily implement that for model registry in pytorch lightning integration

[alifahrri]

maybe in different PR for that, I have temporarily implement that for model registry in pytorch lightning integration

ok

[triwahyuu]

LGTM, sorry I accidentally closed the pr